Unicode text, UTF-8 text
1
{
2
"cells": [
3
{
4
"cell_type": "markdown",
5
"id": "9a67092a",
6
"metadata": {},
7
"source": [
8
"# Training notebook"
9
]
10
},
11
{
12
"cell_type": "markdown",
13
"id": "4dfbc71a-a78d-4ebb-ab77-276dab5821c9",
14
"metadata": {},
15
"source": [
16
"## Please install the requirements\n",
17
"(if you don't have them already)"
18
]
19
},
20
{
21
"cell_type": "code",
22
"execution_count": 11,
23
"id": "20c8a661575d1c6f",
24
"metadata": {
25
"ExecuteTime": {
26
"end_time": "2024-05-15T16:18:22.226800Z",
27
"start_time": "2024-05-15T16:15:37.312969Z"
28
}
29
},
30
"outputs": [
31
{
32
"name": "stdout",
33
"output_type": "stream",
34
"text": [
35
"Requirement already satisfied: torchvision in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (0.18.0)\n",
36
"Requirement already satisfied: numpy in /home/vlad/.local/lib/python3.10/site-packages (from torchvision) (1.23.5)\n",
37
"Requirement already satisfied: torch==2.3.0 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torchvision) (2.3.0)\n",
38
"Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /home/vlad/.local/lib/python3.10/site-packages (from torchvision) (9.5.0)\n",
39
"Requirement already satisfied: filelock in /home/vlad/.local/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (3.12.2)\n",
40
"Requirement already satisfied: typing-extensions>=4.8.0 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (4.11.0)\n",
41
"Requirement already satisfied: sympy in /home/vlad/.local/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (1.12)\n",
42
"Requirement already satisfied: networkx in /home/vlad/.local/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (3.1)\n",
43
"Requirement already satisfied: jinja2 in /home/vlad/.local/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (3.1.2)\n",
44
"Requirement already satisfied: fsspec in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (2024.5.0)\n",
45
"Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (12.1.105)\n",
46
"Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /home/vlad/.local/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (12.1.105)\n",
47
"Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (12.1.105)\n",
48
"Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /home/vlad/.local/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (8.9.2.26)\n",
49
"Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /home/vlad/.local/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (12.1.3.1)\n",
50
"Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (11.0.2.54)\n",
51
"Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (10.3.2.106)\n",
52
"Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (11.4.5.107)\n",
53
"Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (12.1.0.106)\n",
54
"Requirement already satisfied: nvidia-nccl-cu12==2.20.5 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (2.20.5)\n",
55
"Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (12.1.105)\n",
56
"Requirement already satisfied: triton==2.3.0 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch==2.3.0->torchvision) (2.3.0)\n",
57
"Requirement already satisfied: nvidia-nvjitlink-cu12 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch==2.3.0->torchvision) (12.4.127)\n",
58
"Requirement already satisfied: MarkupSafe>=2.0 in /home/vlad/.local/lib/python3.10/site-packages (from jinja2->torch==2.3.0->torchvision) (2.1.3)\n",
59
"Requirement already satisfied: mpmath>=0.19 in /home/vlad/.local/lib/python3.10/site-packages (from sympy->torch==2.3.0->torchvision) (1.3.0)\n",
60
"\n",
61
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
62
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
63
"Note: you may need to restart the kernel to use updated packages.\n",
64
"Requirement already satisfied: torch in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (2.3.0)\n",
65
"Requirement already satisfied: torchvision in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (0.18.0)\n",
66
"Requirement already satisfied: filelock in /home/vlad/.local/lib/python3.10/site-packages (from torch) (3.12.2)\n",
67
"Requirement already satisfied: typing-extensions>=4.8.0 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch) (4.11.0)\n",
68
"Requirement already satisfied: sympy in /home/vlad/.local/lib/python3.10/site-packages (from torch) (1.12)\n",
69
"Requirement already satisfied: networkx in /home/vlad/.local/lib/python3.10/site-packages (from torch) (3.1)\n",
70
"Requirement already satisfied: jinja2 in /home/vlad/.local/lib/python3.10/site-packages (from torch) (3.1.2)\n",
71
"Requirement already satisfied: fsspec in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch) (2024.5.0)\n",
72
"Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch) (12.1.105)\n",
73
"Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /home/vlad/.local/lib/python3.10/site-packages (from torch) (12.1.105)\n",
74
"Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch) (12.1.105)\n",
75
"Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /home/vlad/.local/lib/python3.10/site-packages (from torch) (8.9.2.26)\n",
76
"Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /home/vlad/.local/lib/python3.10/site-packages (from torch) (12.1.3.1)\n",
77
"Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch) (11.0.2.54)\n",
78
"Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch) (10.3.2.106)\n",
79
"Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch) (11.4.5.107)\n",
80
"Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch) (12.1.0.106)\n",
81
"Requirement already satisfied: nvidia-nccl-cu12==2.20.5 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch) (2.20.5)\n",
82
"Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch) (12.1.105)\n",
83
"Requirement already satisfied: triton==2.3.0 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch) (2.3.0)\n",
84
"Requirement already satisfied: nvidia-nvjitlink-cu12 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch) (12.4.127)\n",
85
"Requirement already satisfied: numpy in /home/vlad/.local/lib/python3.10/site-packages (from torchvision) (1.23.5)\n",
86
"Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in /home/vlad/.local/lib/python3.10/site-packages (from torchvision) (9.5.0)\n",
87
"Requirement already satisfied: MarkupSafe>=2.0 in /home/vlad/.local/lib/python3.10/site-packages (from jinja2->torch) (2.1.3)\n",
88
"Requirement already satisfied: mpmath>=0.19 in /home/vlad/.local/lib/python3.10/site-packages (from sympy->torch) (1.3.0)\n",
89
"\n",
90
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
91
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
92
"Note: you may need to restart the kernel to use updated packages.\n",
93
"Requirement already satisfied: ultralytics in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (8.2.15)\n",
94
"Collecting ultralytics\n",
95
" Obtaining dependency information for ultralytics from https://files.pythonhosted.org/packages/d0/90/640c06dfa3e3ac84418bd0357e9b1220742a95d3ec7f66475d0509754bc1/ultralytics-8.2.17-py3-none-any.whl.metadata\n",
96
" Downloading ultralytics-8.2.17-py3-none-any.whl.metadata (40 kB)\n",
97
"\u001b[2K \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.7/40.7 kB\u001b[0m \u001b[31m1.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
98
"\u001b[?25hRequirement already satisfied: matplotlib>=3.3.0 in /home/vlad/.local/lib/python3.10/site-packages (from ultralytics) (3.7.1)\n",
99
"Requirement already satisfied: opencv-python>=4.6.0 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from ultralytics) (4.9.0.80)\n",
100
"Requirement already satisfied: pillow>=7.1.2 in /home/vlad/.local/lib/python3.10/site-packages (from ultralytics) (9.5.0)\n",
101
"Requirement already satisfied: pyyaml>=5.3.1 in /home/vlad/.local/lib/python3.10/site-packages (from ultralytics) (6.0)\n",
102
"Requirement already satisfied: requests>=2.23.0 in /home/vlad/.local/lib/python3.10/site-packages (from ultralytics) (2.31.0)\n",
103
"Requirement already satisfied: scipy>=1.4.1 in /home/vlad/.local/lib/python3.10/site-packages (from ultralytics) (1.10.1)\n",
104
"Requirement already satisfied: torch>=1.8.0 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from ultralytics) (2.3.0)\n",
105
"Requirement already satisfied: torchvision>=0.9.0 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from ultralytics) (0.18.0)\n",
106
"Requirement already satisfied: tqdm>=4.64.0 in /home/vlad/.local/lib/python3.10/site-packages (from ultralytics) (4.65.0)\n",
107
"Requirement already satisfied: psutil in /home/vlad/.local/lib/python3.10/site-packages (from ultralytics) (5.9.5)\n",
108
"Requirement already satisfied: py-cpuinfo in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from ultralytics) (9.0.0)\n",
109
"Requirement already satisfied: thop>=0.1.1 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from ultralytics) (0.1.1.post2209072238)\n",
110
"Requirement already satisfied: pandas>=1.1.4 in /home/vlad/.local/lib/python3.10/site-packages (from ultralytics) (2.0.2)\n",
111
"Requirement already satisfied: seaborn>=0.11.0 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from ultralytics) (0.13.2)\n",
112
"Requirement already satisfied: contourpy>=1.0.1 in /home/vlad/.local/lib/python3.10/site-packages (from matplotlib>=3.3.0->ultralytics) (1.1.0)\n",
113
"Requirement already satisfied: cycler>=0.10 in /home/vlad/.local/lib/python3.10/site-packages (from matplotlib>=3.3.0->ultralytics) (0.11.0)\n",
114
"Requirement already satisfied: fonttools>=4.22.0 in /home/vlad/.local/lib/python3.10/site-packages (from matplotlib>=3.3.0->ultralytics) (4.40.0)\n",
115
"Requirement already satisfied: kiwisolver>=1.0.1 in /home/vlad/.local/lib/python3.10/site-packages (from matplotlib>=3.3.0->ultralytics) (1.4.4)\n",
116
"Requirement already satisfied: numpy>=1.20 in /home/vlad/.local/lib/python3.10/site-packages (from matplotlib>=3.3.0->ultralytics) (1.23.5)\n",
117
"Requirement already satisfied: packaging>=20.0 in /home/vlad/.local/lib/python3.10/site-packages (from matplotlib>=3.3.0->ultralytics) (23.1)\n",
118
"Requirement already satisfied: pyparsing>=2.3.1 in /home/vlad/.local/lib/python3.10/site-packages (from matplotlib>=3.3.0->ultralytics) (3.1.0)\n",
119
"Requirement already satisfied: python-dateutil>=2.7 in /home/vlad/.local/lib/python3.10/site-packages (from matplotlib>=3.3.0->ultralytics) (2.8.2)\n",
120
"Requirement already satisfied: pytz>=2020.1 in /home/vlad/.local/lib/python3.10/site-packages (from pandas>=1.1.4->ultralytics) (2023.3)\n",
121
"Requirement already satisfied: tzdata>=2022.1 in /home/vlad/.local/lib/python3.10/site-packages (from pandas>=1.1.4->ultralytics) (2023.3)\n",
122
"Requirement already satisfied: charset-normalizer<4,>=2 in /home/vlad/.local/lib/python3.10/site-packages (from requests>=2.23.0->ultralytics) (2.0.12)\n",
123
"Requirement already satisfied: idna<4,>=2.5 in /home/vlad/.local/lib/python3.10/site-packages (from requests>=2.23.0->ultralytics) (3.4)\n",
124
"Requirement already satisfied: urllib3<3,>=1.21.1 in /home/vlad/.local/lib/python3.10/site-packages (from requests>=2.23.0->ultralytics) (1.26.16)\n",
125
"Requirement already satisfied: certifi>=2017.4.17 in /home/vlad/.local/lib/python3.10/site-packages (from requests>=2.23.0->ultralytics) (2023.5.7)\n",
126
"Requirement already satisfied: filelock in /home/vlad/.local/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (3.12.2)\n",
127
"Requirement already satisfied: typing-extensions>=4.8.0 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (4.11.0)\n",
128
"Requirement already satisfied: sympy in /home/vlad/.local/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (1.12)\n",
129
"Requirement already satisfied: networkx in /home/vlad/.local/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (3.1)\n",
130
"Requirement already satisfied: jinja2 in /home/vlad/.local/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (3.1.2)\n",
131
"Requirement already satisfied: fsspec in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (2024.5.0)\n",
132
"Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (12.1.105)\n",
133
"Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /home/vlad/.local/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (12.1.105)\n",
134
"Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (12.1.105)\n",
135
"Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /home/vlad/.local/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (8.9.2.26)\n",
136
"Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /home/vlad/.local/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (12.1.3.1)\n",
137
"Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (11.0.2.54)\n",
138
"Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (10.3.2.106)\n",
139
"Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (11.4.5.107)\n",
140
"Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (12.1.0.106)\n",
141
"Requirement already satisfied: nvidia-nccl-cu12==2.20.5 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (2.20.5)\n",
142
"Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (12.1.105)\n",
143
"Requirement already satisfied: triton==2.3.0 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from torch>=1.8.0->ultralytics) (2.3.0)\n",
144
"Requirement already satisfied: nvidia-nvjitlink-cu12 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.8.0->ultralytics) (12.4.127)\n",
145
"Requirement already satisfied: six>=1.5 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from python-dateutil>=2.7->matplotlib>=3.3.0->ultralytics) (1.16.0)\n",
146
"Requirement already satisfied: MarkupSafe>=2.0 in /home/vlad/.local/lib/python3.10/site-packages (from jinja2->torch>=1.8.0->ultralytics) (2.1.3)\n",
147
"Requirement already satisfied: mpmath>=0.19 in /home/vlad/.local/lib/python3.10/site-packages (from sympy->torch>=1.8.0->ultralytics) (1.3.0)\n",
148
"Downloading ultralytics-8.2.17-py3-none-any.whl (757 kB)\n",
149
"\u001b[2K \u001b[38;2;114;156;31m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m757.0/757.0 kB\u001b[0m \u001b[31m6.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m[36m0:00:01\u001b[0mm eta \u001b[36m0:00:01\u001b[0m\n",
150
"\u001b[?25hInstalling collected packages: ultralytics\n",
151
" Attempting uninstall: ultralytics\n",
152
" Found existing installation: ultralytics 8.2.15\n",
153
" Uninstalling ultralytics-8.2.15:\n",
154
" Successfully uninstalled ultralytics-8.2.15\n",
155
"Successfully installed ultralytics-8.2.17\n",
156
"\n",
157
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
158
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
159
"Note: you may need to restart the kernel to use updated packages.\n",
160
"Requirement already satisfied: pillow_heif in /home/vlad/.local/lib/python3.10/site-packages (0.16.0)\n",
161
"Requirement already satisfied: pillow>=9.5.0 in /home/vlad/.local/lib/python3.10/site-packages (from pillow_heif) (9.5.0)\n",
162
"\n",
163
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
164
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
165
"Note: you may need to restart the kernel to use updated packages.\n",
166
"Requirement already satisfied: plotly in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (5.22.0)\n",
167
"Requirement already satisfied: tenacity>=6.2.0 in /home/vlad/miniconda3/envs/tf/lib/python3.10/site-packages (from plotly) (8.3.0)\n",
168
"Requirement already satisfied: packaging in /home/vlad/.local/lib/python3.10/site-packages (from plotly) (23.1)\n",
169
"\n",
170
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
171
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
172
"Note: you may need to restart the kernel to use updated packages.\n",
173
"Requirement already satisfied: Pillow in /home/vlad/.local/lib/python3.10/site-packages (9.5.0)\n",
174
"\n",
175
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
176
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
177
"Note: you may need to restart the kernel to use updated packages.\n",
178
"Requirement already satisfied: tqdm in /home/vlad/.local/lib/python3.10/site-packages (4.65.0)\n",
179
"\n",
180
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m23.2.1\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.0\u001b[0m\n",
181
"\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpip install --upgrade pip\u001b[0m\n",
182
"Note: you may need to restart the kernel to use updated packages.\n"
183
]
184
}
185
],
186
"source": [
187
"%pip install torchvision\n",
188
"%pip install torch torchvision\n",
189
"%pip install --upgrade ultralytics\n",
190
"%pip install pillow_heif\n",
191
"%pip install plotly\n",
192
"%pip install Pillow\n",
193
"%pip install tqdm"
194
]
195
},
196
{
197
"cell_type": "code",
198
"execution_count": 2,
199
"id": "45105e3c6e3463b4",
200
"metadata": {
201
"ExecuteTime": {
202
"end_time": "2024-05-15T12:50:26.052184Z",
203
"start_time": "2024-05-15T12:50:25.148297Z"
204
}
205
},
206
"outputs": [],
207
"source": [
208
"import os # for file operations\n",
209
"import json # for loading the annotations file\n",
210
"from PIL import Image, ImageDraw, ImageOps, ImageEnhance # for processing the image data\n",
211
"import numpy as np\n",
212
"from random import shuffle\n",
213
"import nvidia.cudnn\n",
214
"import torch\n",
215
"from pillow_heif import register_heif_opener\n",
216
"\n",
217
"os.environ[\"CUDA_VISIBLE_DEVICES\"] = \"1\""
218
]
219
},
220
{
221
"cell_type": "markdown",
222
"id": "a9af0815fbb0b5f3",
223
"metadata": {},
224
"source": [
225
"## constants"
226
]
227
},
228
{
229
"cell_type": "code",
230
"execution_count": 3,
231
"id": "3af63db86b518835",
232
"metadata": {
233
"ExecuteTime": {
234
"end_time": "2024-05-18T06:54:53.852571Z",
235
"start_time": "2024-05-18T06:54:53.847457Z"
236
}
237
},
238
"outputs": [],
239
"source": [
240
"# Correctly set CWD\n",
241
"os.chdir(\"/home/vlad/Desktop/litewaste\")\n",
242
"DATA_PATH = \"./data/\" # must contain multiple subdirectories - one for each class\n",
243
"ANNOTATIONS_PATH = \"./via-annotations.json\" # relative to the notebook\n",
244
"\n",
245
"BATCH_SIZE = 8\n",
246
"\n",
247
"CLASS_NAMES = sorted(list(set([os.path.basename(f).split(\",\")[0] for f in os.scandir(DATA_PATH) if f.is_dir()]))) # automatically generated\n",
248
"ALL_CLASS_NAMES = sorted(list(set([os.path.basename(f) for f in os.scandir(DATA_PATH) if f.is_dir()])))\n",
249
"CLASS_COUNT = len(CLASS_NAMES)"
250
]
251
},
252
{
253
"cell_type": "code",
254
"execution_count": 4,
255
"id": "a2bec18569751b3b",
256
"metadata": {},
257
"outputs": [],
258
"source": [
259
"with open(ANNOTATIONS_PATH, \"r\") as via_data:\n",
260
" via_annotations = json.load(via_data)"
261
]
262
},
263
{
264
"cell_type": "code",
265
"execution_count": 4,
266
"id": "1cffea67a1a66a0e",
267
"metadata": {},
268
"outputs": [
269
{
270
"name": "stdout",
271
"output_type": "stream",
272
"text": [
273
"['Electronic', 'Glass', 'Medical', 'Metal', 'Organic', 'Other', 'Paper', 'Plastic', 'Textile', 'Wood']\n"
274
]
275
}
276
],
277
"source": [
278
"print(CLASS_NAMES)"
279
]
280
},
281
{
282
"cell_type": "markdown",
283
"id": "a2e58dbd6685dbb4",
284
"metadata": {},
285
"source": [
286
"## segmentation"
287
]
288
},
289
{
290
"cell_type": "code",
291
"execution_count": 5,
292
"id": "bfdbbe283d63cffc",
293
"metadata": {
294
"ExecuteTime": {
295
"end_time": "2024-05-18T06:54:58.176604Z",
296
"start_time": "2024-05-18T06:54:57.691900Z"
297
}
298
},
299
"outputs": [
300
{
301
"data": {
302
"text/html": [
303
"<iframe\n",
304
" scrolling=\"no\"\n",
305
" width=\"2420px\"\n",
306
" height=\"1220\"\n",
307
" src=\"iframe_figures/figure_5.html\"\n",
308
" frameborder=\"0\"\n",
309
" allowfullscreen\n",
310
"></iframe>\n"
311
]
312
},
313
"metadata": {},
314
"output_type": "display_data"
315
}
316
],
317
"source": [
318
"import os\n",
319
"import collections\n",
320
"import plotly.express as px\n",
321
"import plotly.io as pio\n",
322
"pio.renderers.default = 'iframe'\n",
323
"\n",
324
"subcategories = collections.defaultdict(list)\n",
325
"\n",
326
"for klass in ALL_CLASS_NAMES:\n",
327
" main, _, sub = klass.partition(\", \")\n",
328
" file_count = len(os.listdir(os.path.join(DATA_PATH, klass))) # count files in each subcategory directory\n",
329
" subcategories[main].append((sub, file_count))\n",
330
"\n",
331
"# Prepare data for plotting\n",
332
"categories = []\n",
333
"subcategories_list = []\n",
334
"values = []\n",
335
"\n",
336
"for main, subs in subcategories.items():\n",
337
" for sub, count in subs:\n",
338
" categories.append(main)\n",
339
" subcategories_list.append(sub)\n",
340
" values.append(count)\n",
341
"\n",
342
"# Create DataFrame\n",
343
"import pandas as pd\n",
344
"df = pd.DataFrame({\n",
345
" \"Category\": categories,\n",
346
" \"Subcategory\": subcategories_list,\n",
347
" \"Number of samples\": values\n",
348
"})\n",
349
"\n",
350
"# Create treemap\n",
351
"fig = px.treemap(\n",
352
" df,\n",
353
" path=[px.Constant(\"data\"), \"Category\", \"Subcategory\"],\n",
354
" values=\"Number of samples\",\n",
355
" title=\"Treemap of classes\"\n",
356
")\n",
357
"\n",
358
"material_colours_hex = [\n",
359
" \"#009688\", # Teal\n",
360
" \"#4CAF50\", # Green\n",
361
" \"#8BC34A\", # Light Green\n",
362
" \"#CDDC39\", # Lime\n",
363
" \"#FFEB3B\", # Yellow\n",
364
" \"#FFC107\", # Amber\n",
365
" \"#FF9800\", # Orange\n",
366
" \"#FF5722\", # Deep Orange\n",
367
" \"#F44336\", # Red\n",
368
" \"#E91E63\", # Pink\n",
369
" \"#9C27B0\", # Purple\n",
370
" \"#673AB7\", # Deep Purple\n",
371
" \"#3F51B5\", # Indigo\n",
372
" \"#2196F3\", # Blue\n",
373
" \"#03A9F4\", # Light Blue\n",
374
" \"#00BCD4\", # Cyan\n",
375
" \"#795548\", # Brown\n",
376
" \"#9E9E9E\", # Grey\n",
377
" \"#607D8B\", # Blue Grey\n",
378
"]\n",
379
"\n",
380
"\n",
381
"fig.update_layout(width=2400, height=1200,\n",
382
" treemapcolorway=material_colours_hex\n",
383
" )\n",
384
"\n",
385
"fig.show()\n"
386
]
387
},
388
{
389
"cell_type": "code",
390
"execution_count": 12,
391
"id": "cdc4e80fe5566372",
392
"metadata": {
393
"ExecuteTime": {
394
"start_time": "2024-05-18T06:55:02.144615Z"
395
},
396
"jupyter": {
397
"is_executing": true
398
}
399
},
400
"outputs": [
401
{
402
"name": "stderr",
403
"output_type": "stream",
404
"text": [
405
" 1%|▍ | 44/8357 [00:56<3:03:11, 1.32s/it]"
406
]
407
},
408
{
409
"name": "stdout",
410
"output_type": "stream",
411
"text": [
412
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173532.jpg\n",
413
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174550.jpg\n"
414
]
415
},
416
{
417
"name": "stderr",
418
"output_type": "stream",
419
"text": [
420
" 1%|▍ | 47/8357 [00:57<1:54:08, 1.21it/s]"
421
]
422
},
423
{
424
"name": "stdout",
425
"output_type": "stream",
426
"text": [
427
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174456.jpg\n"
428
]
429
},
430
{
431
"name": "stderr",
432
"output_type": "stream",
433
"text": [
434
" 1%|▌ | 50/8357 [01:00<1:59:42, 1.16it/s]"
435
]
436
},
437
{
438
"name": "stdout",
439
"output_type": "stream",
440
"text": [
441
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173534.jpg\n"
442
]
443
},
444
{
445
"name": "stderr",
446
"output_type": "stream",
447
"text": [
448
" 1%|▌ | 55/8357 [01:05<2:34:19, 1.12s/it]"
449
]
450
},
451
{
452
"name": "stdout",
453
"output_type": "stream",
454
"text": [
455
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174202.jpg\n",
456
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174412.jpg\n"
457
]
458
},
459
{
460
"name": "stderr",
461
"output_type": "stream",
462
"text": [
463
" 1%|▌ | 60/8357 [01:09<2:20:43, 1.02s/it]"
464
]
465
},
466
{
467
"name": "stdout",
468
"output_type": "stream",
469
"text": [
470
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173714.jpg\n"
471
]
472
},
473
{
474
"name": "stderr",
475
"output_type": "stream",
476
"text": [
477
" 1%|▋ | 68/8357 [01:19<2:56:41, 1.28s/it]"
478
]
479
},
480
{
481
"name": "stdout",
482
"output_type": "stream",
483
"text": [
484
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173445.jpg\n"
485
]
486
},
487
{
488
"name": "stderr",
489
"output_type": "stream",
490
"text": [
491
" 1%|▋ | 72/8357 [01:23<2:44:24, 1.19s/it]"
492
]
493
},
494
{
495
"name": "stdout",
496
"output_type": "stream",
497
"text": [
498
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174520.jpg\n"
499
]
500
},
501
{
502
"name": "stderr",
503
"output_type": "stream",
504
"text": [
505
" 1%|▊ | 80/8357 [01:33<2:57:53, 1.29s/it]"
506
]
507
},
508
{
509
"name": "stdout",
510
"output_type": "stream",
511
"text": [
512
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173708.jpg\n"
513
]
514
},
515
{
516
"name": "stderr",
517
"output_type": "stream",
518
"text": [
519
" 1%|▉ | 86/8357 [01:39<2:53:24, 1.26s/it]"
520
]
521
},
522
{
523
"name": "stdout",
524
"output_type": "stream",
525
"text": [
526
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174434.jpg\n"
527
]
528
},
529
{
530
"name": "stderr",
531
"output_type": "stream",
532
"text": [
533
" 1%|▉ | 88/8357 [01:41<2:16:54, 1.01it/s]"
534
]
535
},
536
{
537
"name": "stdout",
538
"output_type": "stream",
539
"text": [
540
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174210.jpg\n"
541
]
542
},
543
{
544
"name": "stderr",
545
"output_type": "stream",
546
"text": [
547
" 1%|▉ | 90/8357 [01:42<1:59:28, 1.15it/s]"
548
]
549
},
550
{
551
"name": "stdout",
552
"output_type": "stream",
553
"text": [
554
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173812.jpg\n"
555
]
556
},
557
{
558
"name": "stderr",
559
"output_type": "stream",
560
"text": [
561
" 1%|█ | 109/8357 [02:06<3:04:57, 1.35s/it]"
562
]
563
},
564
{
565
"name": "stdout",
566
"output_type": "stream",
567
"text": [
568
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173651.jpg\n",
569
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174528.jpg\n"
570
]
571
},
572
{
573
"name": "stderr",
574
"output_type": "stream",
575
"text": [
576
" 1%|█▏ | 116/8357 [02:13<2:40:33, 1.17s/it]"
577
]
578
},
579
{
580
"name": "stdout",
581
"output_type": "stream",
582
"text": [
583
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173651(0).jpg\n"
584
]
585
},
586
{
587
"name": "stderr",
588
"output_type": "stream",
589
"text": [
590
" 1%|█▏ | 120/8357 [02:17<2:37:42, 1.15s/it]"
591
]
592
},
593
{
594
"name": "stdout",
595
"output_type": "stream",
596
"text": [
597
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174441.jpg\n"
598
]
599
},
600
{
601
"name": "stderr",
602
"output_type": "stream",
603
"text": [
604
" 1%|█▎ | 123/8357 [02:19<2:21:38, 1.03s/it]"
605
]
606
},
607
{
608
"name": "stdout",
609
"output_type": "stream",
610
"text": [
611
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174533.jpg\n"
612
]
613
},
614
{
615
"name": "stderr",
616
"output_type": "stream",
617
"text": [
618
" 2%|█▎ | 131/8357 [02:29<2:54:46, 1.27s/it]"
619
]
620
},
621
{
622
"name": "stdout",
623
"output_type": "stream",
624
"text": [
625
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174010.jpg\n",
626
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173540.jpg\n"
627
]
628
},
629
{
630
"name": "stderr",
631
"output_type": "stream",
632
"text": [
633
" 2%|█▍ | 138/8357 [02:36<2:35:39, 1.14s/it]"
634
]
635
},
636
{
637
"name": "stdout",
638
"output_type": "stream",
639
"text": [
640
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173545.jpg\n",
641
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173531.jpg\n"
642
]
643
},
644
{
645
"name": "stderr",
646
"output_type": "stream",
647
"text": [
648
" 2%|█▌ | 150/8357 [02:48<2:51:17, 1.25s/it]"
649
]
650
},
651
{
652
"name": "stdout",
653
"output_type": "stream",
654
"text": [
655
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173530.jpg\n",
656
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174459.jpg\n"
657
]
658
},
659
{
660
"name": "stderr",
661
"output_type": "stream",
662
"text": [
663
" 2%|█▌ | 154/8357 [02:51<2:08:27, 1.06it/s]"
664
]
665
},
666
{
667
"name": "stdout",
668
"output_type": "stream",
669
"text": [
670
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173649.jpg\n"
671
]
672
},
673
{
674
"name": "stderr",
675
"output_type": "stream",
676
"text": [
677
" 2%|█▊ | 172/8357 [03:13<2:55:45, 1.29s/it]"
678
]
679
},
680
{
681
"name": "stdout",
682
"output_type": "stream",
683
"text": [
684
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173520.jpg\n"
685
]
686
},
687
{
688
"name": "stderr",
689
"output_type": "stream",
690
"text": [
691
" 2%|█▊ | 176/8357 [03:17<2:31:53, 1.11s/it]"
692
]
693
},
694
{
695
"name": "stdout",
696
"output_type": "stream",
697
"text": [
698
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174048.jpg\n"
699
]
700
},
701
{
702
"name": "stderr",
703
"output_type": "stream",
704
"text": [
705
" 2%|█▊ | 178/8357 [03:18<2:04:50, 1.09it/s]"
706
]
707
},
708
{
709
"name": "stdout",
710
"output_type": "stream",
711
"text": [
712
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174008.jpg\n"
713
]
714
},
715
{
716
"name": "stderr",
717
"output_type": "stream",
718
"text": [
719
" 2%|█▊ | 182/8357 [03:22<2:10:25, 1.04it/s]"
720
]
721
},
722
{
723
"name": "stdout",
724
"output_type": "stream",
725
"text": [
726
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174637.jpg\n",
727
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230711_215033.jpg\n"
728
]
729
},
730
{
731
"name": "stderr",
732
"output_type": "stream",
733
"text": [
734
" 2%|█▉ | 189/8357 [03:28<2:24:04, 1.06s/it]"
735
]
736
},
737
{
738
"name": "stdout",
739
"output_type": "stream",
740
"text": [
741
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174012.jpg\n"
742
]
743
},
744
{
745
"name": "stderr",
746
"output_type": "stream",
747
"text": [
748
" 2%|█▉ | 193/8357 [03:32<2:19:47, 1.03s/it]"
749
]
750
},
751
{
752
"name": "stdout",
753
"output_type": "stream",
754
"text": [
755
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174329.jpg\n",
756
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174255.jpg\n"
757
]
758
},
759
{
760
"name": "stderr",
761
"output_type": "stream",
762
"text": [
763
" 2%|██ | 200/8357 [03:38<2:21:44, 1.04s/it]"
764
]
765
},
766
{
767
"name": "stdout",
768
"output_type": "stream",
769
"text": [
770
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174354.jpg\n"
771
]
772
},
773
{
774
"name": "stderr",
775
"output_type": "stream",
776
"text": [
777
" 2%|██▏ | 208/8357 [03:47<2:43:11, 1.20s/it]"
778
]
779
},
780
{
781
"name": "stdout",
782
"output_type": "stream",
783
"text": [
784
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174403.jpg\n",
785
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173553.jpg\n"
786
]
787
},
788
{
789
"name": "stderr",
790
"output_type": "stream",
791
"text": [
792
" 3%|██▏ | 214/8357 [03:52<2:18:21, 1.02s/it]"
793
]
794
},
795
{
796
"name": "stdout",
797
"output_type": "stream",
798
"text": [
799
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173513.jpg\n"
800
]
801
},
802
{
803
"name": "stderr",
804
"output_type": "stream",
805
"text": [
806
" 3%|██▏ | 217/8357 [03:54<2:07:30, 1.06it/s]"
807
]
808
},
809
{
810
"name": "stdout",
811
"output_type": "stream",
812
"text": [
813
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230704_163659.jpg\n"
814
]
815
},
816
{
817
"name": "stderr",
818
"output_type": "stream",
819
"text": [
820
" 3%|██▎ | 220/8357 [03:57<2:00:49, 1.12it/s]"
821
]
822
},
823
{
824
"name": "stdout",
825
"output_type": "stream",
826
"text": [
827
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174203.jpg\n"
828
]
829
},
830
{
831
"name": "stderr",
832
"output_type": "stream",
833
"text": [
834
" 3%|██▎ | 224/8357 [04:00<2:11:01, 1.03it/s]"
835
]
836
},
837
{
838
"name": "stdout",
839
"output_type": "stream",
840
"text": [
841
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173521.jpg\n"
842
]
843
},
844
{
845
"name": "stderr",
846
"output_type": "stream",
847
"text": [
848
" 3%|██▎ | 226/8357 [04:02<1:54:03, 1.19it/s]"
849
]
850
},
851
{
852
"name": "stdout",
853
"output_type": "stream",
854
"text": [
855
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174200.jpg\n"
856
]
857
},
858
{
859
"name": "stderr",
860
"output_type": "stream",
861
"text": [
862
" 3%|██▎ | 230/8357 [04:06<2:08:34, 1.05it/s]"
863
]
864
},
865
{
866
"name": "stdout",
867
"output_type": "stream",
868
"text": [
869
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174236.jpg\n"
870
]
871
},
872
{
873
"name": "stderr",
874
"output_type": "stream",
875
"text": [
876
" 3%|██▍ | 232/8357 [04:07<1:49:44, 1.23it/s]"
877
]
878
},
879
{
880
"name": "stdout",
881
"output_type": "stream",
882
"text": [
883
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173442.jpg\n"
884
]
885
},
886
{
887
"name": "stderr",
888
"output_type": "stream",
889
"text": [
890
" 3%|██▍ | 239/8357 [04:14<2:30:03, 1.11s/it]"
891
]
892
},
893
{
894
"name": "stdout",
895
"output_type": "stream",
896
"text": [
897
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174416.jpg\n"
898
]
899
},
900
{
901
"name": "stderr",
902
"output_type": "stream",
903
"text": [
904
" 3%|██▍ | 241/8357 [04:15<2:06:02, 1.07it/s]"
905
]
906
},
907
{
908
"name": "stdout",
909
"output_type": "stream",
910
"text": [
911
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_174408.jpg\n"
912
]
913
},
914
{
915
"name": "stderr",
916
"output_type": "stream",
917
"text": [
918
" 3%|██▌ | 244/8357 [04:18<2:03:55, 1.09it/s]"
919
]
920
},
921
{
922
"name": "stdout",
923
"output_type": "stream",
924
"text": [
925
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173813.jpg\n",
926
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173542.jpg\n"
927
]
928
},
929
{
930
"name": "stderr",
931
"output_type": "stream",
932
"text": [
933
" 3%|██▌ | 248/8357 [04:21<1:48:11, 1.25it/s]"
934
]
935
},
936
{
937
"name": "stdout",
938
"output_type": "stream",
939
"text": [
940
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/original_20230702_173526.jpg\n"
941
]
942
},
943
{
944
"name": "stderr",
945
"output_type": "stream",
946
"text": [
947
" 9%|███████▌ | 716/8357 [13:07<21:37, 5.89it/s]"
948
]
949
},
950
{
951
"name": "stdout",
952
"output_type": "stream",
953
"text": [
954
"Skipping non-image file: data/Organic, Food Waste/original_20230712_095148.jpg\n",
955
"Skipping non-image file: data/Organic, Food Waste/original_20230803_205752.jpg\n",
956
"Skipping non-image file: data/Organic, Food Waste/original_20230712_095153.jpg\n",
957
"Skipping non-image file: data/Organic, Food Waste/original_20230712_095141.jpg\n",
958
"Skipping non-image file: data/Organic, Food Waste/original_20230803_205803.jpg\n",
959
"Skipping non-image file: data/Organic, Food Waste/original_20230803_205713.jpg\n",
960
"Skipping non-image file: data/Organic, Food Waste/original_20230803_205801.jpg\n",
961
"Skipping non-image file: data/Organic, Food Waste/original_20230807_204516.jpg\n",
962
"Skipping non-image file: data/Organic, Food Waste/original_20230803_205814.jpg\n",
963
"Skipping non-image file: data/Organic, Food Waste/original_20230712_095155.jpg\n",
964
"Skipping non-image file: data/Organic, Food Waste/original_20230804_121651.jpg\n",
965
"Skipping non-image file: data/Organic, Food Waste/original_20230803_204603.jpg\n",
966
"Skipping non-image file: data/Organic, Food Waste/original_20230712_095139.jpg\n",
967
"Skipping non-image file: data/Organic, Food Waste/original_20230803_205741.jpg\n",
968
"Skipping non-image file: data/Organic, Food Waste/original_20230803_211012.jpg\n",
969
"Skipping non-image file: data/Organic, Food Waste/original_20230803_205337.jpg\n",
970
"Skipping non-image file: data/Organic, Food Waste/original_20230803_205807.jpg\n",
971
"Skipping non-image file: data/Organic, Food Waste/original_20230712_095126.jpg\n",
972
"Skipping non-image file: data/Organic, Food Waste/original_20230807_204513.jpg\n",
973
"Skipping non-image file: data/Organic, Food Waste/original_20230803_205805.jpg\n",
974
"Skipping non-image file: data/Organic, Food Waste/original_20230712_095129.jpg\n",
975
"Skipping non-image file: data/Organic, Food Waste/original_20230712_095135.jpg\n",
976
"Skipping non-image file: data/Organic, Food Waste/original_20230712_095150.jpg\n",
977
"Skipping non-image file: data/Organic, Food Waste/original_20230712_095121.jpg\n",
978
"Skipping non-image file: data/Organic, Food Waste/original_20230807_204518.jpg\n",
979
"Skipping non-image file: data/Organic, Food Waste/original_20230803_205759.jpg\n",
980
"Skipping non-image file: data/Organic, Food Waste/original_20230803_211006.jpg\n",
981
"Skipping non-image file: data/Organic, Food Waste/original_20230803_210957.jpg\n",
982
"Skipping non-image file: data/Organic, Food Waste/original_20230712_095116.jpg\n",
983
"Skipping non-image file: data/Organic, Food Waste/original_IMG-20230712-WA0018.jpg\n",
984
"Skipping non-image file: data/Organic, Food Waste/original_20230803_205339.jpg\n",
985
"Skipping non-image file: data/Organic, Food Waste/original_20230712_095119.jpg\n",
986
"Skipping non-image file: data/Organic, Food Waste/original_20230803_205756.jpg\n",
987
"Skipping non-image file: data/Organic, Food Waste/original_20230712_095133.jpg\n",
988
"Skipping non-image file: data/Organic, Food Waste/original_20230807_204506.jpg\n"
989
]
990
},
991
{
992
"name": "stderr",
993
"output_type": "stream",
994
"text": [
995
" 12%|██████████▌ | 1041/8357 [16:49<1:29:50, 1.36it/s]"
996
]
997
},
998
{
999
"name": "stdout",
1000
"output_type": "stream",
1001
"text": [
1002
"Skipping non-image file: data/Plastic, PP Film/original_IMG-20230711-WA0005.jpg\n",
1003
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110722.jpg\n",
1004
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110702.jpg\n"
1005
]
1006
},
1007
{
1008
"name": "stderr",
1009
"output_type": "stream",
1010
"text": [
1011
" 13%|██████████▉ | 1056/8357 [16:51<37:26, 3.25it/s]"
1012
]
1013
},
1014
{
1015
"name": "stdout",
1016
"output_type": "stream",
1017
"text": [
1018
"Skipping non-image file: data/Plastic, PP Film/original_20230711_213150.jpg\n",
1019
"Skipping non-image file: data/Plastic, PP Film/original_IMG-20230711-WA0019.jpg\n",
1020
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110646.jpg\n"
1021
]
1022
},
1023
{
1024
"name": "stderr",
1025
"output_type": "stream",
1026
"text": [
1027
" 13%|███████████ | 1066/8357 [16:54<37:36, 3.23it/s]"
1028
]
1029
},
1030
{
1031
"name": "stdout",
1032
"output_type": "stream",
1033
"text": [
1034
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110657.jpg\n",
1035
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110717.jpg\n"
1036
]
1037
},
1038
{
1039
"name": "stderr",
1040
"output_type": "stream",
1041
"text": [
1042
" 13%|███████████▏ | 1071/8357 [16:55<36:13, 3.35it/s]"
1043
]
1044
},
1045
{
1046
"name": "stdout",
1047
"output_type": "stream",
1048
"text": [
1049
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110736.jpg\n",
1050
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110642.jpg\n",
1051
"Skipping non-image file: data/Plastic, PP Film/original_IMG-20230711-WA0016.jpg\n",
1052
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110608.jpg\n",
1053
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110706.jpg\n",
1054
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110631.jpg\n",
1055
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110736(0).jpg\n",
1056
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110725.jpg\n",
1057
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110731.jpg\n"
1058
]
1059
},
1060
{
1061
"name": "stderr",
1062
"output_type": "stream",
1063
"text": [
1064
" 13%|███████████▍ | 1097/8357 [16:57<14:44, 8.21it/s]"
1065
]
1066
},
1067
{
1068
"name": "stdout",
1069
"output_type": "stream",
1070
"text": [
1071
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110601.jpg\n",
1072
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110739.jpg\n",
1073
"Skipping non-image file: data/Plastic, PP Film/original_20230705_110614.jpg\n"
1074
]
1075
},
1076
{
1077
"name": "stderr",
1078
"output_type": "stream",
1079
"text": [
1080
" 15%|████████████▌ | 1212/8357 [17:16<22:29, 5.29it/s]"
1081
]
1082
},
1083
{
1084
"name": "stdout",
1085
"output_type": "stream",
1086
"text": [
1087
"Skipping non-image file: data/Plastic, PS Container/original_20230803_204306.jpg\n",
1088
"Skipping non-image file: data/Plastic, PS Container/original_20230803_204304.jpg\n",
1089
"Skipping non-image file: data/Plastic, PS Container/original_20230803_203655.jpg\n",
1090
"Skipping non-image file: data/Plastic, PS Container/original_20230803_203706.jpg\n"
1091
]
1092
},
1093
{
1094
"name": "stderr",
1095
"output_type": "stream",
1096
"text": [
1097
" 18%|███████████████▎ | 1511/8357 [20:18<2:10:30, 1.14s/it]"
1098
]
1099
},
1100
{
1101
"name": "stdout",
1102
"output_type": "stream",
1103
"text": [
1104
"Skipping non-image file: data/Paper, Newspaper or Magazine/original_20230616_195725.jpg\n",
1105
"Skipping non-image file: data/Paper, Newspaper or Magazine/original_20230616_195632.jpg\n",
1106
"Skipping non-image file: data/Paper, Newspaper or Magazine/original_20230616_195714.jpg\n",
1107
"Skipping non-image file: data/Paper, Newspaper or Magazine/original_20230616_195639.jpg\n",
1108
"Skipping non-image file: data/Paper, Newspaper or Magazine/original_20230804_121548.jpg\n",
1109
"Skipping non-image file: data/Paper, Newspaper or Magazine/original_20230616_195628.jpg\n",
1110
"Skipping non-image file: data/Paper, Newspaper or Magazine/original_20230616_195701.jpg\n",
1111
"Skipping non-image file: data/Paper, Newspaper or Magazine/original_20230616_195707.jpg\n",
1112
"Skipping non-image file: data/Paper, Newspaper or Magazine/original_20230616_195648.jpg\n"
1113
]
1114
},
1115
{
1116
"name": "stderr",
1117
"output_type": "stream",
1118
"text": [
1119
" 19%|███████████████▊ | 1559/8357 [21:04<1:14:11, 1.53it/s]"
1120
]
1121
},
1122
{
1123
"name": "stdout",
1124
"output_type": "stream",
1125
"text": [
1126
"Skipping non-image file: data/Plastic, LDPE Bag or Film/original_punga_plastic3.jpg\n"
1127
]
1128
},
1129
{
1130
"name": "stderr",
1131
"output_type": "stream",
1132
"text": [
1133
" 19%|████████████████▎ | 1563/8357 [21:05<48:12, 2.35it/s]"
1134
]
1135
},
1136
{
1137
"name": "stdout",
1138
"output_type": "stream",
1139
"text": [
1140
"Skipping non-image file: data/Plastic, LDPE Bag or Film/original_punga_plastic.jpg\n"
1141
]
1142
},
1143
{
1144
"name": "stderr",
1145
"output_type": "stream",
1146
"text": [
1147
" 19%|████████████████▌ | 1587/8357 [21:12<20:06, 5.61it/s]"
1148
]
1149
},
1150
{
1151
"name": "stdout",
1152
"output_type": "stream",
1153
"text": [
1154
"Skipping non-image file: data/Organic, Food Waste/original_cartof.jpg\n",
1155
"Skipping non-image file: data/Organic, Food Waste/original_cartof1.jpg\n",
1156
"Skipping non-image file: data/Organic, Food Waste/original_coaja_banana.jpg\n",
1157
"Skipping non-image file: data/Organic, Food Waste/original_coaja_banana1.jpg\n"
1158
]
1159
},
1160
{
1161
"name": "stderr",
1162
"output_type": "stream",
1163
"text": [
1164
" 20%|█████████████████ | 1638/8357 [21:26<41:34, 2.69it/s]"
1165
]
1166
},
1167
{
1168
"name": "stdout",
1169
"output_type": "stream",
1170
"text": [
1171
"Skipping non-image file: data/Paper, Newspaper or Magazine/original_hartie7.jpg\n"
1172
]
1173
},
1174
{
1175
"name": "stderr",
1176
"output_type": "stream",
1177
"text": [
1178
" 20%|█████████████████ | 1642/8357 [21:27<41:19, 2.71it/s]"
1179
]
1180
},
1181
{
1182
"name": "stdout",
1183
"output_type": "stream",
1184
"text": [
1185
"Skipping non-image file: data/list.py\n",
1186
"Skipping non-image file: data/list.txt\n",
1187
"Skipping non-image file: data/Other, Eyeglass/trash-detection_000084_jpg.rf.74e93f0e083fc9a138ad5ea1e2929997.jpg\n"
1188
]
1189
},
1190
{
1191
"name": "stderr",
1192
"output_type": "stream",
1193
"text": [
1194
" 22%|██████████████████▌ | 1807/8357 [21:28<00:47, 136.52it/s]"
1195
]
1196
},
1197
{
1198
"name": "stdout",
1199
"output_type": "stream",
1200
"text": [
1201
"Skipping non-image file: data/Electronic, Cylindrical Battery/trash-detection_000055_jpg.rf.a58387c170dcc187d186834bec8a7ff4.jpg\n",
1202
"Skipping non-image file: data/Plastic, HDPE Bottle/trash-detection_000034_jpg.rf.0bd186f544632be53d2373981fe99424.jpg\n",
1203
"Skipping non-image file: data/Plastic, HDPE Bottle/trash-detection_000056_jpg.rf.b9f515822050108f5cc6ddc758b937e0.jpg\n",
1204
"Skipping non-image file: data/Plastic, HDPE Bottle/trash-detection_000077_jpg.rf.d477e3f731065481a0c0469575ac2747.jpg\n",
1205
"Skipping non-image file: data/Plastic, HDPE Bottle/trash-detection_000054_jpg.rf.e89b84ce28dbf31a5eecddebee07c12a.jpg\n"
1206
]
1207
},
1208
{
1209
"name": "stderr",
1210
"output_type": "stream",
1211
"text": [
1212
" 32%|███████████████████████████▎ | 2659/8357 [21:29<00:06, 918.21it/s]"
1213
]
1214
},
1215
{
1216
"name": "stdout",
1217
"output_type": "stream",
1218
"text": [
1219
"Skipping non-image file: data/Plastic, HDPE Bottle/trash-detection_000056_jpg.rf.a315a4bb64943c311999c10258c46091.jpg\n",
1220
"Skipping non-image file: data/Plastic, HDPE Bottle/trash-detection_000034_jpg.rf.57cd84376560e4819d93576eced020cd.jpg\n",
1221
"Skipping non-image file: data/Plastic, HDPE Bottle/trash-detection_000054_jpg.rf.52d3e5da4ba955c9cc2014e380e85583.jpg\n",
1222
"Skipping non-image file: data/Plastic, Nylon/trash-detection_000030_jpg.rf.99edff332d42e7802089e81c6cc1b9ea.jpg\n",
1223
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000009_JPG.rf.fe3fb1f65594a703d764293b2c18f1bb.jpg\n",
1224
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_IMG_4875_JPG.rf.f2f90487e15f2292bf484f502f93ee3f.jpg\n",
1225
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000127_JPG.rf.41a86e80943d2cbfa87535dbf0420816.jpg\n",
1226
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000129_JPG.rf.30c58d28c97979c283336d2aceefb691.jpg\n",
1227
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000016_jpg.rf.eb18550fdd4e1e5bae4be88089cf770e.jpg\n",
1228
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000102_JPG.rf.b729e45fc59520e23d1585f8d653509a.jpg\n",
1229
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_IMG_4874_JPG.rf.a5c3c25e23f256dc6746bdec0d303eeb.jpg\n",
1230
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000006_jpg.rf.f7720cc367ba2f48e943f5a064efdb89.jpg\n",
1231
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000129_JPG.rf.c95541a7afe9234959cff8c45683efca.jpg\n",
1232
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000017_jpg.rf.afacb6fa4ca6c34d2c0e9d45921f34e0.jpg\n",
1233
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_IMG_4865_JPG.rf.1a868d831495e2428fd83dd5ea0d8efa.jpg\n",
1234
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000009_JPG.rf.f2ab1eb3786bd6a7b84dd5a814026826.jpg\n",
1235
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_IMG_4875_JPG.rf.cf387b7aa845e5f4e72277e24084e586.jpg\n",
1236
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_IMG_4877_JPG.rf.743618c9743adf0ba0c9dbd7b0f4abee.jpg\n",
1237
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000127_JPG.rf.6486829f4e092489c41695005f136521.jpg\n",
1238
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000129_JPG.rf.dc2a4ff5ae2ba54fafa0c0d812f578a7.jpg\n",
1239
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000102_JPG.rf.d813ec7e629a92ffad2a155018741621.jpg\n",
1240
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000016_jpg.rf.d4ba4b2eb44f38154dfe70ff19e073fb.jpg\n",
1241
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_IMG_4875_JPG.rf.379c28c7f70ae87e70c27743928fa2fd.jpg\n",
1242
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000002_JPG.rf.219b30762e77260ca143a6dc27e9ffa7.jpg\n",
1243
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000016_jpg.rf.562f9267f7225718c9ebec5213ae9e01.jpg\n",
1244
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000127_JPG.rf.a991704c0c39c3a712d25cc274212dc9.jpg\n",
1245
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000102_JPG.rf.c225ec2cb6cf171b17bff0aa576223b5.jpg\n",
1246
"Skipping non-image file: data/Paper, Cardboard Box or Sheet/trash-detection_000008_jpg.rf.9e1ce10dc4429a62e2225f9c4b8a2927.jpg\n",
1247
"Skipping non-image file: data/Plastic, LDPE Bag or Film/trash-detection_000096_jpg.rf.66a37e1b40381b796ec9e9393336fe96.jpg\n",
1248
"Skipping non-image file: data/Plastic, LDPE Bag or Film/trash-detection_000039_jpg.rf.0b971d9a05a4c9a684e9f001d134d39f.jpg\n",
1249
"Skipping non-image file: data/Plastic, LDPE Bag or Film/trash-detection_000039_jpg.rf.32efb3603dd19185aa92ee8061c8cad3.jpg\n",
1250
"Skipping non-image file: data/Plastic, LDPE Bag or Film/trash-detection_000039_jpg.rf.5771589f4345ee6412c70d2b40eeb47d.jpg\n",
1251
"Skipping non-image file: data/Plastic, LDPE Bag or Film/trash-detection_000080_jpg.rf.0403b125d6d5a957f24983a7e0131d4d.jpg\n",
1252
"Skipping non-image file: data/Plastic, LDPE Bag or Film/trash-detection_000058_jpg.rf.908f8accb12ca0804a557f6e847dc6e3.jpg\n",
1253
"Skipping non-image file: data/Plastic, LDPE Bag or Film/trash-detection_000080_jpg.rf.a6644e4fa400759c51c292df7866ace8.jpg\n",
1254
"Skipping non-image file: data/Plastic, LDPE Bag or Film/trash-detection_000095_JPG.rf.26542bace8d5ba80d216636d1727af01.jpg\n",
1255
"Skipping non-image file: data/Plastic, LDPE Bag or Film/trash-detection_000097_jpg.rf.33b634407451b1d45e72d31aae72df16.jpg\n",
1256
"Skipping non-image file: data/Plastic, LDPE Bag or Film/trash-detection_000002_jpg.rf.4c25aae77ac54f9f6e32f9884134f387.jpg\n",
1257
"Skipping non-image file: data/Plastic, LDPE Bag or Film/trash-detection_000080_jpg.rf.f7ef09c73232ed14c9e1eaec2f606607.jpg\n",
1258
"Skipping non-image file: data/Plastic, PET Container/trash-detection_000091_jpg.rf.601b5daa023051f915dfe6596bf522bd.jpg\n",
1259
"Skipping non-image file: data/Plastic, PET Container/trash-detection_000091_jpg.rf.eca6ef32687054cd700bec67c36e6382.jpg\n",
1260
"Skipping non-image file: data/Plastic, PET Container/trash-detection_000045_JPG.rf.3b1d9eb97c960f57bec66f7bff3a701e.jpg\n",
1261
"Skipping non-image file: data/Plastic, PET Container/trash-detection_000091_jpg.rf.bcf118a51b289b513601e9d22d36089f.jpg\n",
1262
"Skipping non-image file: data/Plastic, PET Container/trash-detection_IMG_4916_JPG.rf.f5f26dba128900f164f0195c658ff9e5.jpg\n",
1263
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000021_jpg.rf.b000873b84a7a6bb5aac2bc6b19f2594.jpg\n"
1264
]
1265
},
1266
{
1267
"name": "stderr",
1268
"output_type": "stream",
1269
"text": [
1270
" 34%|████████████████████████████▋ | 2821/8357 [21:29<00:05, 1031.49it/s]"
1271
]
1272
},
1273
{
1274
"name": "stdout",
1275
"output_type": "stream",
1276
"text": [
1277
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000049_jpg.rf.cc894acfd69a999f04ea52dbecb76faf.jpg\n",
1278
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000073_JPG.rf.df6fc77ac6c5548f498b18a56156ac6c.jpg\n",
1279
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000067_jpg.rf.d2cd0dae8b54fee36599f7c589502230.jpg\n",
1280
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000039_jpg.rf.4cfb1006a857efe685fee9acfbbcd8eb.jpg\n",
1281
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000074_JPG.rf.2fad68abb062720e45f27f4163793899.jpg\n",
1282
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000086_jpg.rf.316ae1e6cfd15ae0129df0a676667e82.jpg\n",
1283
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_data_37_jpg.rf.2f39222900838621b925e90904f32616.jpg\n",
1284
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000039_jpg.rf.5e9c475076657fd910e62aa7311e5be4.jpg\n",
1285
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000057_jpg.rf.f800c2068ccb27ae8962efeb7c7b8ab0.jpg\n",
1286
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000017_JPG.rf.22e2d13a49b77208f25d63bcc4b4cdb6.jpg\n"
1287
]
1288
},
1289
{
1290
"name": "stderr",
1291
"output_type": "stream",
1292
"text": [
1293
" 37%|████████████████████████████████ | 3110/8357 [21:29<00:05, 885.47it/s]"
1294
]
1295
},
1296
{
1297
"name": "stdout",
1298
"output_type": "stream",
1299
"text": [
1300
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000094_jpg.rf.395a623a73fdc98e4e68b186f157ff61.jpg\n",
1301
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000013_jpg.rf.2e23b83466bb5075f537a4e994967a8e.jpg\n",
1302
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000092_jpg.rf.93eb991238b363c4b503f01afa6da398.jpg\n",
1303
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000023_jpg.rf.00fe867b0e7f3dbeb94f5a93d9b2b66c.jpg\n",
1304
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000095_jpg.rf.aec129512d9746e6d2d0f2afa905b13e.jpg\n",
1305
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000042_jpg.rf.1adc214402d5375bc36fef44d229500e.jpg\n",
1306
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000092_jpg.rf.001a29943d70a5530c0a49f73a314c14.jpg\n",
1307
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_data_37_jpg.rf.4ed007f01ef0cbbc762541fc753138f4.jpg\n",
1308
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000000_jpg.rf.6e44e53011fb167241bf4155fb7c36c2.jpg\n",
1309
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000094_jpg.rf.5f6f4cde56a233f91819858cfa0b9bd5.jpg\n",
1310
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000042_jpg.rf.150d084e70acf15ba5188b0011fd2dbe.jpg\n"
1311
]
1312
},
1313
{
1314
"name": "stderr",
1315
"output_type": "stream",
1316
"text": [
1317
" 44%|█████████████████████████████████████▎ | 3670/8357 [21:29<00:02, 1646.49it/s]"
1318
]
1319
},
1320
{
1321
"name": "stdout",
1322
"output_type": "stream",
1323
"text": [
1324
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000001_jpg.rf.603b917eb1b92a7c7e6019366d334355.jpg\n",
1325
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000023_jpg.rf.0dd4bd399ba244de9a4761c1240271de.jpg\n",
1326
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000046_JPG.rf.d52de7ef048b1a1ca61b3a202fb69ada.jpg\n",
1327
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000043_jpg.rf.d058e9e0066b04edd63fda639291cf80.jpg\n",
1328
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000045_JPG.rf.ffc387d93a6a185e07eb549488ea0641.jpg\n",
1329
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000071_JPG.rf.8a18a3cf980008393315edd96d98ba49.jpg\n",
1330
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000019_jpg.rf.ed8eb22f6beb29b7e8dbe953e4e1a2ba.jpg\n",
1331
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000037_jpg.rf.ecc1f668aac2390e281a9b1a16e38ddd.jpg\n",
1332
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000094_jpg.rf.214194c2a2cab03bd34596d7194b0860.jpg\n",
1333
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000094_jpg.rf.58893ad895e507914ac57684c8d2f00b.jpg\n",
1334
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000043_jpg.rf.81285e686442e81806e7eedff1b537a2.jpg\n",
1335
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000067_jpg.rf.c04a5c379db14649da11946e0243db18.jpg\n",
1336
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000079_jpg.rf.3f2cf88ec98e117c3a2417719a6e61fa.jpg\n",
1337
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000093_jpg.rf.98cdf5c08459bd5889c23c6946c8afee.jpg\n",
1338
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000071_JPG.rf.2f3e6078e4df31f3ca3747ee8902c8d9.jpg\n",
1339
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000023_jpg.rf.febf039667ed7d07ef0a00f1902e0fe1.jpg\n",
1340
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000053_jpg.rf.52b35dee2053270f2c761bcbb24239a5.jpg\n",
1341
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000067_jpg.rf.e440e9f0a352f558b6c51004019cc9ca.jpg\n",
1342
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000053_jpg.rf.cd3a5f0bcbaa292c19c430cb23e3048b.jpg\n",
1343
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000037_jpg.rf.05089937c070aa55282fe3f70c325e59.jpg\n",
1344
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000057_jpg.rf.3f6e795e1a3439d77044ec7a910b3cf5.jpg\n",
1345
"Skipping non-image file: data/Plastic, PET Bottle/PET1,170.jpg\n",
1346
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000028_jpg.rf.5536b02d610322f70e5ecbdd37935e55.jpg\n",
1347
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000058_JPG.rf.05467090f6f292910403af293cb4665d.jpg\n",
1348
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000086_jpg.rf.8bfcae8ecde7ee9ba12a520772a4cd10.jpg\n",
1349
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000028_jpg.rf.ecb411246627c2a08a1a6443389aa94c.jpg\n",
1350
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000074_JPG.rf.04f1276b53642b5761bb08ccc85d779f.jpg\n",
1351
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000095_jpg.rf.a70c5cf24612935eacd2fbd87c58a91f.jpg\n",
1352
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000019_jpg.rf.0cbf664625747303a2e1cfc7ef87a970.jpg\n",
1353
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_data_37_jpg.rf.abd4769e81e07567b49840db2156fbd0.jpg\n",
1354
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000047_jpg.rf.6cec29b82d37d470e3cee6a9e0b415ed.jpg\n"
1355
]
1356
},
1357
{
1358
"name": "stderr",
1359
"output_type": "stream",
1360
"text": [
1361
" 49%|█████████████████████████████████████████▎ | 4056/8357 [21:29<00:01, 2163.54it/s]"
1362
]
1363
},
1364
{
1365
"name": "stdout",
1366
"output_type": "stream",
1367
"text": [
1368
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000042_jpg.rf.7c7dcf0e2bf76fdbd837c1545dc9f4e2.jpg\n",
1369
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000028_jpg.rf.33cd8e172f94a3d46093b769e55b4387.jpg\n",
1370
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000073_JPG.rf.1624f0e45499e1da6c31e0ecd7b71a9a.jpg\n",
1371
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000090_jpg.rf.f2127e447a46b4fdfd9bfc4e339e439e.jpg\n",
1372
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000092_jpg.rf.170ade53b76d4817459bfa7aa0a0e125.jpg\n",
1373
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000094_jpg.rf.7571e5b3f8816159e8afd00a7c86385f.jpg\n",
1374
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000053_jpg.rf.c5f14fd3f933eaed6d4578b22297a88e.jpg\n",
1375
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000039_jpg.rf.f6842e8bf51fd26bfde2bd8169f4b409.jpg\n",
1376
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_IMG_4915_JPG.rf.03f432e462c4f00667e82de175db6040.jpg\n",
1377
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000053_jpg.rf.5848c4f9bf633fa1e1bb3e80e22a2d7e.jpg\n",
1378
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000086_jpg.rf.127b8d204afdeb5be31a1b8ece897e52.jpg\n",
1379
"Skipping non-image file: data/Plastic, PET Bottle/trash-detection_000073_JPG.rf.5d90367ed42e02f19886ee12f1e93b3b.jpg\n",
1380
"Skipping non-image file: data/Plastic, Clear PS Cup/trash-detection_000030_JPG.rf.4276a2e6a950aa4781c843d872e605c4.jpg\n",
1381
"Skipping non-image file: data/Plastic, Expanded Polystyrene/trash-detection_000124_JPG.rf.db0246fa68535b703a56081894e4be42.jpg\n",
1382
"Skipping non-image file: data/Plastic, Expanded Polystyrene/trash-detection_000035_jpg.rf.0112b1d6a2607f861682e3f0421c85b6.jpg\n",
1383
"Skipping non-image file: data/Plastic, Expanded Polystyrene/trash-detection_000063_jpg.rf.5aea1babd781238b98b40942a6ca799f.jpg\n",
1384
"Skipping non-image file: data/Plastic, Expanded Polystyrene/trash-detection_000063_jpg.rf.087f319c70a3d22eb8ff24b111f78b48.jpg\n",
1385
"Skipping non-image file: data/Plastic, Expanded Polystyrene/trash-detection_000063_jpg.rf.0a9a79fd667fdda2581100aba2e6a4bc.jpg\n",
1386
"Skipping non-image file: data/Plastic, Expanded Polystyrene/trash-detection_000124_JPG.rf.41fbb35fbee9cc663197336e5ca99316.jpg\n",
1387
"Skipping non-image file: data/Plastic, Expanded Polystyrene/trash-detection_000124_JPG.rf.643a5854c8c0a79ad2cce4432f6664f8.jpg\n",
1388
"Skipping non-image file: data/Plastic, PET Cup/trash-detection_000031_jpg.rf.8f0d8822143279258b6ad7ee1555f35e.jpg\n",
1389
"Skipping non-image file: data/Plastic, PET Cup/trash-detection_000091_jpg.rf.a1fd19ce954e7aab7022f8f58778d568.jpg\n",
1390
"Skipping non-image file: data/Plastic, PET Cup/trash-detection_000084_JPG.rf.a2cad4eadd95cda4891fd41772b04d28.jpg\n",
1391
"Skipping non-image file: data/Plastic, PS Foam Cup/trash-detection_straw4_jpg.rf.cbeec8d067db3c17eb4595c378141f4d.jpg\n",
1392
"Skipping non-image file: data/Plastic, PS Foam Cup/trash-detection_000100_JPG.rf.ba509d1b4609ea0ec374f923bba51a04.jpg\n",
1393
"Skipping non-image file: data/Plastic, PS Foam Cup/trash-detection_000100_JPG.rf.d5ea543e5c2c884b0cbab2b80de1b3dc.jpg\n",
1394
"Skipping non-image file: data/Plastic, PS Foam Cup/trash-detection_straw4_jpg.rf.ded6956faa764612d027c52dd7077431.jpg\n",
1395
"Skipping non-image file: data/Plastic, PS Foam Cup/trash-detection_straw4_jpg.rf.b54e63530a294c872029975065b29a47.jpg\n",
1396
"Skipping non-image file: data/Plastic, PS Foam Cup/trash-detection_000100_JPG.rf.e8157bf69944bb103f5cfcbad2b67f5b.jpg\n",
1397
"Skipping non-image file: data/Metal, Aluminium Sauce Tube/trash-detection_000091_JPG.rf.2d8b9625529df57fcaef8991fc209e77.jpg\n",
1398
"Skipping non-image file: data/Metal, Aluminium Sauce Tube/trash-detection_000091_JPG.rf.db75d0423131f817b687a714d9b069d3.jpg\n",
1399
"Skipping non-image file: data/Metal, Aluminium Sauce Tube/trash-detection_000091_JPG.rf.737a9a06aa4d0864f702c0f562ae7664.jpg\n",
1400
"Skipping non-image file: data/Plastic, Clear PP Cup/trash-detection_000098_jpg.rf.ec31b330e2b2c6021703749f78bfb994.jpg\n",
1401
"Skipping non-image file: data/Plastic, Clear PP Cup/trash-detection_000014_jpg.rf.d1833bf76009525f49fb73bb424a9772.jpg\n",
1402
"Skipping non-image file: data/Plastic, Clear PP Cup/trash-detection_000098_jpg.rf.873f4a6122e5bfb472176aae0dc1ff40.jpg\n",
1403
"Skipping non-image file: data/Plastic, Clear PP Cup/trash-detection_000001_jpg.rf.d38895de814e60a557eb5d113b058cb2.jpg\n",
1404
"Skipping non-image file: data/Plastic, Clear PP Cup/trash-detection_000001_jpg.rf.930e89885bdfa0d9eafa52776bce0035.jpg\n",
1405
"Skipping non-image file: data/Other, Cellophane/trash-detection_000041_jpg.rf.bcdf390d1c8157c7780d3c87bf161fa8.jpg\n"
1406
]
1407
},
1408
{
1409
"name": "stderr",
1410
"output_type": "stream",
1411
"text": [
1412
" 52%|███████████████████████████████████████████▉ | 4325/8357 [21:30<00:03, 1213.45it/s]"
1413
]
1414
},
1415
{
1416
"name": "stdout",
1417
"output_type": "stream",
1418
"text": [
1419
"Skipping non-image file: data/Plastic, Starch Bag/trash-detection_000010_jpg.rf.a2ebb2c5251ad8d792768ecdeb3b0d43.jpg\n",
1420
"Skipping non-image file: data/Plastic, Starch Bag/trash-detection_000049_JPG.rf.509271c4a2cc1b5737b82d42747a528d.jpg\n",
1421
"Skipping non-image file: data/Plastic, PP Cutlery/trash-detection_000001_jpg.rf.73ffe599f23a986acdeb0da3be52bd19.jpg\n",
1422
"Skipping non-image file: data/Plastic, PP Cutlery/trash-detection_000001_jpg.rf.467466abeab29f04eda507a217f59f35.jpg\n",
1423
"Skipping non-image file: data/Plastic, PP Cutlery/trash-detection_000014_jpg.rf.3e485a98bf3da3342073fdd6c076e925.jpg\n",
1424
"Skipping non-image file: data/Plastic, PP Cutlery/trash-detection_000001_jpg.rf.90f36c11f7151ea1d711c3311dfed611.jpg\n",
1425
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000088_jpg.rf.827b42031df286c071ddff71416f41d3.jpg\n",
1426
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000007_JPG.rf.24e98d7ff14ac30ff42e6368223415ba.jpg\n",
1427
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000088_jpg.rf.ba1a563d81bac29f167d7cd68689469f.jpg\n",
1428
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000045_jpg.rf.481b4088e850c11de0b0aa9ae15c423c.jpg\n",
1429
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000050_jpg.rf.50620d3d9331a54ac38d19477261590a.jpg\n",
1430
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000051_JPG.rf.f049ca49b706033a7e75546f5658f0b9.jpg\n",
1431
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000069_JPG.rf.7f64c639220b47f0dc0c0ecb13ddc13c.jpg\n"
1432
]
1433
},
1434
{
1435
"name": "stderr",
1436
"output_type": "stream",
1437
"text": [
1438
" 54%|██████████████████████████████████████████████▌ | 4528/8357 [21:32<00:12, 308.68it/s]"
1439
]
1440
},
1441
{
1442
"name": "stdout",
1443
"output_type": "stream",
1444
"text": [
1445
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000069_JPG.rf.b46cff38a43731ba6f661d97fd2824af.jpg\n",
1446
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000035_jpg.rf.09216398f2534950b542beeaef25c199.jpg\n"
1447
]
1448
},
1449
{
1450
"name": "stderr",
1451
"output_type": "stream",
1452
"text": [
1453
" 56%|████████████████████████████████████████████████ | 4673/8357 [21:32<00:11, 331.75it/s]"
1454
]
1455
},
1456
{
1457
"name": "stdout",
1458
"output_type": "stream",
1459
"text": [
1460
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000082_jpg.rf.0207914f92d1dc33507ef12456abc3e5.jpg\n",
1461
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000082_jpg.rf.03576ad19b6d473cf194155425b5d712.jpg\n",
1462
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_IMG_4868_JPG.rf.83dab611e6530e68439567b59c78e40f.jpg\n",
1463
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000073_JPG.rf.a138ffeb8f50d5aa365773709e106e18.jpg\n",
1464
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000073_JPG.rf.f9b638fd73618972a6231734ce7f1928.jpg\n",
1465
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000027_jpg.rf.b6b979464363cfab4ed1ebb9c6d2bad8.jpg\n",
1466
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000045_jpg.rf.2454f2c1436f2ef47ee28366a4cbba65.jpg\n",
1467
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000078_jpg.rf.fd820e794e85205e957e76dc18943865.jpg\n",
1468
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000037_jpg.rf.303cc775919c068bb5154dfc1362e06c.jpg\n",
1469
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000037_jpg.rf.a2537e81d8d71c1550022e3732abbdc9.jpg\n"
1470
]
1471
},
1472
{
1473
"name": "stderr",
1474
"output_type": "stream",
1475
"text": [
1476
" 58%|██████████████████████████████████████████████████▏ | 4874/8357 [21:32<00:08, 430.04it/s]"
1477
]
1478
},
1479
{
1480
"name": "stdout",
1481
"output_type": "stream",
1482
"text": [
1483
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000077_jpg.rf.e852156069087724da0cf8f31bf03fb2.jpg\n",
1484
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000073_JPG.rf.f85fbf2b858b1da8830b6cee5cedc888.jpg\n",
1485
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000050_jpg.rf.fcd240ee977d6599438b9ff1c15dc9fb.jpg\n"
1486
]
1487
},
1488
{
1489
"name": "stderr",
1490
"output_type": "stream",
1491
"text": [
1492
" 61%|████████████████████████████████████████████████████▌ | 5112/8357 [21:33<00:07, 417.93it/s]"
1493
]
1494
},
1495
{
1496
"name": "stdout",
1497
"output_type": "stream",
1498
"text": [
1499
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000069_JPG.rf.0ba2451e39889be369c75da4d21d6f7c.jpg\n",
1500
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000088_jpg.rf.cc62e778a8e9891e60c31ba503c6135c.jpg\n",
1501
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000050_jpg.rf.3c9f21ec926aad940dd149a1e111e39e.jpg\n",
1502
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000053_jpg.rf.8711925cb4bb38e1c1d011548bea1300.jpg\n",
1503
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_IMG_4868_JPG.rf.fe2221a3586d17b00f4eefa1f5ea29d4.jpg\n",
1504
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000050_jpg.rf.9a352549e1bbaa34fa9749acd06351c4.jpg\n",
1505
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000053_jpg.rf.65036d37974e18d4db0bb3691cec4391.jpg\n",
1506
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000053_jpg.rf.ce99f9096913a0fd7628434bf438b900.jpg\n",
1507
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000023_jpg.rf.6c48ab6b309ac0701fedfe9d7376d43b.jpg\n",
1508
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000050_jpg.rf.b58379deb2914af441b175392fefc9c6.jpg\n",
1509
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000082_jpg.rf.9e3b6fb722f83c4e5db5d2ef162aa7c1.jpg\n",
1510
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000077_jpg.rf.3ec22d5e82b2a53250b020a34340501a.jpg\n",
1511
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000048_jpg.rf.7778dc3171a960d999d3940f9ace3fcb.jpg\n",
1512
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000050_jpg.rf.ba40b763cc59b49350538e30684b9952.jpg\n",
1513
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_IMG_4868_JPG.rf.65de60ce3cf35babb27b03d57f2cbdee.jpg\n",
1514
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000027_jpg.rf.c3a062cd699c7eee699225ba5b922d5f.jpg\n",
1515
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000083_jpg.rf.8a200363cb9cc7b66046c980d154d569.jpg\n",
1516
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000037_jpg.rf.bc02a372e220eb633865725721eb2090.jpg\n",
1517
"Skipping non-image file: data/Metal, Aluminium Can/trash-detection_000077_jpg.rf.0365686dccb3b768ec76c397c2146642.jpg\n",
1518
"Skipping non-image file: data/Paper, Liquid Carton/trash-detection_000009_jpg.rf.a94b36795daefd71822b827f5bc0a9cc.jpg\n",
1519
"Skipping non-image file: data/Paper, Liquid Carton/trash-detection_data_39_jpg.rf.e5f6d6e3495303399064f6c5609884e0.jpg\n",
1520
"Skipping non-image file: data/Paper, Liquid Carton/trash-detection_000092_JPG.rf.a0b5b2565a466efcaff46a1a775c898b.jpg\n",
1521
"Skipping non-image file: data/Paper, Liquid Carton/trash-detection_000098_jpg.rf.f57e8759a23897c1b773420e4af12479.jpg\n",
1522
"Skipping non-image file: data/Wood, Solid Wood/trash-detection_000000_jpg.rf.e3fe7e2f0223906d4a754b6650db1cc1.jpg\n",
1523
"Skipping non-image file: data/Other, Cigarette Package/trash-detection_000089_jpg.rf.411c3ed6c713bea7dd69ae01541e529c.jpg\n",
1524
"Skipping non-image file: data/Other, Cigarette Package/trash-detection_000089_jpg.rf.bfcf2eb02f2f56c0d0017ca8f33f793c.jpg\n",
1525
"Skipping non-image file: data/Other, Cigarette Package/trash-detection_000089_jpg.rf.e0e15dfe328226f71195e02805b7a330.jpg\n",
1526
"Skipping non-image file: data/Other, Cigarette Package/trash-detection_000004_jpg.rf.07fbf6e684efbed23a5f0157ab02ffe1.jpg\n",
1527
"Skipping non-image file: data/Medical, Rubber Glove/trash-detection_000018_JPG.rf.f54390999224cd25396741fd7feb7260.jpg\n",
1528
"Skipping non-image file: data/Other, Aerosol/trash-detection_000060_jpg.rf.83131efccaae47450f11dc88d48a8f06.jpg\n",
1529
"Skipping non-image file: data/Other, Aerosol/trash-detection_000055_jpg.rf.5e8e1a9714500d9181b2d682879b57c8.jpg\n",
1530
"Skipping non-image file: data/Other, Aerosol/trash-detection_000061_jpg.rf.d5b3b83776edd1ec3eaf6ac48e3b2de3.jpg\n",
1531
"Skipping non-image file: data/Other, Aerosol/trash-detection_000055_jpg.rf.c53b492b6656ee981a87708be784a87c.jpg\n",
1532
"Skipping non-image file: data/Other, Aerosol/trash-detection_000060_jpg.rf.36d9f5da22142e7dbb0233cbcfcb7a13.jpg\n",
1533
"Skipping non-image file: data/Paper, Pulp Egg Container/trash-detection_000067_JPG.rf.57dfa6c4d9b164c4fb93655b81b991cd.jpg\n",
1534
"Skipping non-image file: data/Metal, Tin Can/trash-detection_000043_jpg.rf.d4077eb745994c7bee926ae00884f401.jpg\n",
1535
"Skipping non-image file: data/Metal, Tin Can/trash-detection_000045_jpg.rf.b1aa560ace86c9f4e6efdc56b0962602.jpg\n",
1536
"Skipping non-image file: data/Metal, Tin Can/trash-detection_000007_jpg.rf.7752ae2b3099a6e651d547e113628498.jpg\n",
1537
"Skipping non-image file: data/Metal, Tin Can/trash-detection_000045_jpg.rf.57b432a1de2098923a76d818a53a64b6.jpg\n",
1538
"Skipping non-image file: data/Metal, Tin Can/trash-detection_000022_jpg.rf.b18e9f77c22c26ec98bfb7e1bb610f19.jpg\n",
1539
"Skipping non-image file: data/Metal, Tin Can/trash-detection_000022_jpg.rf.f51e01fdbc97c82d982d0631a52f1d4e.jpg\n",
1540
"Skipping non-image file: data/Metal, Tin Can/trash-detection_000037_jpg.rf.762e53010cc55b8820a1e41bd3bcc31a.jpg\n",
1541
"Skipping non-image file: data/Metal, Tin Can/trash-detection_000038_jpg.rf.e6268330f48c4bcba2b0af2aebde5f90.jpg\n",
1542
"Skipping non-image file: data/Metal, Tin Can/trash-detection_000090_JPG.rf.087bedf5e888bf3a2af8ff1a4ff8fd3d.jpg\n",
1543
"Skipping non-image file: data/Metal, Tin Can/trash-detection_000040_jpg.rf.71348790f07f547a66b52aa9a3e43f2d.jpg\n",
1544
"Skipping non-image file: data/Metal, Tin Can/trash-detection_000043_jpg.rf.c05b1345fbd2d99e80a96af6a77091d1.jpg\n",
1545
"Skipping non-image file: data/Metal, Tin Can/trash-detection_000008_jpg.rf.88603faa9cae2ec4646b0b75a3e648be.jpg\n",
1546
"Skipping non-image file: data/Metal, Tin Can/trash-detection_000042_jpg.rf.fd6535744cf2c15c7550df726bcec4d4.jpg\n",
1547
"Skipping non-image file: data/Metal, Tin Can/trash-detection_000008_jpg.rf.3186979106920fb91f55bb923c55f25e.jpg\n",
1548
"Skipping non-image file: data/Plastic, PP Film/trash-detection_000026_JPG.rf.923be41e1110b7c15c7ee62a7cc4b599.jpg\n",
1549
"Skipping non-image file: data/Plastic, PP Film/trash-detection_000112_JPG.rf.ecb494d674fbfe57583517a4593c8276.jpg\n",
1550
"Skipping non-image file: data/Plastic, PP Film/trash-detection_IMG_4859_JPG.rf.9680bd1e41e69d8ca0a118a10a146bf6.jpg\n",
1551
"Skipping non-image file: data/Paper, Stationery/trash-detection_000098_jpg.rf.713e85e2c9b0d55cb1808768f59272b6.jpg\n",
1552
"Skipping non-image file: data/Other, Chewing Gum Package/trash-detection_000031_jpg.rf.ce23b351f854dc43b568e8b1507def81.jpg\n",
1553
"Skipping non-image file: data/Other, Chewing Gum Package/trash-detection_000031_jpg.rf.bfa579e8ec1d6cd2cd44f8ebf8fcabe4.jpg\n"
1554
]
1555
},
1556
{
1557
"name": "stderr",
1558
"output_type": "stream",
1559
"text": [
1560
" 68%|██████████████████████████████████████████████████████████▎ | 5672/8357 [21:34<00:04, 572.74it/s]"
1561
]
1562
},
1563
{
1564
"name": "stdout",
1565
"output_type": "stream",
1566
"text": [
1567
"Skipping non-image file: data/Glass, Clear Glass/dwc_Glass1,086.HEIC\n",
1568
"Skipping non-image file: data/Glass, Clear Glass/dwc_Glass1,082.HEIC\n",
1569
"Skipping non-image file: data/Glass, Clear Glass/dwc_Glass1,083.HEIC\n",
1570
"Skipping non-image file: data/Glass, Clear Glass/dwc_Glass1,087.HEIC\n",
1571
"Skipping non-image file: data/Glass, Clear Glass/dwc_Glass1,084.HEIC\n",
1572
"Skipping non-image file: data/Glass, Clear Glass/trash-detection_IMG_4914_JPG.rf.9d83429ee75104d7d3e6894b279aff0e.jpg\n",
1573
"Skipping non-image file: data/Glass, Clear Glass/dwc_Glass1,085.HEIC\n",
1574
"Skipping non-image file: data/Glass, Clear Glass/dwc_Glass1,081.HEIC\n"
1575
]
1576
},
1577
{
1578
"name": "stderr",
1579
"output_type": "stream",
1580
"text": [
1581
" 76%|████████████████████████████████████████████████████████████████▉ | 6381/8357 [21:34<00:01, 1446.63it/s]"
1582
]
1583
},
1584
{
1585
"name": "stdout",
1586
"output_type": "stream",
1587
"text": [
1588
"Skipping non-image file: data/Glass, Clear Glass/trash-detection_000012_jpg.rf.5d8e0f9500f3cad343111da55d9e46c0.jpg\n",
1589
"Skipping non-image file: data/Glass, Clear Glass/dwc_Glass1,088.HEIC\n",
1590
"Skipping non-image file: data/Plastic, PS Foam Container/trash-detection_IMG_4921_JPG.rf.9391c78a598c648b795332d9afbb7ffd.jpg\n",
1591
"Skipping non-image file: data/Metal, Bottle Crown/trash-detection_000084_jpg.rf.c65e545b09cf07603bb3a0597ba4ee89.jpg\n",
1592
"Skipping non-image file: data/Other, Construction Waste/trash-detection_000009_jpg.rf.8dbb1bd234f44a6b91031402016768fa.jpg\n",
1593
"Skipping non-image file: data/Plastic, Plastic Bottle Cap/trash-detection_000073_jpg.rf.15adc3dcc4f6c27c10b8355cd39dbbd6.jpg\n",
1594
"Skipping non-image file: data/Plastic, Plastic Bottle Cap/trash-detection_000073_jpg.rf.2a0a26daad68375f61f7449e44f5d497.jpg\n",
1595
"Skipping non-image file: data/Plastic, Plastic Bottle Cap/trash-detection_000073_jpg.rf.2275d8e7deb4e01bcd907ba265a6668b.jpg\n",
1596
"Skipping non-image file: data/Plastic, Plastic Bottle Cap/trash-detection_000042_jpg.rf.5aaefc29b479685507e84f41bd46f87a.jpg\n",
1597
"Skipping non-image file: data/Plastic, Plastic Bottle Cap/trash-detection_000023_jpg.rf.b445fabd1c84f1b89bb9aa2c7676ac87.jpg\n",
1598
"Skipping non-image file: data/Plastic, Plastic Bottle Cap/trash-detection_000006_jpg.rf.457a95ab01fe990be13b7c8052bbc869.jpg\n",
1599
"Skipping non-image file: data/Glass, Green Glass/trash-detection_000017_jpg.rf.05cff7e748de9b8b9f60867aff794b00.jpg\n",
1600
"Skipping non-image file: data/Glass, Green Glass/trash-detection_000016_jpg.rf.4c1acd1340c2bccf65b4b453a94f7664.jpg\n",
1601
"Skipping non-image file: data/Plastic, Plastic Pouch/trash-detection_000009_jpg.rf.2b6766bfae0c905c1c4ce3a98739de89.jpg\n",
1602
"Skipping non-image file: data/Plastic, Plastic Pouch/trash-detection_000014_JPG.rf.a811642d2584206076109bdd469ed44c.jpg\n",
1603
"Skipping non-image file: data/Plastic, Plastic Pouch/trash-detection_000043_JPG.rf.ee923a749c98cd6770534213dddb9cc3.jpg\n",
1604
"Skipping non-image file: data/Plastic, Plastic Pouch/trash-detection_000009_jpg.rf.aa8aee947b58635fb4e978589bdae60c.jpg\n",
1605
"Skipping non-image file: data/Plastic, Plastic Pouch/trash-detection_000009_jpg.rf.66cbaf6da1cd4aa1e8a1430349b77df8.jpg\n",
1606
"Skipping non-image file: data/Plastic, Plastic Pouch/trash-detection_000016_JPG.rf.da64084dc945276c4780e57cce2a9075.jpg\n",
1607
"Skipping non-image file: data/Plastic, Plastic Pouch/trash-detection_000013_JPG.rf.aba0c9a1901d1d2686b2f5b634189bae.jpg\n",
1608
"Skipping non-image file: data/Plastic, Plastic Pouch/trash-detection_000003_JPG.rf.0c7a8e2577a394b6679c60df9a93868d.jpg\n",
1609
"Skipping non-image file: data/Glass, Brown Glass/trash-detection_000024_JPG.rf.1a2e523e0c3e325009a1f2e602bb92c0.jpg\n",
1610
"Skipping non-image file: data/Glass, Brown Glass/trash-detection_000021_jpg.rf.2b192c276cb919dcb803fbed91c07673.jpg\n"
1611
]
1612
},
1613
{
1614
"name": "stderr",
1615
"output_type": "stream",
1616
"text": [
1617
" 80%|████████████████████████████████████████████████████████████████████▏ | 6709/8357 [21:34<00:00, 1781.64it/s]"
1618
]
1619
},
1620
{
1621
"name": "stdout",
1622
"output_type": "stream",
1623
"text": [
1624
"Skipping non-image file: data/Paper, Paper Straw/trash-detection_straw6_jpg.rf.0c8d62c415ac91c59a8c1909628fbc83.jpg\n",
1625
"Skipping non-image file: data/Paper, Paper Straw/trash-detection_000101_JPG.rf.5209e4d21fe4be03a30db44140a32b54.jpg\n",
1626
"Skipping non-image file: data/Paper, Paper Straw/trash-detection_000101_JPG.rf.279716ef392c967c49df65ca8fe1497c.jpg\n",
1627
"Skipping non-image file: data/Paper, Paper Straw/trash-detection_000101_JPG.rf.c52547e12ed83e18c308b611db27bb9d.jpg\n",
1628
"Skipping non-image file: data/Other, Paper Wipe Package/trash-detection_000083_jpg.rf.cc91bf49a7ed8dc8131a608a7e762fd9.jpg\n",
1629
"Skipping non-image file: data/Other, Paper Wipe Package/trash-detection_000083_jpg.rf.517662ed3f68e33ed3c4f2e78f61f932.jpg\n",
1630
"Skipping non-image file: data/Other, Paper Wipe Package/trash-detection_000083_jpg.rf.298ade95114738414612edb5e0a902d1.jpg\n",
1631
"Skipping non-image file: data/Other, Wet Wipe Package/trash-detection_000083_jpg.rf.561a41af1c08dd700e8668a3c48c796a.jpg\n",
1632
"Skipping non-image file: data/Other, Wet Wipe Package/trash-detection_000083_jpg.rf.f5e1213e3d839711fb4433ea4824e855.jpg\n",
1633
"Skipping non-image file: data/Other, Wet Wipe Package/trash-detection_000083_jpg.rf.c9fac0e7f119399de0844c3eaa1462d7.jpg\n",
1634
"Skipping non-image file: data/Plastic, PP Yoghurt Cup/trash-detection_000093_JPG.rf.e6733ce4724a24f9622c3b146f283900.jpg\n",
1635
"Skipping non-image file: data/Plastic, PP Yoghurt Cup/trash-detection_000093_JPG.rf.dca8499c4a876ae8110dc2c6d8c57965.jpg\n",
1636
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000083_jpg.rf.16820a70113dce0f0bca2ed80befd00f.jpg\n",
1637
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000055_JPG.rf.e09498065798e0993e75f0e4e3dc0dc2.jpg\n",
1638
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000029_JPG.rf.d6282a380e9419014fd7fa3cef6f3761.jpg\n",
1639
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000077_jpg.rf.6520d22a5d5af2da584ce9b1438ac499.jpg\n",
1640
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000036_jpg.rf.c4c4a893340b1376e907eac4c47f582d.jpg\n",
1641
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000083_jpg.rf.e3b8d7f50643d0e5227fa72bb2197466.jpg\n",
1642
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000077_jpg.rf.f87afef1b42e3907b721c8664ebb0dce.jpg\n",
1643
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000002_jpg.rf.fca3c2987c7234c5d040895ebd62c569.jpg\n",
1644
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000002_jpg.rf.632e253ff68bcdc1b02c23c5c71e842b.jpg\n",
1645
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000083_jpg.rf.17e11ae8d5ce763b3c897561d09b26e1.jpg\n",
1646
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000002_jpg.rf.222846be53b7ae266eed3959d6e29e4a.jpg\n",
1647
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000052_jpg.rf.7b491604fe5db8d449f1773c0666cc11.jpg\n",
1648
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000003_jpg.rf.792c79caddce68d1323aeee78d2565d0.jpg\n",
1649
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000077_jpg.rf.8486f0621eacf794a5ca2c8b0ac2e8c2.jpg\n",
1650
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000036_jpg.rf.92d56f3c825acce75c98ccaaa8439d3a.jpg\n",
1651
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000026_JPG.rf.52891c20f2272c704d2c4558e9cb9144.jpg\n",
1652
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000002_jpg.rf.9cc898800c81a96a92149265d91b2c4e.jpg\n",
1653
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000031_JPG.rf.e6d983b590746b30cf2f1270b8f840d5.jpg\n",
1654
"Skipping non-image file: data/Paper, Cardboard Cup/trash-detection_000008_JPG.rf.9697ebd659386b8662e56ac099aa156b.jpg\n",
1655
"Skipping non-image file: data/Other, Lighter/trash-detection_000037_jpg.rf.c038b66097e09c72bacfe467ddfd8f9a.jpg\n",
1656
"Skipping non-image file: data/Other, Lighter/trash-detection_000037_jpg.rf.dbfd5f3ee0546731fceeba6bf67a3ca6.jpg\n",
1657
"Skipping non-image file: data/Other, Lighter/trash-detection_000037_jpg.rf.4643eada760d7848eb415e1dacc06712.jpg\n",
1658
"Skipping non-image file: data/Paper, Newspaper or Magazine/trash-detection_IMG_5068_JPG.rf.db14c3ed2832a4b5d84f38d2bb66da4e.jpg\n",
1659
"Skipping non-image file: data/Plastic, HDPE Bottle/hitl_8_gdhRoYsJIm.jpeg\n",
1660
"Skipping non-image file: data/Paper, Newsprint/trash-detection_IMG_5068_JPG.rf.db14c3ed2832a4b5d84f38d2bb66da4e.jpg\n",
1661
"Skipping non-image file: data/Paper, Newsprint/hitl_11_XZQww99SEd.jpeg\n",
1662
"Skipping non-image file: data/Plastic, PET Bottle/hitl_27.jpg\n",
1663
"Skipping non-image file: data/Plastic, PET Bottle/hitl_332.jpeg\n",
1664
"Skipping non-image file: data/Plastic, PET Bottle/hitl_154.jpg\n",
1665
"Skipping non-image file: data/Plastic, PET Bottle/hitl_4.jpeg\n",
1666
"Skipping non-image file: data/Plastic, PET Bottle/hitl_335.jpg\n",
1667
"Skipping non-image file: data/Plastic, PET Bottle/hitl_3_4Xdbl.jpg\n",
1668
"Skipping non-image file: data/Plastic, PET Bottle/hitl_89image00201.jpeg\n",
1669
"Skipping non-image file: data/Plastic, PET Bottle/hitl_334.jpg\n",
1670
"Skipping non-image file: data/Plastic, PET Bottle/hitl_88image00202.jpeg\n",
1671
"Skipping non-image file: data/Plastic, PET Bottle/hitl_14_1.jpg\n",
1672
"Skipping non-image file: data/Plastic, PET Bottle/hitl_114.jpg\n",
1673
"Skipping non-image file: data/Plastic, PET Bottle/hitl_28image01502.jpeg\n",
1674
"Skipping non-image file: data/Plastic, PET Bottle/hitl_343.jpg\n",
1675
"Skipping non-image file: data/Plastic, PET Bottle/hitl_331.jpg\n",
1676
"Skipping non-image file: data/Plastic, PET Bottle/hitl_329.jpg\n",
1677
"Skipping non-image file: data/Plastic, PET Bottle/hitl_324.jpg\n",
1678
"Skipping non-image file: data/Plastic, PET Bottle/hitl_27_jjyAnZyFxh.jpeg\n",
1679
"Skipping non-image file: data/Plastic, PET Bottle/hitl_325.jpg\n",
1680
"Skipping non-image file: data/Plastic, PET Bottle/hitl_2_1.jpg\n",
1681
"Skipping non-image file: data/Plastic, PET Bottle/hitl_327.jpeg\n",
1682
"Skipping non-image file: data/Plastic, PET Bottle/hitl_90_tF5bS9WGD6.jpeg\n",
1683
"Skipping non-image file: data/Plastic, PET Bottle/hitl_28.jpg\n",
1684
"Skipping non-image file: data/Plastic, PET Bottle/hitl_90image00200.jpeg\n",
1685
"Skipping non-image file: data/Plastic, PET Bottle/hitl_183.jpeg\n",
1686
"Skipping non-image file: data/Plastic, PET Bottle/hitl_124.jpg\n",
1687
"Skipping non-image file: data/Plastic, Expanded Polystyrene/hitl_43.jpg\n",
1688
"Skipping non-image file: data/Plastic, Expanded Polystyrene/hitl_9.jpg\n"
1689
]
1690
},
1691
{
1692
"name": "stderr",
1693
"output_type": "stream",
1694
"text": [
1695
" 89%|████████████████████████████████████████████████████████████████████████████▊ | 7467/8357 [21:41<00:03, 230.90it/s]"
1696
]
1697
},
1698
{
1699
"name": "stdout",
1700
"output_type": "stream",
1701
"text": [
1702
"Skipping non-image file: data/Plastic, Clear PP Cup/hitl_9_bYQgKtBz7r.jpeg\n",
1703
"Skipping non-image file: data/Metal, Aluminium Can/hitl_43image00247.jpeg\n",
1704
"Skipping non-image file: data/Metal, Aluminium Can/hitl_47image00243.jpeg\n",
1705
"Skipping non-image file: data/Metal, Aluminium Can/hitl_41image01489.jpeg\n",
1706
"Skipping non-image file: data/Metal, Aluminium Can/hitl_25.jpg\n",
1707
"Skipping non-image file: data/Metal, Aluminium Can/hitl_75.jpeg\n",
1708
"Skipping non-image file: data/Metal, Aluminium Can/hitl_44.jpg\n",
1709
"Skipping non-image file: data/Metal, Aluminium Can/hitl_340.jpg\n",
1710
"Skipping non-image file: data/Paper, Liquid Carton/hitl_44image00246.jpeg\n",
1711
"Skipping non-image file: data/Organic, Leaves/hitl_4_aWfm4.jpeg\n",
1712
"Skipping non-image file: data/Other, Cigarette Package/hitl_29image01501.jpeg\n"
1713
]
1714
},
1715
{
1716
"name": "stderr",
1717
"output_type": "stream",
1718
"text": [
1719
" 90%|██████████████████████████████████████████████████████████████████████████████▋ | 7559/8357 [21:50<00:15, 52.33it/s]"
1720
]
1721
},
1722
{
1723
"name": "stdout",
1724
"output_type": "stream",
1725
"text": [
1726
"Skipping non-image file: data/Plastic, Clear PP Food Container/trash-detection_000045_JPG.rf.3b1d9eb97c960f57bec66f7bff3a701e.jpg\n"
1727
]
1728
},
1729
{
1730
"name": "stderr",
1731
"output_type": "stream",
1732
"text": [
1733
" 95%|██████████████████████████████████████████████████████████████████████████████████▌ | 7925/8357 [21:54<00:05, 83.37it/s]"
1734
]
1735
},
1736
{
1737
"name": "stdout",
1738
"output_type": "stream",
1739
"text": [
1740
"Skipping non-image file: data/Glass, Green Glass/hitl_72.jpg\n",
1741
"Skipping non-image file: data/Plastic, Plastic Pouch/hitl_24image01506.jpeg\n"
1742
]
1743
},
1744
{
1745
"name": "stderr",
1746
"output_type": "stream",
1747
"text": [
1748
" 98%|████████████████████████████████████████████████████████████████████████████████████▉ | 8155/8357 [22:09<00:08, 24.85it/s]"
1749
]
1750
},
1751
{
1752
"name": "stdout",
1753
"output_type": "stream",
1754
"text": [
1755
"Skipping non-image file: data/Paper, Cardboard Cup/hitl_1image01529.jpeg\n"
1756
]
1757
},
1758
{
1759
"name": "stderr",
1760
"output_type": "stream",
1761
"text": [
1762
"100%|███████████████████████████████████████████████████████████████████████████████████████| 8357/8357 [22:12<00:00, 6.27it/s]\n"
1763
]
1764
}
1765
],
1766
"source": [
1767
"import json\n",
1768
"import os\n",
1769
"import shutil\n",
1770
"import random\n",
1771
"import math\n",
1772
"from PIL import Image, UnidentifiedImageError, ImageEnhance, ImageOps\n",
1773
"from tqdm import tqdm\n",
1774
"\n",
1775
"def rotate_point(point, origin, angle):\n",
1776
" \"\"\"Rotate a point around a given centre by angle.\"\"\"\n",
1777
" # Fast calculation for 90 degree rotations\n",
1778
" match angle % 360:\n",
1779
" case 0:\n",
1780
" return point\n",
1781
" case 90:\n",
1782
" return origin[1] + origin[0] - point[1], origin[1] - origin[0] + point[0]\n",
1783
" case 180:\n",
1784
" return 2 * origin[0] - point[0], 2 * origin[1] - point[1]\n",
1785
" case 270:\n",
1786
" return origin[1] - origin[0] + point[1], origin[1] + origin[0] - point[0]\n",
1787
" angle_rad = math.radians(angle)\n",
1788
" ox, oy = origin\n",
1789
" px, py = point\n",
1790
" \n",
1791
" qx = ox + math.cos(angle_rad) * (px - ox) - math.sin(angle_rad) * (py - oy)\n",
1792
" qy = oy + math.sin(angle_rad) * (px - ox) + math.cos(angle_rad) * (py - oy)\n",
1793
" \n",
1794
" return qx, qy\n",
1795
"\n",
1796
"def via_to_yolo_with_rotation(via_annotations_path, images_directory, output_directory, rotation_angles, num_augmented_copies=3):\n",
1797
" if os.path.exists(output_directory):\n",
1798
" shutil.rmtree(output_directory)\n",
1799
" os.makedirs(output_directory)\n",
1800
"\n",
1801
" with open(via_annotations_path, 'r') as f:\n",
1802
" data = json.load(f)\n",
1803
"\n",
1804
" class_mapping = {}\n",
1805
"\n",
1806
" for image_id, image_data in tqdm(data['_via_img_metadata'].items()):\n",
1807
" filename = image_data['filename']\n",
1808
" image_path = os.path.normpath(os.path.join(images_directory, filename))\n",
1809
" try:\n",
1810
" image = Image.open(image_path)\n",
1811
" except (UnidentifiedImageError, IOError):\n",
1812
" print(f\"Skipping non-image file: {image_path}\")\n",
1813
" continue # Skip non-image files\n",
1814
"\n",
1815
" image.verify() # Verifies that this is an image, but does not load it\n",
1816
" image.close() # Close the image file\n",
1817
"\n",
1818
" image = Image.open(image_path) # Reopen for processing\n",
1819
" w, h = image.size\n",
1820
" cx, cy = w / 2, h / 2\n",
1821
"\n",
1822
" class_name = os.path.basename(os.path.dirname(image_path)).split(\",\")[0]\n",
1823
" if class_name not in class_mapping:\n",
1824
" class_mapping[class_name] = len(class_mapping)\n",
1825
" \n",
1826
" # Skip images with no annotations\n",
1827
" if 'regions' not in image_data or len(image_data['regions']) == 0:\n",
1828
" continue\n",
1829
"\n",
1830
" for i in range(num_augmented_copies + 1): # Generate original and augmented copies\n",
1831
" if i == 0:\n",
1832
" angle = 0 # Original image\n",
1833
" flip = False\n",
1834
" output_image_path = os.path.join(output_directory, os.path.basename(image_path))\n",
1835
" image.save(output_image_path)\n",
1836
" else:\n",
1837
" angle = random.choice(rotation_angles)\n",
1838
" output_image_path = os.path.join(output_directory, os.path.splitext(os.path.basename(image_path))[0] + \"_\" + str(i) + os.path.splitext(image_path)[1])\n",
1839
" \n",
1840
" # Random rotation\n",
1841
" modified_image = image.rotate(angle)\n",
1842
" # Random brightness\n",
1843
" enhancer = ImageEnhance.Brightness(modified_image)\n",
1844
" modified_image = enhancer.enhance(random.uniform(0.75, 1.25))\n",
1845
" # Random contrast\n",
1846
" enhancer = ImageEnhance.Contrast(modified_image)\n",
1847
" modified_image = enhancer.enhance(random.uniform(0.625, 1.375))\n",
1848
" # Random sharpness\n",
1849
" enhancer = ImageEnhance.Sharpness(modified_image)\n",
1850
" modified_image = enhancer.enhance(random.uniform(0.5, 1.5))\n",
1851
" # Random colour\n",
1852
" enhancer = ImageEnhance.Color(modified_image)\n",
1853
" modified_image = enhancer.enhance(random.uniform(0.625, 1.375))\n",
1854
" # Random horizontal flip\n",
1855
" if random.random() < 0.5:\n",
1856
" flip = True\n",
1857
" modified_image = ImageOps.mirror(modified_image)\n",
1858
" else:\n",
1859
" flip = False\n",
1860
" # Random RGB deviation\n",
1861
" r_multiplier = random.uniform(0.875, 1.125)\n",
1862
" g_multiplier = random.uniform(0.875, 1.125)\n",
1863
" b_multiplier = random.uniform(0.875, 1.125)\n",
1864
" r, g, b = modified_image.split()\n",
1865
" r = r.point(lambda p: min(255, max(0, int(p * r_multiplier))))\n",
1866
" g = g.point(lambda p: min(255, max(0, int(p * g_multiplier))))\n",
1867
" b = b.point(lambda p: min(255, max(0, int(p * b_multiplier))))\n",
1868
" modified_image = Image.merge(\"RGB\", (r, g, b))\n",
1869
" # Noise\n",
1870
" noise = Image.new(\"RGB\", modified_image.size, (0, 0, 0))\n",
1871
" for _ in range(int(w * h * 0.01)):\n",
1872
" x, y = random.randint(0, w - 1), random.randint(0, h - 1)\n",
1873
" # Salt or pepper?\n",
1874
" if random.random() > 0.25:\n",
1875
" noise.putpixel((x, y), (255, 255, 255))\n",
1876
" else:\n",
1877
" noise.putpixel((x, y), (0, 0, 0))\n",
1878
" modified_image = Image.blend(modified_image, noise, 0.25)\n",
1879
" modified_image.save(output_image_path)\n",
1880
"\n",
1881
" annotations_output_path = os.path.join(output_directory, os.path.splitext(os.path.basename(output_image_path))[0] + '.txt')\n",
1882
" with open(annotations_output_path, 'w') as file:\n",
1883
" if 'regions' not in image_data or len(image_data['regions']) == 0:\n",
1884
" continue # skip unannotated images\n",
1885
" for region in image_data['regions']:\n",
1886
" shape_attr = region['shape_attributes']\n",
1887
" points = []\n",
1888
" if shape_attr['name'] == 'rect':\n",
1889
" x, y, width, height = shape_attr['x'], shape_attr['y'], shape_attr['width'], shape_attr['height']\n",
1890
" points = [(x, y), (x + width, y), (x + width, y + height), (x, y + height)]\n",
1891
" elif shape_attr['name'] == 'polygon':\n",
1892
" points = list(zip(shape_attr['all_points_x'], shape_attr['all_points_y']))\n",
1893
" elif shape_attr['name'] == 'circle':\n",
1894
" cx, cy, r = shape_attr['cx'], shape_attr['cy'], shape_attr['r']\n",
1895
" points = [(cx - r, cy - r), (cx + r, cy - r), (cx + r, cy + r), (cx - r, cy + r)]\n",
1896
" elif shape_attr['name'] == 'ellipse':\n",
1897
" cx, cy, rx, ry = shape_attr['cx'], shape_attr['cy'], shape_attr['rx'], shape_attr['ry']\n",
1898
" angle += shape_attr.get(\"theta\", 0) # Add the rotation angle\n",
1899
" points = [(cx - rx, cy - ry), (cx + rx, cy - ry), (cx + rx, cy + ry), (cx - rx, cy + ry)]\n",
1900
"\n",
1901
" # Rotate points\n",
1902
" if flip:\n",
1903
" points = [(w - pt[0], pt[1]) for pt in points]\n",
1904
" rotated_points = [rotate_point(pt, (cx, cy), angle) for pt in points]\n",
1905
" min_x = max(0, min(pt[0] for pt in rotated_points))\n",
1906
" max_x = min(w, max(pt[0] for pt in rotated_points))\n",
1907
" min_y = max(0, min(pt[1] for pt in rotated_points))\n",
1908
" max_y = min(h, max(pt[1] for pt in rotated_points))\n",
1909
"\n",
1910
" x_center = ((min_x + max_x) / 2) / w\n",
1911
" y_center = ((min_y + max_y) / 2) / h\n",
1912
" box_width = (max_x - min_x) / w\n",
1913
" box_height = (max_y - min_y) / h\n",
1914
" file.write(f\"{class_mapping[class_name]} {x_center} {y_center} {box_width} {box_height}\\n\")\n",
1915
"\n",
1916
" return class_mapping\n",
1917
"\n",
1918
"# Usage example:\n",
1919
"rotation_angles = [0, 90, 180, 270] # Possible rotation angles\n",
1920
"\n",
1921
"OUTPUT_PATH = \"yolo_data/\"\n",
1922
"class_mapping = via_to_yolo_with_rotation(ANNOTATIONS_PATH, DATA_PATH, OUTPUT_PATH, rotation_angles)\n",
1923
"\n",
1924
"# Ensure to define ANNOTATIONS_PATH and DATA_PATH before running the function.\n"
1925
]
1926
},
1927
{
1928
"cell_type": "raw",
1929
"id": "9f725a0feba7feb",
1930
"metadata": {},
1931
"source": [
1932
"import torchvision.transforms.functional as trans\n",
1933
"\n",
1934
"class MyDataset(torch.utils.data.Dataset):\n",
1935
" def __init__(self, image_paths, boxes, classes):\n",
1936
" self.image_paths = image_paths\n",
1937
" self.boxes = boxes\n",
1938
" self.classes = classes\n",
1939
" \n",
1940
" def __len__(self):\n",
1941
" return len(self.image_paths)\n",
1942
" \n",
1943
" def __getitem__(self, idx):\n",
1944
" # image = Image.open(self.image_paths[idx]).convert(\"RGB\")\n",
1945
" image = self.image_paths[idx]\n",
1946
" original_width, original_height = image.shape[2], image.shape[1]\n",
1947
" \n",
1948
" new_width, new_height = 640, 640\n",
1949
" new_boxes = []\n",
1950
" for box in self.boxes[idx]:\n",
1951
" xmin, ymin, xmax, ymax = box\n",
1952
" xmin, xmax = xmin * new_width / original_width, xmax * new_width / original_width\n",
1953
" ymin, ymax = ymin * new_height / original_height, ymax * new_height / original_height\n",
1954
" new_boxes.append([xmin, ymin, xmax, ymax])\n",
1955
" \n",
1956
" info = {\n",
1957
" \"boxes\": new_boxes,\n",
1958
" \"classes\": self.classes[idx],\n",
1959
" }\n",
1960
" \n",
1961
" image = trans.resize(image, (new_width, new_height))\n",
1962
" \n",
1963
" return image, info"
1964
]
1965
},
1966
{
1967
"cell_type": "raw",
1968
"id": "91c7b6a8bcade4f8",
1969
"metadata": {},
1970
"source": [
1971
"def custom_collate_fn(batch):\n",
1972
" images, targets = zip(*batch)\n",
1973
" \n",
1974
" images = torch.stack(images, dim=0)\n",
1975
" \n",
1976
" batch_boxes = []\n",
1977
" batch_classes = []\n",
1978
" \n",
1979
" for target in targets:\n",
1980
" batch_boxes.append(target[\"boxes\"])\n",
1981
" batch_classes.append(target[\"classes\"])\n",
1982
" \n",
1983
" return images, {\n",
1984
" \"boxes\": batch_boxes,\n",
1985
" \"classes\": batch_classes,\n",
1986
" }"
1987
]
1988
},
1989
{
1990
"cell_type": "code",
1991
"execution_count": 1,
1992
"id": "73a63f9dc63594a1",
1993
"metadata": {
1994
"ExecuteTime": {
1995
"end_time": "2024-05-18T06:53:22.560748Z",
1996
"start_time": "2024-05-18T06:53:22.479246Z"
1997
}
1998
},
1999
"outputs": [
2000
{
2001
"ename": "NameError",
2002
"evalue": "name 'class_mapping' is not defined",
2003
"output_type": "error",
2004
"traceback": [
2005
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
2006
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
2007
"Cell \u001b[0;32mIn[1], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;28mlen\u001b[39m(\u001b[43mclass_mapping\u001b[49m), class_mapping\u001b[38;5;241m.\u001b[39mkeys())\n",
2008
"\u001b[0;31mNameError\u001b[0m: name 'class_mapping' is not defined"
2009
]
2010
}
2011
],
2012
"source": [
2013
"print(len(class_mapping), class_mapping.keys())"
2014
]
2015
},
2016
{
2017
"cell_type": "code",
2018
"execution_count": null,
2019
"id": "65fa97a1ae1c78f2",
2020
"metadata": {},
2021
"outputs": [
2022
{
2023
"name": "stdout",
2024
"output_type": "stream",
2025
"text": [
2026
"New https://pypi.org/project/ultralytics/8.2.17 available 😃 Update with 'pip install -U ultralytics'\n",
2027
"Ultralytics YOLOv8.2.15 🚀 Python-3.10.0 torch-2.3.0+cu121 CPU (13th Gen Intel Core(TM) i9-13900KF)\n",
2028
"\u001b[34m\u001b[1mengine/trainer: \u001b[0mtask=detect, mode=train, model=yolov8n.pt, data=yolo.yaml, epochs=40, time=None, patience=100, batch=16, imgsz=640, save=True, save_period=-1, cache=False, device=None, workers=8, project=None, name=train20, exist_ok=False, pretrained=True, optimizer=auto, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, amp=True, fraction=1.0, profile=False, freeze=None, multi_scale=False, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, vid_stride=1, stream_buffer=False, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, embed=None, show=False, save_frames=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, show_boxes=True, line_width=None, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=None, workspace=4, nms=False, lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=7.5, cls=0.5, dfl=1.5, pose=12.0, kobj=1.0, label_smoothing=0.0, nbs=64, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, bgr=0.0, mosaic=1.0, mixup=0.0, copy_paste=0.0, auto_augment=randaugment, erasing=0.4, crop_fraction=1.0, cfg=None, tracker=botsort.yaml, save_dir=runs/detect/train20\n",
2029
"Overriding model.yaml nc=80 with nc=10\n",
2030
"\n",
2031
" from n params module arguments \n",
2032
" 0 -1 1 464 ultralytics.nn.modules.conv.Conv [3, 16, 3, 2] \n",
2033
" 1 -1 1 4672 ultralytics.nn.modules.conv.Conv [16, 32, 3, 2] \n",
2034
" 2 -1 1 7360 ultralytics.nn.modules.block.C2f [32, 32, 1, True] \n",
2035
" 3 -1 1 18560 ultralytics.nn.modules.conv.Conv [32, 64, 3, 2] \n",
2036
" 4 -1 2 49664 ultralytics.nn.modules.block.C2f [64, 64, 2, True] \n",
2037
" 5 -1 1 73984 ultralytics.nn.modules.conv.Conv [64, 128, 3, 2] \n",
2038
" 6 -1 2 197632 ultralytics.nn.modules.block.C2f [128, 128, 2, True] \n",
2039
" 7 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2] \n",
2040
" 8 -1 1 460288 ultralytics.nn.modules.block.C2f [256, 256, 1, True] \n",
2041
" 9 -1 1 164608 ultralytics.nn.modules.block.SPPF [256, 256, 5] \n",
2042
" 10 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n",
2043
" 11 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] \n",
2044
" 12 -1 1 148224 ultralytics.nn.modules.block.C2f [384, 128, 1] \n",
2045
" 13 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n",
2046
" 14 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] \n",
2047
" 15 -1 1 37248 ultralytics.nn.modules.block.C2f [192, 64, 1] \n",
2048
" 16 -1 1 36992 ultralytics.nn.modules.conv.Conv [64, 64, 3, 2] \n",
2049
" 17 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1] \n",
2050
" 18 -1 1 123648 ultralytics.nn.modules.block.C2f [192, 128, 1] \n",
2051
" 19 -1 1 147712 ultralytics.nn.modules.conv.Conv [128, 128, 3, 2] \n",
2052
" 20 [-1, 9] 1 0 ultralytics.nn.modules.conv.Concat [1] \n",
2053
" 21 -1 1 493056 ultralytics.nn.modules.block.C2f [384, 256, 1] \n",
2054
" 22 [15, 18, 21] 1 753262 ultralytics.nn.modules.head.Detect [10, [64, 128, 256]] \n",
2055
"Model summary: 225 layers, 3012798 parameters, 3012782 gradients, 8.2 GFLOPs\n",
2056
"\n",
2057
"Transferred 319/355 items from pretrained weights\n",
2058
"Freezing layer 'model.22.dfl.conv.weight'\n"
2059
]
2060
},
2061
{
2062
"name": "stderr",
2063
"output_type": "stream",
2064
"text": [
2065
"\u001b[34m\u001b[1mtrain: \u001b[0mScanning /home/vlad/Desktop/litewaste/yolo_data... 5008 images, 0 backgrounds, 7 corrupt: 100%|██████████| 5008/5008 [00:\u001b[0m"
2066
]
2067
},
2068
{
2069
"name": "stdout",
2070
"output_type": "stream",
2071
"text": [
2072
"\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /home/vlad/Desktop/litewaste/yolo_data/dwc_AluCan186_3.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.0073]\n",
2073
"\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /home/vlad/Desktop/litewaste/yolo_data/dwc_AluCan953_3.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.0103]\n",
2074
"\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /home/vlad/Desktop/litewaste/yolo_data/original_20230702_175219_2.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.0301 1.0441]\n",
2075
"\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /home/vlad/Desktop/litewaste/yolo_data/original_20230702_175219_3.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.0301 1.0441]\n",
2076
"\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /home/vlad/Desktop/litewaste/yolo_data/original_20230702_175652_2.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.0154]\n",
2077
"\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /home/vlad/Desktop/litewaste/yolo_data/original_20230702_175652_3.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.0013]\n",
2078
"\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /home/vlad/Desktop/litewaste/yolo_data/original_IMG-20240422-WA0026_1.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.0037]\n"
2079
]
2080
},
2081
{
2082
"name": "stderr",
2083
"output_type": "stream",
2084
"text": [
2085
"\n"
2086
]
2087
},
2088
{
2089
"name": "stdout",
2090
"output_type": "stream",
2091
"text": [
2092
"\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: /home/vlad/Desktop/litewaste/yolo_data.cache\n"
2093
]
2094
},
2095
{
2096
"name": "stderr",
2097
"output_type": "stream",
2098
"text": [
2099
"\u001b[34m\u001b[1mval: \u001b[0mScanning /home/vlad/Desktop/litewaste/yolo_data.cache... 5008 images, 0 backgrounds, 7 corrupt: 100%|██████████| 5008/5008 \u001b[0m"
2100
]
2101
},
2102
{
2103
"name": "stdout",
2104
"output_type": "stream",
2105
"text": [
2106
"\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /home/vlad/Desktop/litewaste/yolo_data/dwc_AluCan186_3.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.0073]\n",
2107
"\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /home/vlad/Desktop/litewaste/yolo_data/dwc_AluCan953_3.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.0103]\n",
2108
"\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /home/vlad/Desktop/litewaste/yolo_data/original_20230702_175219_2.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.0301 1.0441]\n",
2109
"\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /home/vlad/Desktop/litewaste/yolo_data/original_20230702_175219_3.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.0301 1.0441]\n",
2110
"\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /home/vlad/Desktop/litewaste/yolo_data/original_20230702_175652_2.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.0154]\n",
2111
"\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /home/vlad/Desktop/litewaste/yolo_data/original_20230702_175652_3.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.0013]\n",
2112
"\u001b[34m\u001b[1mtrain: \u001b[0mWARNING ⚠️ /home/vlad/Desktop/litewaste/yolo_data/original_IMG-20240422-WA0026_1.jpg: ignoring corrupt image/label: non-normalized or out of bounds coordinates [ 1.0037]\n",
2113
"Plotting labels to runs/detect/train20/labels.jpg... \n"
2114
]
2115
},
2116
{
2117
"name": "stderr",
2118
"output_type": "stream",
2119
"text": [
2120
"\n"
2121
]
2122
},
2123
{
2124
"name": "stdout",
2125
"output_type": "stream",
2126
"text": [
2127
"\u001b[34m\u001b[1moptimizer:\u001b[0m 'optimizer=auto' found, ignoring 'lr0=0.01' and 'momentum=0.937' and determining best 'optimizer', 'lr0' and 'momentum' automatically... \n",
2128
"\u001b[34m\u001b[1moptimizer:\u001b[0m AdamW(lr=0.000714, momentum=0.9) with parameter groups 57 weight(decay=0.0), 64 weight(decay=0.0005), 63 bias(decay=0.0)\n",
2129
"Image sizes 640 train, 640 val\n",
2130
"Using 0 dataloader workers\n",
2131
"Logging results to \u001b[1mruns/detect/train20\u001b[0m\n",
2132
"Starting training for 40 epochs...\n",
2133
"\n",
2134
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
2135
]
2136
},
2137
{
2138
"name": "stderr",
2139
"output_type": "stream",
2140
"text": [
2141
" 1/40 0G 1.51 3.486 1.918 19 640: 100%|██████████| 313/313 [09:37<00:00, 1.84s/it]\n",
2142
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 157/157 [05:41<00:00,\n"
2143
]
2144
},
2145
{
2146
"name": "stdout",
2147
"output_type": "stream",
2148
"text": [
2149
" all 5001 5662 0.447 0.142 0.0814 0.0415\n",
2150
"\n",
2151
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
2152
]
2153
},
2154
{
2155
"name": "stderr",
2156
"output_type": "stream",
2157
"text": [
2158
" 2/40 0G 1.563 2.99 1.939 20 640: 100%|██████████| 313/313 [09:58<00:00, 1.91s/it]\n",
2159
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 157/157 [05:47<00:00,\n"
2160
]
2161
},
2162
{
2163
"name": "stdout",
2164
"output_type": "stream",
2165
"text": [
2166
" all 5001 5662 0.473 0.14 0.0936 0.0474\n",
2167
"\n",
2168
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
2169
]
2170
},
2171
{
2172
"name": "stderr",
2173
"output_type": "stream",
2174
"text": [
2175
" 3/40 0G 1.574 2.802 1.938 25 640: 100%|██████████| 313/313 [10:02<00:00, 1.93s/it]\n",
2176
" Class Images Instances Box(P R mAP50 mAP50-95): 100%|██████████| 157/157 [05:44<00:00,\n"
2177
]
2178
},
2179
{
2180
"name": "stdout",
2181
"output_type": "stream",
2182
"text": [
2183
" all 5001 5662 0.726 0.155 0.142 0.0717\n",
2184
"\n",
2185
" Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size\n"
2186
]
2187
},
2188
{
2189
"name": "stderr",
2190
"output_type": "stream",
2191
"text": [
2192
" 4/40 0G 1.54 2.684 1.911 35 640: 17%|█▋ | 52/313 [01:41<08:47, 2.02s/it]"
2193
]
2194
}
2195
],
2196
"source": [
2197
"# from torch.utils.data import DataLoader\n",
2198
"# \n",
2199
"# # Create the dataset\n",
2200
"# dataset = MyDataset(images, boxes, classes)\n",
2201
"# \n",
2202
"# # Create the DataLoader\n",
2203
"# data_loader = DataLoader(dataset, batch_size=4, shuffle=True, collate_fn=custom_collate_fn)\n",
2204
"\n",
2205
"from ultralytics import YOLO\n",
2206
"model = YOLO(\"yolov8n.pt\")\n",
2207
"\n",
2208
"results = model.train(data=\"yolo.yaml\", epochs=40, verbose=True, imgsz=640)"
2209
]
2210
},
2211
{
2212
"cell_type": "markdown",
2213
"id": "177aa8663f9b3ecd",
2214
"metadata": {},
2215
"source": [
2216
"Splitting data into training and validation:"
2217
]
2218
},
2219
{
2220
"cell_type": "code",
2221
"execution_count": null,
2222
"id": "138880b6a127671a",
2223
"metadata": {},
2224
"outputs": [],
2225
"source": [
2226
"torch.save(model.state_dict(), 'model.pt')"
2227
]
2228
},
2229
{
2230
"cell_type": "code",
2231
"execution_count": 1,
2232
"id": "cf66bcb81e1b29f",
2233
"metadata": {
2234
"ExecuteTime": {
2235
"end_time": "2024-05-17T18:33:43.472585Z",
2236
"start_time": "2024-05-17T18:24:30.254649Z"
2237
}
2238
},
2239
"outputs": [
2240
{
2241
"name": "stdout",
2242
"output_type": "stream",
2243
"text": [
2244
"\n",
2245
"0: 640x640 (no detections), 4.8ms\n",
2246
"Speed: 2.3ms preprocess, 4.8ms inference, 25.7ms postprocess per image at shape (1, 3, 640, 640)\n"
2247
]
2248
},
2249
{
2250
"ename": "KeyboardInterrupt",
2251
"evalue": "",
2252
"output_type": "error",
2253
"traceback": [
2254
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
2255
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
2256
"Cell \u001b[0;32mIn[1], line 70\u001b[0m\n\u001b[1;32m 66\u001b[0m img \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39marray(img_pil)\n\u001b[1;32m 69\u001b[0m cv\u001b[38;5;241m.\u001b[39mimshow(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mWebcam\u001b[39m\u001b[38;5;124m'\u001b[39m, img)\n\u001b[0;32m---> 70\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[43mcv\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mwaitKey\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m1\u001b[39;49m\u001b[43m)\u001b[49m \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m27\u001b[39m:\n\u001b[1;32m 71\u001b[0m \u001b[38;5;28;01mbreak\u001b[39;00m\n\u001b[1;32m 73\u001b[0m cap\u001b[38;5;241m.\u001b[39mrelease()\n",
2257
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
2258
]
2259
}
2260
],
2261
"source": [
2262
"from ultralytics import YOLO\n",
2263
"import os\n",
2264
"\n",
2265
"#model = YOLO(\"model.pt\")\n",
2266
"os.chdir(\"/home/vlad/Desktop/litewaste\")\n",
2267
"\n",
2268
"model = YOLO(\"runs/detect/train15/weights/best.pt\")\n",
2269
"# test.load_state_dict(torch.load('model.pt'), strict=False)\n",
2270
"\n",
2271
"import cv2 as cv\n",
2272
"import numpy as np\n",
2273
"import torchvision.transforms as transforms\n",
2274
"from PIL import Image, ImageFont, ImageDraw\n",
2275
"\n",
2276
"import matplotlib.pyplot as plt\n",
2277
"import matplotlib.patches as patches\n",
2278
"\n",
2279
"results = model([\"../tester.jpg\"])\n",
2280
"\n",
2281
"# Convert PIL image to array for plotting\n",
2282
"import numpy as np\n",
2283
"import math\n",
2284
"cap = cv.VideoCapture(0)\n",
2285
"cap.set(3, 640)\n",
2286
"cap.set(4, 640)\n",
2287
"\n",
2288
"class_mapping = ['Textile', 'Paper', 'Plastic', 'Other', 'Metal', 'Medical', 'Wood', 'Glass', 'Organic', 'Electronic']\n",
2289
"\n",
2290
"font = ImageFont.truetype(\"/home/vlad/.local/share/fonts/Roboto-Medium.ttf\", 20)\n",
2291
"\n",
2292
"while True:\n",
2293
" success, img = cap.read()\n",
2294
" results = model(img, stream=True, verbose=False)\n",
2295
"\n",
2296
" # coordinates\n",
2297
" for r in results:\n",
2298
" boxes = r.boxes\n",
2299
"\n",
2300
" for box in boxes:\n",
2301
" # bounding box\n",
2302
" x1, y1, x2, y2 = box.xyxy[0]\n",
2303
" x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2) # convert to int values\n",
2304
"\n",
2305
" # put box in cam\n",
2306
" cv.rectangle(img, (x1, y1), (x2, y2), (255, 255, 255), 2)\n",
2307
" cv.rectangle(img, (x1-1, y1-1), (x2+1, y2+1), (136, 150, 0), 2)\n",
2308
"\n",
2309
" # confidence\n",
2310
" confidence = round(float(box.conf[0] * 100))\n",
2311
"\n",
2312
" if confidence < 50:\n",
2313
" continue\n",
2314
"\n",
2315
" # class name\n",
2316
" cls = int(box.cls[0])\n",
2317
"\n",
2318
" # object details\n",
2319
" img_pil = Image.fromarray(img)\n",
2320
" draw = ImageDraw.Draw(img_pil)\n",
2321
" draw.text((x1, y1),\n",
2322
" f\"[{confidence}%] {class_mapping[cls]}\",\n",
2323
" font=font,\n",
2324
" fill=(255, 255, 255),\n",
2325
" stroke_width=1,\n",
2326
" stroke_fill=(0, 0, 0))\n",
2327
" img = np.array(img_pil)\n",
2328
"\n",
2329
"\n",
2330
" cv.imshow('Webcam', img)\n",
2331
" if cv.waitKey(1) == 27:\n",
2332
" break\n",
2333
"\n",
2334
"cap.release()\n",
2335
"cv.destroyAllWindows()"
2336
]
2337
},
2338
{
2339
"cell_type": "code",
2340
"execution_count": 6,
2341
"id": "5c3a7e358cf3efb5",
2342
"metadata": {
2343
"ExecuteTime": {
2344
"end_time": "2024-05-15T16:20:48.053119Z",
2345
"start_time": "2024-05-15T16:20:45.864277Z"
2346
}
2347
},
2348
"outputs": [
2349
{
2350
"name": "stdout",
2351
"output_type": "stream",
2352
"text": [
2353
"\n",
2354
"0: 640x640 (no detections), 3.2ms\n",
2355
"Speed: 1.7ms preprocess, 3.2ms inference, 8.2ms postprocess per image at shape (1, 3, 640, 640)\n"
2356
]
2357
},
2358
{
2359
"ename": "NameError",
2360
"evalue": "name 'cap' is not defined",
2361
"output_type": "error",
2362
"traceback": [
2363
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
2364
"\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
2365
"Cell \u001b[0;32mIn[6], line 67\u001b[0m\n\u001b[1;32m 63\u001b[0m cv\u001b[38;5;241m.\u001b[39mimshow(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mPhoto\u001b[39m\u001b[38;5;124m'\u001b[39m, img)\n\u001b[1;32m 65\u001b[0m cv\u001b[38;5;241m.\u001b[39mwaitKey(\u001b[38;5;241m27\u001b[39m)\n\u001b[0;32m---> 67\u001b[0m \u001b[43mcap\u001b[49m\u001b[38;5;241m.\u001b[39mrelease()\n\u001b[1;32m 68\u001b[0m cv\u001b[38;5;241m.\u001b[39mdestroyAllWindows()\n",
2366
"\u001b[0;31mNameError\u001b[0m: name 'cap' is not defined"
2367
]
2368
}
2369
],
2370
"source": [
2371
"from ultralytics import YOLO\n",
2372
"import os\n",
2373
"\n",
2374
"#model = YOLO(\"model.pt\")\n",
2375
"os.chdir(\"/home/vlad/Desktop/litewaste\")\n",
2376
"\n",
2377
"model = YOLO(\"runs/detect/train15/weights/best.pt\")\n",
2378
"# test.load_state_dict(torch.load('model.pt'), strict=False)\n",
2379
"\n",
2380
"import cv2 as cv\n",
2381
"import numpy as np\n",
2382
"import torchvision.transforms as transforms\n",
2383
"from PIL import Image, ImageFont, ImageDraw\n",
2384
"\n",
2385
"import matplotlib.pyplot as plt\n",
2386
"import matplotlib.patches as patches\n",
2387
"\n",
2388
"# Convert PIL image to array for plotting\n",
2389
"import numpy as np\n",
2390
"import math\n",
2391
"\n",
2392
"class_mapping = ['Textile', 'Paper', 'Plastic', 'Other', 'Metal', 'Medical', 'Wood', 'Glass', 'Organic', 'Electronic']\n",
2393
"\n",
2394
"font = ImageFont.truetype(\"/home/vlad/.local/share/fonts/Roboto-Medium.ttf\", 20)\n",
2395
"\n",
2396
"img = cv.imread(\"../tester.jpg\")\n",
2397
"results = model(img)\n",
2398
"\n",
2399
"# coordinates\n",
2400
"for r in results:\n",
2401
" boxes = r.boxes\n",
2402
"\n",
2403
" for box in boxes:\n",
2404
" # bounding box\n",
2405
" x1, y1, x2, y2 = box.xyxy[0]\n",
2406
" x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2) # convert to int values\n",
2407
"\n",
2408
" # put box in cam\n",
2409
" cv.rectangle(img, (x1, y1), (x2, y2), (255, 255, 255), 2)\n",
2410
" cv.rectangle(img, (x1-1, y1-1), (x2+1, y2+1), (136, 150, 0), 2)\n",
2411
"\n",
2412
" # confidence\n",
2413
" confidence = round(float(box.conf[0] * 100))\n",
2414
"\n",
2415
" if confidence < 25:\n",
2416
" continue\n",
2417
"\n",
2418
" # class name\n",
2419
" cls = int(box.cls[0])\n",
2420
"\n",
2421
" # object details\n",
2422
" img_pil = Image.fromarray(img)\n",
2423
" draw = ImageDraw.Draw(img_pil)\n",
2424
" draw.text((x1, y1),\n",
2425
" f\"[{confidence}%] {class_mapping[cls]}\",\n",
2426
" font=font,\n",
2427
" fill=(255, 255, 255),\n",
2428
" stroke_width=1,\n",
2429
" stroke_fill=(0, 0, 0))\n",
2430
" img = np.array(img_pil)\n",
2431
"\n",
2432
"\n",
2433
"cv.imshow('Photo', img)\n",
2434
"\n",
2435
"cv.waitKey(27)\n",
2436
"\n",
2437
"cv.destroyAllWindows()"
2438
]
2439
},
2440
{
2441
"cell_type": "markdown",
2442
"id": "32abd240-9aff-4ede-a315-a04438b80312",
2443
"metadata": {},
2444
"source": [
2445
"Reading the images:"
2446
]
2447
},
2448
{
2449
"cell_type": "code",
2450
"execution_count": 75,
2451
"id": "4c3af032-689c-4913-96b7-29a1bf9c8103",
2452
"metadata": {},
2453
"outputs": [],
2454
"source": [
2455
"def load_image(path):\n",
2456
" image = tf.io.read_file(path)\n",
2457
" image = tf.image.decode_jpeg(image, channels=3)\n",
2458
" return image"
2459
]
2460
},
2461
{
2462
"cell_type": "code",
2463
"execution_count": 76,
2464
"id": "4afa270a-b5ca-4a75-b443-5adf9544b9b9",
2465
"metadata": {},
2466
"outputs": [],
2467
"source": [
2468
"def load_dataset(path, kls, bbx):\n",
2469
" image = load_image(path)\n",
2470
" boxes = {\n",
2471
" \"classes\": tf.cast(kls, dtype=tf.float32),\n",
2472
" \"boxes\": bbx,\n",
2473
" }\n",
2474
" return {\n",
2475
" \"images\": tf.cast(image, tf.float32),\n",
2476
" \"bounding_boxes\": boxes,\n",
2477
" }"
2478
]
2479
},
2480
{
2481
"cell_type": "markdown",
2482
"id": "d5f48353-5825-487d-8419-d46a65406a01",
2483
"metadata": {},
2484
"source": [
2485
"Augmentation:"
2486
]
2487
},
2488
{
2489
"cell_type": "code",
2490
"execution_count": 77,
2491
"id": "07515196-d6d2-4f21-b5ff-109886fa2c2f",
2492
"metadata": {
2493
"scrolled": true
2494
},
2495
"outputs": [
2496
{
2497
"name": "stdout",
2498
"output_type": "stream",
2499
"text": [
2500
"(927,) (927, None) (927, None, None)\n"
2501
]
2502
}
2503
],
2504
"source": [
2505
"from tensorflow import keras\n",
2506
"import keras_cv\n",
2507
"from keras_cv import bounding_box\n",
2508
"from keras_cv import visualization\n",
2509
"\n",
2510
"augmenter = keras.Sequential(\n",
2511
" layers=[\n",
2512
" keras_cv.layers.RandomFlip(mode=\"horizontal\", bounding_box_format=\"xyxy\"),\n",
2513
" keras_cv.layers.RandomShear(\n",
2514
" x_factor=0.2, y_factor=0.2, bounding_box_format=\"xyxy\"\n",
2515
" ),\n",
2516
" keras_cv.layers.JitteredResize(\n",
2517
" target_size=(640, 640), scale_factor=(0.75, 1.3), bounding_box_format=\"xyxy\"\n",
2518
" ),\n",
2519
" ]\n",
2520
")\n",
2521
"\n",
2522
"print(img.get_shape(), kls.get_shape(), bbx.get_shape())"
2523
]
2524
},
2525
{
2526
"cell_type": "code",
2527
"execution_count": 78,
2528
"id": "1c6d5293-afe6-467d-88f1-a1a4eacbd32d",
2529
"metadata": {},
2530
"outputs": [],
2531
"source": [
2532
"resizing = keras_cv.layers.JitteredResize(\n",
2533
" target_size=(640, 640),\n",
2534
" scale_factor=(0.75, 1.3),\n",
2535
" bounding_box_format=\"xyxy\",\n",
2536
")\n",
2537
"\n",
2538
"train_ds = train_data.map(load_dataset, num_parallel_calls=tf.data.AUTOTUNE)\n",
2539
"train_ds = train_ds.shuffle(BATCH_SIZE * 4)\n",
2540
"train_ds = train_ds.ragged_batch(BATCH_SIZE, drop_remainder=True)\n",
2541
"train_ds = train_ds.map(resizing, num_parallel_calls=tf.data.AUTOTUNE)"
2542
]
2543
},
2544
{
2545
"cell_type": "code",
2546
"execution_count": 79,
2547
"id": "c3092d2f-e38c-4d5b-9711-41351f26e63b",
2548
"metadata": {},
2549
"outputs": [],
2550
"source": [
2551
"resizing = keras_cv.layers.JitteredResize(\n",
2552
" target_size=(640, 640),\n",
2553
" scale_factor=(0.75, 1.3),\n",
2554
" bounding_box_format=\"xyxy\",\n",
2555
")\n",
2556
"\n",
2557
"val_ds = val_data.map(load_dataset, num_parallel_calls=tf.data.AUTOTUNE)\n",
2558
"val_ds = val_ds.shuffle(BATCH_SIZE * 4)\n",
2559
"val_ds = val_ds.ragged_batch(BATCH_SIZE, drop_remainder=True)\n",
2560
"val_ds = val_ds.map(resizing, num_parallel_calls=tf.data.AUTOTUNE)"
2561
]
2562
},
2563
{
2564
"cell_type": "code",
2565
"execution_count": 80,
2566
"id": "8e405972-ef9e-4a06-90e5-5534de03941f",
2567
"metadata": {},
2568
"outputs": [],
2569
"source": [
2570
"def dict_to_tuple(inputs):\n",
2571
" return inputs[\"images\"], inputs[\"bounding_boxes\"]\n",
2572
"\n",
2573
"\n",
2574
"train_ds = train_ds.map(dict_to_tuple, num_parallel_calls=tf.data.AUTOTUNE)\n",
2575
"train_ds = train_ds.prefetch(tf.data.AUTOTUNE)\n",
2576
"\n",
2577
"val_ds = val_ds.map(dict_to_tuple, num_parallel_calls=tf.data.AUTOTUNE)\n",
2578
"val_ds = val_ds.prefetch(tf.data.AUTOTUNE)"
2579
]
2580
},
2581
{
2582
"cell_type": "code",
2583
"execution_count": 81,
2584
"id": "2e8fbba0-7de8-4d1b-b20e-980b4a54feaa",
2585
"metadata": {},
2586
"outputs": [
2587
{
2588
"name": "stdout",
2589
"output_type": "stream",
2590
"text": [
2591
"<_PrefetchDataset element_spec=(TensorSpec(shape=(8, 640, 640, 3), dtype=tf.float32, name=None), {'classes': RaggedTensorSpec(TensorShape([8, None]), tf.float32, 1, tf.int64), 'boxes': RaggedTensorSpec(TensorShape([8, None, None]), tf.float32, 1, tf.int64)})>\n"
2592
]
2593
}
2594
],
2595
"source": [
2596
"print(val_ds)"
2597
]
2598
},
2599
{
2600
"cell_type": "code",
2601
"execution_count": 82,
2602
"id": "4716d3ba-8894-403f-bd72-1b86bd111826",
2603
"metadata": {},
2604
"outputs": [
2605
{
2606
"name": "stderr",
2607
"output_type": "stream",
2608
"text": [
2609
"/home/vlad/miniconda3/envs/tf/lib/python3.9/site-packages/keras_cv/src/models/backbones/backbone.py:44: UserWarning:\n",
2610
"\n",
2611
"`Model.state_updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically.\n",
2612
"\n",
2613
"/home/vlad/miniconda3/envs/tf/lib/python3.9/site-packages/keras_cv/src/models/backbones/backbone.py:44: UserWarning:\n",
2614
"\n",
2615
"`layer.updates` will be removed in a future version. This property should not be used in TensorFlow 2.0, as `updates` are applied automatically.\n",
2616
"\n"
2617
]
2618
}
2619
],
2620
"source": [
2621
"class_mapping = dict(zip(range(len(CLASS_NAMES)), CLASS_NAMES))\n",
2622
"\n",
2623
"with keras.utils.custom_object_scope({'YOLOV8Backbone': keras_cv.models.YOLOV8Backbone}):\n",
2624
" backbone = keras_cv.models.YOLOV8Backbone.from_preset(\n",
2625
" \"yolo_v8_m_backbone_coco\" # We will use yolov8 small backbone with coco weights\n",
2626
" )\n",
2627
" \n",
2628
" yolo = keras_cv.models.YOLOV8Detector(\n",
2629
" num_classes=len(class_mapping),\n",
2630
" bounding_box_format=\"xyxy\",\n",
2631
" backbone=backbone,\n",
2632
" fpn_depth=1,\n",
2633
" )"
2634
]
2635
},
2636
{
2637
"cell_type": "markdown",
2638
"id": "b139c0c2",
2639
"metadata": {},
2640
"source": [
2641
"## model definition and training"
2642
]
2643
},
2644
{
2645
"cell_type": "code",
2646
"execution_count": 100,
2647
"id": "4d11f037-0c71-4df8-9944-54e2fd72fef8",
2648
"metadata": {},
2649
"outputs": [],
2650
"source": [
2651
"total_layers = len(model.layers)\n",
2652
"freeze_until = int(total_layers * 0.25) # Freezing first 70% of layers\n",
2653
"\n",
2654
"# Freeze the first 70% of layers\n",
2655
"for layer in model.layers[:freeze_until]:\n",
2656
" layer.trainable = False\n",
2657
"\n",
2658
"# Unfreeze the remaining layers\n",
2659
"for layer in model.layers[freeze_until:]:\n",
2660
" layer.trainable = True\n",
2661
"\n",
2662
"optimizer = tf.keras.optimizers.Adam(\n",
2663
" learning_rate=0.000625,\n",
2664
" global_clipnorm=10,\n",
2665
")\n",
2666
"\n",
2667
"yolo.compile(\n",
2668
" optimizer=optimizer, classification_loss=\"binary_crossentropy\", box_loss=\"ciou\"\n",
2669
")"
2670
]
2671
},
2672
{
2673
"cell_type": "code",
2674
"execution_count": 101,
2675
"id": "29166924-3e9c-49cb-8dff-02899f6cbe51",
2676
"metadata": {
2677
"collapsed": true,
2678
"jupyter": {
2679
"outputs_hidden": true,
2680
"source_hidden": true
2681
}
2682
},
2683
"outputs": [
2684
{
2685
"name": "stderr",
2686
"output_type": "stream",
2687
"text": [
2688
"2024-05-09 22:28:23.870505: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_1' with dtype variant and shape [927]\n",
2689
"\t [[{{node Placeholder/_1}}]]\n",
2690
"2024-05-09 22:28:23.870671: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_2' with dtype variant and shape [927]\n",
2691
"\t [[{{node Placeholder/_2}}]]\n"
2692
]
2693
},
2694
{
2695
"name": "stdout",
2696
"output_type": "stream",
2697
"text": [
2698
"tf.Tensor(\n",
2699
"[[[[204.8016 197.3596 160.6386]\n",
2700
" [212.791 203.4798 168.2062]\n",
2701
" [204.6741 194.3912 162.704 ]\n",
2702
" ...\n",
2703
" [149.748 136.3546 121.3158]\n",
2704
" [202.0562 194.942 178.2246]\n",
2705
" [252.0557 249.3583 231.6049]]\n",
2706
"\n",
2707
" [[192.8409 186.3591 150.1182]\n",
2708
" [191.3198 184.6421 150.0023]\n",
2709
" [190.1237 183.1214 150.1269]\n",
2710
" ...\n",
2711
" [179.4656 168.3742 151.0153]\n",
2712
" [234.9913 229.3943 209.9673]\n",
2713
" [247.1081 244.988 224.6991]]\n",
2714
"\n",
2715
" [[172.6535 166.6535 130.6535]\n",
2716
" [174.3477 168.3477 134.3477]\n",
2717
" [177.8477 171.8477 138.519 ]\n",
2718
" ...\n",
2719
" [217.3168 207.358 185.964 ]\n",
2720
" [242.9402 237.403 215.6355]\n",
2721
" [227.7901 226.0432 202.9718]]\n",
2722
"\n",
2723
" ...\n",
2724
"\n",
2725
" [[144.806 156.4224 134.8525]\n",
2726
" [123.3911 138.774 118.048 ]\n",
2727
" [ 89.824 109.2165 87.8544]\n",
2728
" ...\n",
2729
" [186.2921 180.5943 181.4161]\n",
2730
" [201.576 194.3604 192.5675]\n",
2731
" [201.0829 193.4781 191.2181]]\n",
2732
"\n",
2733
" [[113.8869 129.0949 108.9071]\n",
2734
" [ 88.5344 106.508 87.0471]\n",
2735
" [ 65.92 86.5084 66.9947]\n",
2736
" ...\n",
2737
" [194.5228 190.2998 191.4127]\n",
2738
" [204.854 200.4095 198.6846]\n",
2739
" [188.9374 184.1287 181.0699]]\n",
2740
"\n",
2741
" [[ 74.8236 92.7973 73.1145]\n",
2742
" [ 59.1424 78.199 59.0149]\n",
2743
" [ 48.0821 69.7535 51.9495]\n",
2744
" ...\n",
2745
" [198.4635 195.8813 197.9681]\n",
2746
" [192.6104 190.7708 189.5002]\n",
2747
" [171.1728 169.0474 165.2515]]]\n",
2748
"\n",
2749
"\n",
2750
" [[[ 99.7307 89.7307 87.7307]\n",
2751
" [ 99.6084 89.6084 87.6084]\n",
2752
" [ 98.3023 88.3023 86.6046]\n",
2753
" ...\n",
2754
" [ 93.4985 83.4985 81.4985]\n",
2755
" [ 96.8099 86.8099 84.8099]\n",
2756
" [ 98.9996 88.9996 86.9996]]\n",
2757
"\n",
2758
" [[100.5832 90.5832 88.5832]\n",
2759
" [ 99.5858 89.5858 87.5858]\n",
2760
" [ 98.2895 88.2895 86.5791]\n",
2761
" ...\n",
2762
" [ 97.1905 87.1905 85.1905]\n",
2763
" [100.5632 90.5632 88.5632]\n",
2764
" [103.7336 93.7336 91.7336]]\n",
2765
"\n",
2766
" [[ 99.7448 89.7448 87.7448]\n",
2767
" [ 99.1363 89.1363 87.1363]\n",
2768
" [ 98.0361 88.0361 86.0722]\n",
2769
" ...\n",
2770
" [ 98.2774 88.2774 86.2774]\n",
2771
" [103.0784 93.0784 91.0784]\n",
2772
" [106.2488 96.2488 94.2488]]\n",
2773
"\n",
2774
" ...\n",
2775
"\n",
2776
" [[ 84.0999 74.0999 72.0999]\n",
2777
" [ 82.9079 72.9079 70.9079]\n",
2778
" [ 85.3522 75.3522 73.3522]\n",
2779
" ...\n",
2780
" [ 89.1482 79.1482 77.1482]\n",
2781
" [ 89.8367 79.8367 77.8367]\n",
2782
" [ 90.1445 80.1445 78.1445]]\n",
2783
"\n",
2784
" [[ 82.4136 72.4136 70.4136]\n",
2785
" [ 80.9143 70.9143 68.9143]\n",
2786
" [ 84.2856 74.2856 72.2856]\n",
2787
" ...\n",
2788
" [ 88.958 78.958 76.958 ]\n",
2789
" [ 89.1798 79.1798 77.1798]\n",
2790
" [ 88.2369 78.2369 76.2369]]\n",
2791
"\n",
2792
" [[ 83.4626 73.4626 71.4626]\n",
2793
" [ 83.7586 73.7586 71.7586]\n",
2794
" [ 85.9435 75.9435 73.9435]\n",
2795
" ...\n",
2796
" [ 87.757 77.757 75.757 ]\n",
2797
" [ 87.5026 77.5026 75.5026]\n",
2798
" [ 85.9004 75.9004 73.9004]]]\n",
2799
"\n",
2800
"\n",
2801
" [[[172.6817 157.1644 149.9057]\n",
2802
" [173.8141 158.2967 151.0381]\n",
2803
" [175.1479 159.6305 152.3719]\n",
2804
" ...\n",
2805
" [ 0.0511 82.0511 93.0511]\n",
2806
" [ 1.3411 83.3411 95.1112]\n",
2807
" [ 0.8382 82.8382 94.8382]]\n",
2808
"\n",
2809
" [[170.1306 153.1306 145.1306]\n",
2810
" [171.8036 154.8036 146.8036]\n",
2811
" [172.1854 155.1854 147.1854]\n",
2812
" ...\n",
2813
" [ 0.2871 81.9238 92.9238]\n",
2814
" [ 0.5958 82.3174 94.0875]\n",
2815
" [ 1.6785 83.6192 95.6192]]\n",
2816
"\n",
2817
" [[167.8969 150.5086 142.7027]\n",
2818
" [169.8058 152.4175 144.6117]\n",
2819
" [169.2657 151.8774 144.0716]\n",
2820
" ...\n",
2821
" [ 0.8661 81.5729 92.5729]\n",
2822
" [ 0.0893 81.0982 92.7188]\n",
2823
" [ 1.1892 82.6914 94.4973]]\n",
2824
"\n",
2825
" ...\n",
2826
"\n",
2827
" [[121.9999 102.9999 96.9999]\n",
2828
" [140.8918 121.229 116.2232]\n",
2829
" [153.566 131.9403 129.1488]\n",
2830
" ...\n",
2831
" [142.0739 144.0739 143.0739]\n",
2832
" [138.8696 140.8696 139.8696]\n",
2833
" [133.4807 135.4807 134.4807]]\n",
2834
"\n",
2835
" [[131.6227 112.1389 106.3808]\n",
2836
" [145.2008 124.6485 119.6466]\n",
2837
" [154.6197 132.7224 129.0891]\n",
2838
" ...\n",
2839
" [142.2765 144.2765 143.2765]\n",
2840
" [137.8669 139.8669 138.8669]\n",
2841
" [133.3801 135.3801 134.3801]]\n",
2842
"\n",
2843
" [[139.8237 119.9239 113.4246]\n",
2844
" [150.2441 129.8769 123.6113]\n",
2845
" [156.0569 135.171 129.6134]\n",
2846
" ...\n",
2847
" [139.7307 141.7307 139.4651]\n",
2848
" [138.4892 140.4892 138.2236]\n",
2849
" [136.1518 138.1518 135.8862]]]\n",
2850
"\n",
2851
"\n",
2852
" ...\n",
2853
"\n",
2854
"\n",
2855
" [[[203.3902 196.3902 188.3902]\n",
2856
" [202.4281 195.4281 187.4281]\n",
2857
" [203.9667 196.9667 188.9667]\n",
2858
" ...\n",
2859
" [200.701 195.701 191.701 ]\n",
2860
" [199.2772 194.2772 190.2772]\n",
2861
" [199.3182 194.3182 190.3182]]\n",
2862
"\n",
2863
" [[204.9299 197.9299 189.9299]\n",
2864
" [203.4584 196.4584 188.4584]\n",
2865
" [203.0887 196.0887 188.0887]\n",
2866
" ...\n",
2867
" [200.9726 195.9726 191.9726]\n",
2868
" [200.8419 195.8419 191.8419]\n",
2869
" [201.5515 196.5515 192.5515]]\n",
2870
"\n",
2871
" [[205.0237 198.0237 190.0237]\n",
2872
" [204.0821 197.0821 189.0821]\n",
2873
" [203.7229 196.7229 188.7229]\n",
2874
" ...\n",
2875
" [200.8779 195.8779 191.8779]\n",
2876
" [200.2967 195.2967 191.2967]\n",
2877
" [200.4924 195.4924 191.4924]]\n",
2878
"\n",
2879
" ...\n",
2880
"\n",
2881
" [[207.1546 199.1546 196.1546]\n",
2882
" [206.8088 198.8088 195.8088]\n",
2883
" [206.494 198.494 195.494 ]\n",
2884
" ...\n",
2885
" [200.5247 191.3558 186.8623]\n",
2886
" [200.0171 190.0442 187.9629]\n",
2887
" [199.5921 189.5921 187.5921]]\n",
2888
"\n",
2889
" [[206.0148 198.0148 195.0148]\n",
2890
" [206. 198. 195. ]\n",
2891
" [206.5229 198.5229 195.5229]\n",
2892
" ...\n",
2893
" [199.8563 190.6875 186.1939]\n",
2894
" [199.9953 190.0224 187.9411]\n",
2895
" [201.4198 191.4198 189.4198]]\n",
2896
"\n",
2897
" [[206.0834 198.0834 195.0834]\n",
2898
" [206. 198. 195. ]\n",
2899
" [206.5229 198.5229 195.5229]\n",
2900
" ...\n",
2901
" [199.1879 190.019 185.5255]\n",
2902
" [199.9735 190.0006 187.9193]\n",
2903
" [200.7949 190.7949 188.7949]]]\n",
2904
"\n",
2905
"\n",
2906
" [[[ 90.5269 37.5269 21.5269]\n",
2907
" [ 88.8094 35.8094 19.8094]\n",
2908
" [ 93.9973 40.9973 24.9973]\n",
2909
" ...\n",
2910
" [118.3559 170.4276 157.3917]\n",
2911
" [115.1429 168.0561 154.5995]\n",
2912
" [112.1826 166.1826 152.1826]]\n",
2913
"\n",
2914
" [[ 93.5673 40.0377 24.5673]\n",
2915
" [ 89.6825 36.153 20.6825]\n",
2916
" [ 92.3764 38.8468 23.3764]\n",
2917
" ...\n",
2918
" [117.2742 169.2742 156.4507]\n",
2919
" [113.6343 166.353 153.1702]\n",
2920
" [112.7061 166.353 152.7061]]\n",
2921
"\n",
2922
" [[ 94.2131 38.2131 25.2131]\n",
2923
" [ 92.763 36.763 23.763 ]\n",
2924
" [ 90.8188 35.2222 22.0877]\n",
2925
" ...\n",
2926
" [113.0666 165.0666 153.0666]\n",
2927
" [115.5616 167.5616 155.5616]\n",
2928
" [115.7477 167.7477 155.7477]]\n",
2929
"\n",
2930
" ...\n",
2931
"\n",
2932
" [[126.8632 178.8632 165.8632]\n",
2933
" [128.2961 180.2961 167.2961]\n",
2934
" [129.3007 181.3007 168.3007]\n",
2935
" ...\n",
2936
" [119.8919 165.8919 152.8919]\n",
2937
" [120.2614 166.2614 153.2614]\n",
2938
" [117.6067 163.6068 150.6068]]\n",
2939
"\n",
2940
" [[127.3596 179.3596 166.3596]\n",
2941
" [127.4388 179.4388 166.4388]\n",
2942
" [127.661 179.661 166.661 ]\n",
2943
" ...\n",
2944
" [117.3124 163.3124 150.3124]\n",
2945
" [122.6635 168.6635 155.6635]\n",
2946
" [120.5875 166.5875 153.5875]]\n",
2947
"\n",
2948
" [[125.4024 177.4024 164.4024]\n",
2949
" [127.0162 179.0162 166.0162]\n",
2950
" [127.775 179.775 166.775 ]\n",
2951
" ...\n",
2952
" [119.493 165.493 152.493 ]\n",
2953
" [119.2783 165.2783 152.2783]\n",
2954
" [119.4326 165.4326 152.4326]]]\n",
2955
"\n",
2956
"\n",
2957
" [[[245.5498 249.5498 251.7239]\n",
2958
" [244.1997 248.1997 250.4625]\n",
2959
" [244.0034 248.0034 251.0034]\n",
2960
" ...\n",
2961
" [211.2918 192.2918 178.2918]\n",
2962
" [214.5348 195.5348 181.5348]\n",
2963
" [213.8363 194.8363 180.8363]]\n",
2964
"\n",
2965
" [[243.9593 247.9593 248.9593]\n",
2966
" [242.3858 246.3858 247.6005]\n",
2967
" [245.3056 249.3056 252.3056]\n",
2968
" ...\n",
2969
" [212.3729 193.3729 179.3729]\n",
2970
" [214.5676 195.5676 181.5676]\n",
2971
" [213.8248 194.8248 180.8248]]\n",
2972
"\n",
2973
" [[241.8275 245.8275 246.8275]\n",
2974
" [241.5368 245.5368 246.6281]\n",
2975
" [245.7033 249.7033 251.5532]\n",
2976
" ...\n",
2977
" [213.0938 194.0938 180.0938]\n",
2978
" [213.5933 194.5933 180.5933]\n",
2979
" [212.6366 193.6366 179.6366]]\n",
2980
"\n",
2981
" ...\n",
2982
"\n",
2983
" [[ 94.0651 123.0651 119.0651]\n",
2984
" [ 97.2689 126.2689 122.2689]\n",
2985
" [ 99.561 128.561 124.561 ]\n",
2986
" ...\n",
2987
" [188.1702 188.1702 186.1702]\n",
2988
" [194.9897 194.9897 192.9897]\n",
2989
" [197.8067 197.8067 195.8067]]\n",
2990
"\n",
2991
" [[ 93.1756 122.1806 118.1781]\n",
2992
" [ 92.8621 122.0501 117.9561]\n",
2993
" [ 93.8894 123.0774 118.9834]\n",
2994
" ...\n",
2995
" [191.5663 191.7542 189.6602]\n",
2996
" [198.4874 198.6754 196.5814]\n",
2997
" [199.7756 199.9636 197.8696]]\n",
2998
"\n",
2999
" [[ 94.6932 124.0868 119.89 ]\n",
3000
" [ 89.2506 120.2506 115.2506]\n",
3001
" [ 84.4089 115.4089 110.4089]\n",
3002
" ...\n",
3003
" [197.3543 199.3543 196.3543]\n",
3004
" [204.9348 206.9348 203.9348]\n",
3005
" [206.575 208.575 205.575 ]]]], shape=(8, 640, 640, 3), dtype=float32) {'classes': <tf.RaggedTensor [[7.0], [6.0], [6.0], [6.0], [6.0], [6.0], [6.0], []]>, 'boxes': <tf.RaggedTensor [[[401.13666, 0.0, 640.0, 519.2079]], [[0.0, 0.0, 640.0, 640.0]],\n",
3006
" [[0.0, 0.0, 640.0, 640.0]], [[382.48413, 0.0, 640.0, 640.0]],\n",
3007
" [[0.0, 0.0, 640.0, 640.0]], [[0.0, 0.0, 640.0, 640.0]],\n",
3008
" [[0.0, 0.0, 640.0, 640.0]], []]>}\n",
3009
"tf.Tensor(\n",
3010
"[[[[138.926 134.0144 130.5216]\n",
3011
" [140.7129 136.0292 133.0292]\n",
3012
" [142.9553 138.2716 135.2716]\n",
3013
" ...\n",
3014
" [159.4476 151.4476 148.4476]\n",
3015
" [158.882 150.882 147.882 ]\n",
3016
" [159.5815 151.5815 148.5815]]\n",
3017
"\n",
3018
" [[139.2594 134.2594 130.5387]\n",
3019
" [140.0506 135.0506 132.0506]\n",
3020
" [140.8417 135.8417 132.8417]\n",
3021
" ...\n",
3022
" [161.0713 153.0713 150.0713]\n",
3023
" [160.6603 152.6603 149.6603]\n",
3024
" [161.4423 153.4423 150.4423]]\n",
3025
"\n",
3026
" [[139.1082 132.9459 129.5044]\n",
3027
" [139.1332 133.1234 130.0726]\n",
3028
" [137.4831 132.4633 129.0825]\n",
3029
" ...\n",
3030
" [160.1282 152.1282 149.1282]\n",
3031
" [160.4846 152.4846 149.4846]\n",
3032
" [160.7519 152.7519 149.7519]]\n",
3033
"\n",
3034
" ...\n",
3035
"\n",
3036
" [[116.4706 115.7499 113.7499]\n",
3037
" [114.7795 114.7795 112.7795]\n",
3038
" [113.3483 113.3483 111.3483]\n",
3039
" ...\n",
3040
" [ 73.6497 64.6497 59.6497]\n",
3041
" [ 73.4348 64.4348 59.4348]\n",
3042
" [ 73.7815 64.7815 59.7815]]\n",
3043
"\n",
3044
" [[113.9695 113.2488 111.2488]\n",
3045
" [113.8383 113.8383 111.8383]\n",
3046
" [112.9865 112.9865 110.9865]\n",
3047
" ...\n",
3048
" [ 72.5982 63.5982 58.5982]\n",
3049
" [ 72.2446 63.2446 58.2446]\n",
3050
" [ 72.0654 63.0654 58.0654]]\n",
3051
"\n",
3052
" [[108.9934 108.2727 106.2727]\n",
3053
" [108.839 108.839 106.839 ]\n",
3054
" [107.9471 107.9471 105.9471]\n",
3055
" ...\n",
3056
" [ 70.2554 61.2554 56.2554]\n",
3057
" [ 72.302 63.302 58.302 ]\n",
3058
" [ 72.3809 63.3809 58.3809]]]\n",
3059
"\n",
3060
"\n",
3061
" [[[153.4065 144.4065 135.4065]\n",
3062
" [150.8992 143.21 134.8654]\n",
3063
" [145.7408 138.7408 130.7408]\n",
3064
" ...\n",
3065
" [125.8395 118.8395 111.2163]\n",
3066
" [130.6458 123.6458 117.1082]\n",
3067
" [133.5136 126.5136 119.7389]]\n",
3068
"\n",
3069
" [[153.3822 144.3822 135.3822]\n",
3070
" [151.1575 143.4683 135.1237]\n",
3071
" [145.5895 138.5895 130.5895]\n",
3072
" ...\n",
3073
" [126.1894 119.1894 111.1894]\n",
3074
" [132.2584 125.2584 117.2584]\n",
3075
" [134.3185 127.3185 119.3185]]\n",
3076
"\n",
3077
" [[152.7581 143.7581 135.1045]\n",
3078
" [150.1396 142.2234 134.1117]\n",
3079
" [147.9139 140.5675 132.7407]\n",
3080
" ...\n",
3081
" [129.3023 121.9559 113.7827]\n",
3082
" [130.165 122.8185 114.6453]\n",
3083
" [129.922 122.6317 114.4304]]\n",
3084
"\n",
3085
" ...\n",
3086
"\n",
3087
" [[107.732 101.732 101.732 ]\n",
3088
" [107.046 101.5856 99.9669]\n",
3089
" [109.8613 104.6845 102.2148]\n",
3090
" ...\n",
3091
" [169.899 158.5455 152.192 ]\n",
3092
" [175.0903 163.7368 157.3833]\n",
3093
" [178.3109 166.6904 160.1273]]\n",
3094
"\n",
3095
" [[107.4547 101.4547 101.4547]\n",
3096
" [108.0938 102.7492 100.783 ]\n",
3097
" [108.762 103.762 100.762 ]\n",
3098
" ...\n",
3099
" [171.8577 160.8577 154.8577]\n",
3100
" [172.8004 161.8004 155.8004]\n",
3101
" [174.2123 162.8881 156.5639]]\n",
3102
"\n",
3103
" [[104.011 98.011 98.011 ]\n",
3104
" [104.8992 99.5546 97.5884]\n",
3105
" [105.9243 100.9243 97.9243]\n",
3106
" ...\n",
3107
" [172.5325 161.5325 155.5325]\n",
3108
" [169.2997 158.2997 152.2997]\n",
3109
" [170.4878 159.1636 152.8394]]]\n",
3110
"\n",
3111
"\n",
3112
" [[[180.9777 179.9777 184.9777]\n",
3113
" [180.1358 179.1358 184.1358]\n",
3114
" [177.7484 176.7484 181.7484]\n",
3115
" ...\n",
3116
" [187.8711 186.807 182.9815]\n",
3117
" [185.1501 184.086 182.0108]\n",
3118
" [180.7583 179.6942 177.7156]]\n",
3119
"\n",
3120
" [[180.0459 179.0459 184.0459]\n",
3121
" [178.7189 177.7189 182.7189]\n",
3122
" [177.1308 176.1308 181.1308]\n",
3123
" ...\n",
3124
" [189.5584 185.8121 184.568 ]\n",
3125
" [185.2382 181.4919 180.399 ]\n",
3126
" [180.0031 176.2568 175.1722]]\n",
3127
"\n",
3128
" [[178.7264 177.7264 182.7264]\n",
3129
" [177.3018 176.3018 181.3018]\n",
3130
" [175.7622 174.7622 179.7622]\n",
3131
" ...\n",
3132
" [188.8172 184.8172 183.8172]\n",
3133
" [182.8978 178.8978 177.8978]\n",
3134
" [176.8192 172.8192 171.8192]]\n",
3135
"\n",
3136
" ...\n",
3137
"\n",
3138
" [[193.4176 183.9743 184.9743]\n",
3139
" [192.3279 182.8846 183.5166]\n",
3140
" [191.0567 181.7856 181.2456]\n",
3141
" ...\n",
3142
" [163.5681 161.4739 164.5053]\n",
3143
" [167.3483 163.7604 167.2897]\n",
3144
" [169.0544 166.7951 169.8815]]\n",
3145
"\n",
3146
" [[173.9058 166.2584 167.7093]\n",
3147
" [172.0413 164.3939 165.4704]\n",
3148
" [169.9928 162.5151 162.5549]\n",
3149
" ...\n",
3150
" [160.8586 157.8131 159.9678]\n",
3151
" [164.2083 158.8832 161.9321]\n",
3152
" [166.6782 163.3807 165.6342]]\n",
3153
"\n",
3154
" [[151.0875 145.7774 147.4325]\n",
3155
" [149.2731 143.963 145.0742]\n",
3156
" [147.5514 142.2413 142.373 ]\n",
3157
" ...\n",
3158
" [155.9711 151.2073 152.5892]\n",
3159
" [157.1739 151.2385 153.2062]\n",
3160
" [162.0172 157.1238 158.5705]]]\n",
3161
"\n",
3162
"\n",
3163
" ...\n",
3164
"\n",
3165
"\n",
3166
" [[[120.5783 106.5783 97.5783]\n",
3167
" [118.8588 104.8588 95.8588]\n",
3168
" [120.5227 106.5227 97.5227]\n",
3169
" ...\n",
3170
" [147.0149 134.0149 125.0149]\n",
3171
" [149.7584 136.7584 127.7584]\n",
3172
" [151.8039 138.8039 129.8039]]\n",
3173
"\n",
3174
" [[119.0161 105.0161 96.0161]\n",
3175
" [118.9986 104.9986 95.9986]\n",
3176
" [119.5547 105.5547 96.5547]\n",
3177
" ...\n",
3178
" [146.2846 133.2846 124.2846]\n",
3179
" [150.3772 137.3772 128.3772]\n",
3180
" [153.7717 140.7717 131.7717]]\n",
3181
"\n",
3182
" [[121.12 107.12 98.12 ]\n",
3183
" [119.0865 105.0865 96.0865]\n",
3184
" [117.8466 103.8466 94.8466]\n",
3185
" ...\n",
3186
" [146.8646 133.8646 124.8646]\n",
3187
" [147.6336 134.6336 125.6336]\n",
3188
" [149.4064 136.4064 127.4064]]\n",
3189
"\n",
3190
" ...\n",
3191
"\n",
3192
" [[162.1278 157.1278 163.8044]\n",
3193
" [160.7738 155.7738 162.4504]\n",
3194
" [162.4559 157.4559 164.1325]\n",
3195
" ...\n",
3196
" [123.8684 114.8684 109.8684]\n",
3197
" [127.1536 118.1536 113.1536]\n",
3198
" [126.9696 117.9696 112.9696]]\n",
3199
"\n",
3200
" [[159.5051 154.5051 160.5051]\n",
3201
" [162.0101 157.0101 163.0101]\n",
3202
" [166.1893 161.1893 167.1893]\n",
3203
" ...\n",
3204
" [125.2297 116.2297 111.2297]\n",
3205
" [128.6337 119.6337 114.6337]\n",
3206
" [126.8487 117.8487 112.8487]]\n",
3207
"\n",
3208
" [[156.1396 151.1396 157.1396]\n",
3209
" [161.1014 156.1014 162.1014]\n",
3210
" [165.7419 160.7419 166.7419]\n",
3211
" ...\n",
3212
" [125.2752 116.2752 111.2752]\n",
3213
" [129.3537 120.3537 115.3537]\n",
3214
" [126.5235 117.5235 112.5235]]]\n",
3215
"\n",
3216
"\n",
3217
" [[[ 62.059 45.059 38.059 ]\n",
3218
" [ 62.6443 45.6443 38.6443]\n",
3219
" [ 62.2111 45.2111 38.2111]\n",
3220
" ...\n",
3221
" [ 82.7981 67.7981 64.7981]\n",
3222
" [ 81.9208 66.9208 63.9208]\n",
3223
" [ 80.5304 65.5304 62.5304]]\n",
3224
"\n",
3225
" [[ 63. 46. 39. ]\n",
3226
" [ 62.8353 45.8353 38.8353]\n",
3227
" [ 61.7876 44.7876 37.7876]\n",
3228
" ...\n",
3229
" [ 83.4861 68.4861 65.4861]\n",
3230
" [ 83.049 68.049 65.049 ]\n",
3231
" [ 81.5486 66.5486 63.5486]]\n",
3232
"\n",
3233
" [[ 62.0419 45.0419 38.0419]\n",
3234
" [ 62.3489 45.3489 38.3489]\n",
3235
" [ 61.3803 44.3803 37.3803]\n",
3236
" ...\n",
3237
" [ 83.3774 68.3774 65.3774]\n",
3238
" [ 82.6439 67.6439 64.6439]\n",
3239
" [ 82.0453 67.0453 64.0453]]\n",
3240
"\n",
3241
" ...\n",
3242
"\n",
3243
" [[ 59.599 43.599 30.599 ]\n",
3244
" [ 60.854 44.854 31.854 ]\n",
3245
" [ 61.6771 44.8882 32.2827]\n",
3246
" ...\n",
3247
" [ 62.7275 53.7275 46.7275]\n",
3248
" [ 59.2792 50.2792 43.2792]\n",
3249
" [ 55.3129 46.3129 39.3129]]\n",
3250
"\n",
3251
" [[ 61.666 45.666 32.666 ]\n",
3252
" [ 62.53 46.53 33.53 ]\n",
3253
" [ 61.9894 45.2004 32.5949]\n",
3254
" ...\n",
3255
" [ 62.6473 53.6473 46.6473]\n",
3256
" [ 61.9467 52.9467 45.9467]\n",
3257
" [ 59.0406 50.0406 43.0406]]\n",
3258
"\n",
3259
" [[ 61.7667 45.7667 32.7667]\n",
3260
" [ 61.8681 45.8681 32.8681]\n",
3261
" [ 59.336 42.5471 29.9415]\n",
3262
" ...\n",
3263
" [ 60.8142 51.8142 44.8142]\n",
3264
" [ 61.0486 52.0486 45.0486]\n",
3265
" [ 60.9211 51.9211 44.9211]]]\n",
3266
"\n",
3267
"\n",
3268
" [[[169.8636 156.8667 150.8667]\n",
3269
" [172.2332 159.5395 153.5395]\n",
3270
" [172.356 159.678 153.678 ]\n",
3271
" ...\n",
3272
" [145.1885 144.1885 140.1885]\n",
3273
" [143.1166 142.1166 138.1166]\n",
3274
" [142.6685 141.6685 137.6685]]\n",
3275
"\n",
3276
" [[168.8956 155.9151 149.9151]\n",
3277
" [168.7027 157.6052 151.6052]\n",
3278
" [168.7842 157.7842 151.7842]\n",
3279
" ...\n",
3280
" [144.6195 143.6195 139.6195]\n",
3281
" [143.6387 142.6387 138.6387]\n",
3282
" [142.938 141.938 137.938 ]]\n",
3283
"\n",
3284
" [[167.893 154.9996 148.9996]\n",
3285
" [166.0515 154.9582 148.9582]\n",
3286
" [166.888 155.888 149.888 ]\n",
3287
" ...\n",
3288
" [143.7781 142.6463 138.6902]\n",
3289
" [143.3514 142.307 138.3218]\n",
3290
" [142.3951 141.3951 137.3951]]\n",
3291
"\n",
3292
" ...\n",
3293
"\n",
3294
" [[137.8659 122.8659 115.8659]\n",
3295
" [137.1632 122.1632 115.1632]\n",
3296
" [137.0136 122.0136 115.0136]\n",
3297
" ...\n",
3298
" [204.3025 206.3025 205.3025]\n",
3299
" [202.5037 204.5037 203.5037]\n",
3300
" [205.2722 207.2722 206.2722]]\n",
3301
"\n",
3302
" [[137.1677 122.1677 115.1677]\n",
3303
" [135.4593 120.4593 113.4593]\n",
3304
" [135.3708 120.3708 113.3708]\n",
3305
" ...\n",
3306
" [207.723 209.723 208.723 ]\n",
3307
" [206.7461 208.7461 207.7461]\n",
3308
" [207.2385 209.2385 208.2385]]\n",
3309
"\n",
3310
" [[136.9879 121.9879 114.9879]\n",
3311
" [135.8168 120.8168 113.8168]\n",
3312
" [135.0811 120.0812 113.0812]\n",
3313
" ...\n",
3314
" [208.1082 210.1082 209.1082]\n",
3315
" [207.9203 209.9203 208.9203]\n",
3316
" [208.8183 210.8183 209.8183]]]], shape=(8, 640, 640, 3), dtype=float32) {'classes': <tf.RaggedTensor [[7.0], [6.0], [], [7.0], [6.0], [7.0], [7.0], [7.0]]>, 'boxes': <tf.RaggedTensor [[[0.0, 0.0, 640.0, 640.0]], [[0.0, 0.0, 640.0, 640.0]], [],\n",
3317
" [[0.0, 0.0, 640.0, 640.0]], [[0.0, 0.0, 640.0, 640.0]],\n",
3318
" [[0.0, 0.0, 640.0, 640.0]], [[0.0, 393.40704, 640.0, 640.0]],\n",
3319
" [[0.0, 0.0, 640.0, 640.0]]]>}\n",
3320
"tf.Tensor(\n",
3321
"[[[[152.521 150.521 153.0544]\n",
3322
" [150.2944 148.2944 151.2944]\n",
3323
" [150.4801 148.4801 151.4801]\n",
3324
" ...\n",
3325
" [140.2334 126.2334 117.2334]\n",
3326
" [141.14 127.14 118.14 ]\n",
3327
" [141.1855 127.1855 118.1855]]\n",
3328
"\n",
3329
" [[151.2275 149.2275 151.761 ]\n",
3330
" [147.2776 145.2776 148.2776]\n",
3331
" [149.067 147.067 150.067 ]\n",
3332
" ...\n",
3333
" [140.8722 126.8722 117.8722]\n",
3334
" [140.4999 126.4999 117.4999]\n",
3335
" [138.9666 124.9666 115.9666]]\n",
3336
"\n",
3337
" [[147.7529 145.7529 148.2864]\n",
3338
" [145.3166 143.3166 146.3166]\n",
3339
" [146.1801 144.1801 147.1801]\n",
3340
" ...\n",
3341
" [141. 127. 118. ]\n",
3342
" [140.94 126.94 117.94 ]\n",
3343
" [140.7634 126.4333 118.0934]]\n",
3344
"\n",
3345
" ...\n",
3346
"\n",
3347
" [[152.8213 150.8213 151.8213]\n",
3348
" [152.4 150.4 151.4 ]\n",
3349
" [153.1335 151.1335 152.1335]\n",
3350
" ...\n",
3351
" [143. 135.1789 131.6422]\n",
3352
" [146.2435 139.0101 133.7103]\n",
3353
" [151.4191 144.2713 138.7147]]\n",
3354
"\n",
3355
" [[154.2968 152.2968 153.2968]\n",
3356
" [154.0168 152.0168 153.0168]\n",
3357
" [154.2601 152.2601 153.2601]\n",
3358
" ...\n",
3359
" [140.6367 132.6367 129.6367]\n",
3360
" [144.9803 136.9803 133.9803]\n",
3361
" [152.5768 144.9435 140.8434]]\n",
3362
"\n",
3363
" [[155.2523 153.3378 154.0812]\n",
3364
" [155.9389 153.9389 154.9389]\n",
3365
" [155.4299 153.4299 154.4299]\n",
3366
" ...\n",
3367
" [140.3625 132.3625 129.3625]\n",
3368
" [144.4404 136.4404 133.4404]\n",
3369
" [151.5989 143.8312 140.1345]]]\n",
3370
"\n",
3371
"\n",
3372
" [[[196.0218 195.0218 200.0218]\n",
3373
" [199.4815 198.4815 203.4815]\n",
3374
" [196.7551 195.7551 200.7551]\n",
3375
" ...\n",
3376
" [130.1971 135.1971 54.8599]\n",
3377
" [130.891 135.891 53.979 ]\n",
3378
" [130.868 135.868 53.8874]]\n",
3379
"\n",
3380
" [[197.0688 196.5833 201.5833]\n",
3381
" [196.3451 195.8596 200.8596]\n",
3382
" [193.6878 193.2023 198.2023]\n",
3383
" ...\n",
3384
" [130.1944 135.1944 54.8416]\n",
3385
" [130.5407 135.5407 53.5407]\n",
3386
" [130.499 135.499 53.499 ]]\n",
3387
"\n",
3388
" [[196.0008 197.0008 202.0008]\n",
3389
" [194.4545 195.4545 200.4545]\n",
3390
" [191.9326 192.9326 197.9326]\n",
3391
" ...\n",
3392
" [127.3142 132.3143 51.9615]\n",
3393
" [128.9098 133.9098 51.9098]\n",
3394
" [129.9223 134.9223 52.9223]]\n",
3395
"\n",
3396
" ...\n",
3397
"\n",
3398
" [[193.1799 191.1799 196.1799]\n",
3399
" [195.3827 192.8372 198.9283]\n",
3400
" [197.5817 194.5817 201.5817]\n",
3401
" ...\n",
3402
" [199.1764 196.1764 203.1764]\n",
3403
" [199.1516 196.1516 203.1516]\n",
3404
" [201.078 198.078 205.078 ]]\n",
3405
"\n",
3406
" [[195.7663 193.7663 198.7663]\n",
3407
" [196.9244 194.3789 200.47 ]\n",
3408
" [198.9121 195.9121 202.9121]\n",
3409
" ...\n",
3410
" [198.3251 195.3251 202.3251]\n",
3411
" [197.7576 194.7576 201.7576]\n",
3412
" [201.3881 198.3881 205.3881]]\n",
3413
"\n",
3414
" [[198.9814 196.4907 202.4722]\n",
3415
" [199.2593 196.4907 203.0278]\n",
3416
" [200.7531 197.7531 204.7531]\n",
3417
" ...\n",
3418
" [201.943 198.943 205.943 ]\n",
3419
" [200.1931 197.1931 204.1931]\n",
3420
" [199.0558 196.0558 203.0558]]]\n",
3421
"\n",
3422
"\n",
3423
" [[[170.784 171.1507 175.4674]\n",
3424
" [168.3235 168.1038 172.7136]\n",
3425
" [161.5363 160.5363 165.5363]\n",
3426
" ...\n",
3427
" [120.2339 108.2339 108.8672]\n",
3428
" [120.8088 108.8088 109.4421]\n",
3429
" [121.1563 109.1563 109.7896]]\n",
3430
"\n",
3431
" [[168.8875 169.8875 173.8875]\n",
3432
" [167.1901 167.3319 171.761 ]\n",
3433
" [162.5438 161.5438 166.5438]\n",
3434
" ...\n",
3435
" [119.0701 107.0701 107.0701]\n",
3436
" [119.5026 107.5026 107.5026]\n",
3437
" [120.3361 108.3361 108.3361]]\n",
3438
"\n",
3439
" [[168.2594 169.2594 173.2594]\n",
3440
" [166.5052 167.1934 171.3493]\n",
3441
" [163.0397 163.3129 167.6763]\n",
3442
" ...\n",
3443
" [116.9248 104.9248 104.9248]\n",
3444
" [118.0861 106.0861 106.0861]\n",
3445
" [119.0449 107.0449 107.0449]]\n",
3446
"\n",
3447
" ...\n",
3448
"\n",
3449
" [[139.1604 131.1604 128.1604]\n",
3450
" [139.8008 131.8008 128.8008]\n",
3451
" [138.3153 130.3153 127.3153]\n",
3452
" ...\n",
3453
" [121.4739 107.3451 99.2754]\n",
3454
" [117.178 103.8068 95.031 ]\n",
3455
" [115.3351 102.3351 93.5593]]\n",
3456
"\n",
3457
" [[137.1549 129.1549 126.1549]\n",
3458
" [137.0658 129.0658 126.0658]\n",
3459
" [136.9891 128.9891 125.9891]\n",
3460
" ...\n",
3461
" [118.9462 104.8335 96.0589]\n",
3462
" [116.6726 103.1941 94.1941]\n",
3463
" [114.6253 101.6253 92.6253]]\n",
3464
"\n",
3465
" [[136.9465 128.9465 125.9465]\n",
3466
" [135.8036 127.8036 124.8036]\n",
3467
" [135.4322 127.4322 124.4322]\n",
3468
" ...\n",
3469
" [116.2105 102.2105 93.2105]\n",
3470
" [116.1181 102.2595 93.2595]\n",
3471
" [115.2308 101.502 92.502 ]]]\n",
3472
"\n",
3473
"\n",
3474
" ...\n",
3475
"\n",
3476
"\n",
3477
" [[[153.9834 144.9834 139.9834]\n",
3478
" [158.503 149.503 144.503 ]\n",
3479
" [158.4995 149.4995 144.4995]\n",
3480
" ...\n",
3481
" [139.4414 128.4414 122.4414]\n",
3482
" [141.4766 130.4766 124.4766]\n",
3483
" [144.4169 133.4169 127.4169]]\n",
3484
"\n",
3485
" [[155.0658 146.0658 141.0658]\n",
3486
" [154.9462 145.9462 140.9462]\n",
3487
" [155.4209 146.4209 141.4209]\n",
3488
" ...\n",
3489
" [139.4356 128.4356 122.4356]\n",
3490
" [140.6563 129.6563 123.6563]\n",
3491
" [143.339 132.339 126.339 ]]\n",
3492
"\n",
3493
" [[155.9104 146.9104 141.9104]\n",
3494
" [154.9748 145.9748 140.9748]\n",
3495
" [155.1081 146.1081 141.1081]\n",
3496
" ...\n",
3497
" [144.0112 133.0112 127.0112]\n",
3498
" [140.8805 129.8805 123.8805]\n",
3499
" [142.8301 131.8301 125.8301]]\n",
3500
"\n",
3501
" ...\n",
3502
"\n",
3503
" [[175.4433 173.4433 174.4433]\n",
3504
" [172.3344 170.6717 170.6599]\n",
3505
" [171.0095 170.0095 168.0095]\n",
3506
" ...\n",
3507
" [138.3438 124.3438 123.3438]\n",
3508
" [137.9648 123.9648 122.9648]\n",
3509
" [139.044 125.044 124.044 ]]\n",
3510
"\n",
3511
" [[174.0924 172.0924 173.0924]\n",
3512
" [177.4865 175.4976 176.4642]\n",
3513
" [174.8846 172.9176 173.8187]\n",
3514
" ...\n",
3515
" [140.7223 126.7223 125.7223]\n",
3516
" [137.3554 123.3554 122.3554]\n",
3517
" [135.8819 121.8819 120.8819]]\n",
3518
"\n",
3519
" [[173.9117 171.9117 172.9117]\n",
3520
" [177.2495 175.2495 176.2495]\n",
3521
" [174.8019 172.8019 173.8019]\n",
3522
" ...\n",
3523
" [138.1417 124.1417 123.1417]\n",
3524
" [134.1821 120.1821 119.1821]\n",
3525
" [136.709 122.709 121.709 ]]]\n",
3526
"\n",
3527
"\n",
3528
" [[[159.3929 156.3929 184.6371]\n",
3529
" [156.7507 153.7507 180.7507]\n",
3530
" [157.3699 154.3699 181.3699]\n",
3531
" ...\n",
3532
" [220.0677 230.0677 254.9128]\n",
3533
" [220.194 230.194 254.9032]\n",
3534
" [220.5106 231.3511 253.7525]]\n",
3535
"\n",
3536
" [[157.625 154.625 181.6276]\n",
3537
" [156.381 153.381 180.381 ]\n",
3538
" [156.8576 153.8576 180.8576]\n",
3539
" ...\n",
3540
" [220.9979 230.9979 255. ]\n",
3541
" [220.9979 230.9979 255. ]\n",
3542
" [220.9997 231.8401 254.1595]]\n",
3543
"\n",
3544
" [[157.474 154.474 181.474 ]\n",
3545
" [157. 154. 181. ]\n",
3546
" [157.6539 154.6539 181.6539]\n",
3547
" ...\n",
3548
" [221. 231. 255. ]\n",
3549
" [221. 231. 255. ]\n",
3550
" [221. 231.8405 254.1595]]\n",
3551
"\n",
3552
" ...\n",
3553
"\n",
3554
" [[170.7204 158.5868 128.9646]\n",
3555
" [170.7174 156.7174 127.7174]\n",
3556
" [170.1418 156.1418 127.1418]\n",
3557
" ...\n",
3558
" [160.0551 153.0551 125.0551]\n",
3559
" [163.3568 156.3568 128.3568]\n",
3560
" [160.8982 153.8982 125.0577]]\n",
3561
"\n",
3562
" [[169.4025 157.2689 127.6467]\n",
3563
" [171.2239 157.2239 128.2239]\n",
3564
" [172.8045 158.8045 129.8045]\n",
3565
" ...\n",
3566
" [162.9549 155.9549 127.9549]\n",
3567
" [162.4155 155.4155 127.4155]\n",
3568
" [157.8539 150.8539 122.0134]]\n",
3569
"\n",
3570
" [[169.9137 157.5891 127.4428]\n",
3571
" [172.2024 158.4228 128.7615]\n",
3572
" [172.598 158.8184 129.1571]\n",
3573
" ...\n",
3574
" [161.0178 154.0178 125.7973]\n",
3575
" [160.7082 153.7082 125.4878]\n",
3576
" [157.4145 150.4145 121.5389]]]\n",
3577
"\n",
3578
"\n",
3579
" [[[ 91.5793 75.5793 42.5793]\n",
3580
" [ 89.5304 73.5304 40.5304]\n",
3581
" [ 90.2171 74.2171 41.183 ]\n",
3582
" ...\n",
3583
" [ 87.4746 71.4746 46.4746]\n",
3584
" [ 88.5856 72.5856 47.5856]\n",
3585
" [ 88.6905 72.6905 47.7233]]\n",
3586
"\n",
3587
" [[ 91.5605 75.5605 42.5605]\n",
3588
" [ 90.3547 74.3547 41.3546]\n",
3589
" [ 91.8067 75.8067 42.7726]\n",
3590
" ...\n",
3591
" [ 87.7167 71.7167 46.7167]\n",
3592
" [ 89.0782 73.0782 48.0782]\n",
3593
" [ 88.1775 72.1775 47.2102]]\n",
3594
"\n",
3595
" [[ 89.4964 73.4964 40.4964]\n",
3596
" [ 91.0875 75.0875 42.0875]\n",
3597
" [ 94.1602 78.1602 45.1261]\n",
3598
" ...\n",
3599
" [ 87.3253 71.3253 46.909 ]\n",
3600
" [ 88.2937 72.2937 47.2937]\n",
3601
" [ 90.619 74.619 49.6517]]\n",
3602
"\n",
3603
" ...\n",
3604
"\n",
3605
" [[158.0933 161.0933 170.0933]\n",
3606
" [159.7669 162.7669 171.7669]\n",
3607
" [159.1223 162.0882 171.1904]\n",
3608
" ...\n",
3609
" [135.3326 132.3326 151.3326]\n",
3610
" [134.8688 131.8688 150.8688]\n",
3611
" [134.8851 131.8851 150.8851]]\n",
3612
"\n",
3613
" [[158.2057 160.8342 170.9486]\n",
3614
" [159.6644 162.293 172.4073]\n",
3615
" [159.5731 162.1802 172.3588]\n",
3616
" ...\n",
3617
" [134.663 131.663 149.9201]\n",
3618
" [134.3715 131.3715 149.6285]\n",
3619
" [134.0103 131.0103 149.2674]]\n",
3620
"\n",
3621
" [[158.958 160.958 172.958 ]\n",
3622
" [160.5315 162.5315 174.5315]\n",
3623
" [158.9451 160.9451 172.9451]\n",
3624
" ...\n",
3625
" [135.9395 132.9395 149.9395]\n",
3626
" [135.7485 132.7485 149.7485]\n",
3627
" [134.6016 131.6016 148.6016]]]], shape=(8, 640, 640, 3), dtype=float32) {'classes': <tf.RaggedTensor [[7.0],\n",
3628
" [6.0],\n",
3629
" [7.0],\n",
3630
" [7.0],\n",
3631
" [7.0],\n",
3632
" [7.0],\n",
3633
" [7.0],\n",
3634
" [7.0]]>, 'boxes': <tf.RaggedTensor [[[0.0, 0.0, 640.0, 640.0]],\n",
3635
"\n",
3636
" [[0.0, 0.0, 640.0, 640.0]],\n",
3637
"\n",
3638
" [[0.0, 0.0, 640.0, 640.0]],\n",
3639
"\n",
3640
" [[0.0, 0.0, 640.0, 640.0]],\n",
3641
"\n",
3642
" [[0.0, 0.0, 640.0, 640.0]],\n",
3643
"\n",
3644
" [[0.0, 0.0, 640.0, 640.0]],\n",
3645
"\n",
3646
" [[0.0, 0.0, 640.0, 640.0]],\n",
3647
"\n",
3648
" [[0.0, 0.0, 640.0, 640.0]]]>}\n",
3649
"tf.Tensor(\n",
3650
"[[[[ 67.9509 63.9509 60.9509]\n",
3651
" [ 68.1779 64.1779 61.1779]\n",
3652
" [ 66.822 62.822 59.822 ]\n",
3653
" ...\n",
3654
" [ 81.729 72.729 65.729 ]\n",
3655
" [ 82.2438 73.2438 66.2438]\n",
3656
" [ 81.3225 72.3225 65.3225]]\n",
3657
"\n",
3658
" [[ 66.0086 62.0086 59.0086]\n",
3659
" [ 65.8236 61.8236 58.8236]\n",
3660
" [ 64.2069 60.2069 57.2069]\n",
3661
" ...\n",
3662
" [ 81.3022 72.3022 65.5156]\n",
3663
" [ 82.7801 73.7801 67.0728]\n",
3664
" [ 84.0877 75.0877 68.3804]]\n",
3665
"\n",
3666
" [[ 64.8579 60.8579 57.8579]\n",
3667
" [ 65.0754 61.0754 58.0754]\n",
3668
" [ 64.6613 60.6613 57.6613]\n",
3669
" ...\n",
3670
" [ 79.0408 70.0408 64.3849]\n",
3671
" [ 78.8957 69.8957 64.7395]\n",
3672
" [ 80.7376 71.7376 66.5814]]\n",
3673
"\n",
3674
" ...\n",
3675
"\n",
3676
" [[ 34.1653 33.1653 31.1653]\n",
3677
" [ 30.5266 29.5266 27.5266]\n",
3678
" [ 26.6671 25.6671 23.6671]\n",
3679
" ...\n",
3680
" [ 79.7524 66.7524 58.7524]\n",
3681
" [ 79.0671 66.0671 58.0671]\n",
3682
" [ 81.0456 68.0456 60.0456]]\n",
3683
"\n",
3684
" [[ 31.6731 30.6731 28.6731]\n",
3685
" [ 30.0677 29.0677 27.0677]\n",
3686
" [ 27.4658 26.4658 24.4658]\n",
3687
" ...\n",
3688
" [ 77.1113 64.1113 56.1113]\n",
3689
" [ 77.0376 64.0376 56.0376]\n",
3690
" [ 78.6721 65.6721 57.6721]]\n",
3691
"\n",
3692
" [[ 31.273 30.273 28.273 ]\n",
3693
" [ 30.8703 29.8703 27.8703]\n",
3694
" [ 29.4709 28.4709 26.4709]\n",
3695
" ...\n",
3696
" [ 80.423 67.423 59.423 ]\n",
3697
" [ 80.1392 67.1392 59.1392]\n",
3698
" [ 80.2537 67.2537 59.2537]]]\n",
3699
"\n",
3700
"\n",
3701
" [[[140.057 132.057 130.057 ]\n",
3702
" [138.2572 130.2572 128.2572]\n",
3703
" [137.168 129.168 127.168 ]\n",
3704
" ...\n",
3705
" [111.7783 97.7783 94.7783]\n",
3706
" [111.2057 97.2057 94.2057]\n",
3707
" [111.2057 97.2057 94.2057]]\n",
3708
"\n",
3709
" [[138.5145 130.5145 128.5145]\n",
3710
" [138.0894 130.0894 128.0894]\n",
3711
" [137.8049 129.8049 127.8049]\n",
3712
" ...\n",
3713
" [111.2506 97.2506 94.2506]\n",
3714
" [110.9105 96.9105 93.9105]\n",
3715
" [110.3508 96.3508 93.3508]]\n",
3716
"\n",
3717
" [[136.7024 128.7024 126.7024]\n",
3718
" [137.5723 129.5723 127.5723]\n",
3719
" [138.2239 130.2239 128.2239]\n",
3720
" ...\n",
3721
" [111.4274 97.4274 94.4274]\n",
3722
" [112.3936 98.3936 95.3936]\n",
3723
" [111.5355 97.5355 94.5355]]\n",
3724
"\n",
3725
" ...\n",
3726
"\n",
3727
" [[ 82.3132 67.3132 60.3132]\n",
3728
" [ 82.2688 67.2688 60.2688]\n",
3729
" [ 81.8309 66.8309 59.8309]\n",
3730
" ...\n",
3731
" [114.2367 97.2367 90.2367]\n",
3732
" [116.2056 99.2056 92.2056]\n",
3733
" [119.0361 102.0361 95.0361]]\n",
3734
"\n",
3735
" [[ 82.1222 67.1222 60.1222]\n",
3736
" [ 80.464 65.464 58.464 ]\n",
3737
" [ 80.0647 65.0647 58.0647]\n",
3738
" ...\n",
3739
" [115.0002 98.0002 91.0002]\n",
3740
" [119.8144 102.8144 95.8144]\n",
3741
" [120.9935 103.9935 96.9935]]\n",
3742
"\n",
3743
" [[ 84.1809 69.0479 62.0479]\n",
3744
" [ 82.7051 67.572 60.572 ]\n",
3745
" [ 82.3642 67.2311 60.2311]\n",
3746
" ...\n",
3747
" [116.2256 99.2256 92.2256]\n",
3748
" [121.6815 104.6815 97.6815]\n",
3749
" [120.9376 103.9376 96.9376]]]\n",
3750
"\n",
3751
"\n",
3752
" [[[ 61.0762 131.0762 182.0762]\n",
3753
" [ 60.7592 130.7592 181.7592]\n",
3754
" [ 60.5381 130.5381 181.5381]\n",
3755
" ...\n",
3756
" [146.4335 120.4335 95.4335]\n",
3757
" [146.1534 120.1534 95.1534]\n",
3758
" [146.66 120.66 95.66 ]]\n",
3759
"\n",
3760
" [[ 59.4463 129.4463 180.4463]\n",
3761
" [ 59.7725 129.7725 180.7725]\n",
3762
" [ 60. 130. 181. ]\n",
3763
" ...\n",
3764
" [147.4922 121.4922 96.4922]\n",
3765
" [146.4523 120.4523 95.4523]\n",
3766
" [145.0206 119.0206 94.0206]]\n",
3767
"\n",
3768
" [[ 60.2915 130.2915 181.2915]\n",
3769
" [ 61.261 131.261 182.261 ]\n",
3770
" [ 61.4975 131.4975 182.4975]\n",
3771
" ...\n",
3772
" [147.859 121.859 96.859 ]\n",
3773
" [145.4016 119.4016 94.4016]\n",
3774
" [142.8855 116.8855 91.8855]]\n",
3775
"\n",
3776
" ...\n",
3777
"\n",
3778
" [[ 60.0912 124.0912 171.0968]\n",
3779
" [ 61.8979 125.8979 171.8979]\n",
3780
" [ 65.1203 129.1203 175.1203]\n",
3781
" ...\n",
3782
" [ 29.8372 96.8372 138.8372]\n",
3783
" [ 29.4121 96.4121 138.4121]\n",
3784
" [ 32.9553 99.4646 141.4646]]\n",
3785
"\n",
3786
" [[ 63.8467 127.8467 174.9698]\n",
3787
" [ 67.0037 131.0037 177.24 ]\n",
3788
" [ 68.1559 132.1559 178.3922]\n",
3789
" ...\n",
3790
" [ 26.0615 93.0615 135.0615]\n",
3791
" [ 27.6319 94.6319 136.6319]\n",
3792
" [ 32.0416 98.6089 140.6089]]\n",
3793
"\n",
3794
" [[ 67.4426 131.4426 179.4426]\n",
3795
" [ 69.3598 133.3598 181.3598]\n",
3796
" [ 69.3099 133.3099 181.3099]\n",
3797
" ...\n",
3798
" [ 26.2586 93.2586 135.2586]\n",
3799
" [ 27.735 94.735 136.735 ]\n",
3800
" [ 32.3323 99.3323 141.3323]]]\n",
3801
"\n",
3802
"\n",
3803
" ...\n",
3804
"\n",
3805
"\n",
3806
" [[[139.0198 125.7819 116.7819]\n",
3807
" [143.9583 130.5383 121.5383]\n",
3808
" [144.6247 130.9855 121.9855]\n",
3809
" ...\n",
3810
" [126.2013 129.2013 111.8057]\n",
3811
" [110.7607 113.5085 97.2651]\n",
3812
" [ 97.5831 99.86 85.0292]]\n",
3813
"\n",
3814
" [[139.4828 127.9402 118.9402]\n",
3815
" [143.9592 132.4165 123.4165]\n",
3816
" [146.4499 134.1621 125.3457]\n",
3817
" ...\n",
3818
" [101.6868 105.1725 88.6865]\n",
3819
" [ 86.6495 89.9117 74.7653]\n",
3820
" [ 86.0539 89.0255 75.0255]]\n",
3821
"\n",
3822
" [[140.6337 130.8035 121.8035]\n",
3823
" [143.0147 133.0147 124.0147]\n",
3824
" [147.103 135.9693 127.3472]\n",
3825
" ...\n",
3826
" [ 84.3007 88.3007 72.7276]\n",
3827
" [ 69.1341 73.1341 58.5689]\n",
3828
" [ 70.4928 74.7594 60.7594]]\n",
3829
"\n",
3830
" ...\n",
3831
"\n",
3832
" [[187.8728 206.8728 238.8728]\n",
3833
" [189.844 208.844 240.844 ]\n",
3834
" [189.9616 208.9616 240.9616]\n",
3835
" ...\n",
3836
" [104.7052 101.3642 104.4762]\n",
3837
" [109.5133 106.4279 108.3424]\n",
3838
" [105.5815 103.0505 104.0991]]\n",
3839
"\n",
3840
" [[187.5962 206.5962 238.5962]\n",
3841
" [188.9456 207.9456 239.9456]\n",
3842
" [188.2441 207.2441 239.2441]\n",
3843
" ...\n",
3844
" [132.0984 127.8387 129.1433]\n",
3845
" [135.8242 131.8242 131.9272]\n",
3846
" [126.6285 123.192 122.426 ]]\n",
3847
"\n",
3848
" [[189.2069 207.1445 239.6992]\n",
3849
" [189.5475 207.4852 240.1934]\n",
3850
" [188.0238 205.9615 238.6697]\n",
3851
" ...\n",
3852
" [146.0065 142.0065 141.9484]\n",
3853
" [149.7699 145.7699 144.462 ]\n",
3854
" [141.9789 138.0995 135.7101]]]\n",
3855
"\n",
3856
"\n",
3857
" [[[165.3064 169.3064 169.5602]\n",
3858
" [163.3519 167.3519 168.3519]\n",
3859
" [165.9987 169.9987 168.9987]\n",
3860
" ...\n",
3861
" [135.8459 131.8459 122.8459]\n",
3862
" [135.9956 131.7458 122.8291]\n",
3863
" [135.9468 128.9468 120.9468]]\n",
3864
"\n",
3865
" [[166.6916 170.6916 171.0454]\n",
3866
" [166.6149 170.6149 171.6149]\n",
3867
" [164.8632 168.8632 167.8632]\n",
3868
" ...\n",
3869
" [135.3877 131.3877 122.3877]\n",
3870
" [132.6915 128.4752 119.5473]\n",
3871
" [133.8611 127.2632 119.1292]]\n",
3872
"\n",
3873
" [[167.4778 171.4778 172.4778]\n",
3874
" [167.5433 171.5433 172.5433]\n",
3875
" [164.6393 168.6393 167.6393]\n",
3876
" ...\n",
3877
" [132.3919 128.3919 119.3919]\n",
3878
" [135.762 131.762 122.762 ]\n",
3879
" [136.3984 132.3984 123.3984]]\n",
3880
"\n",
3881
" ...\n",
3882
"\n",
3883
" [[170.843 174.843 175.843 ]\n",
3884
" [169.5878 173.5878 174.5878]\n",
3885
" [170.2155 172.2155 171.2155]\n",
3886
" ...\n",
3887
" [157.9217 160.9217 143.9217]\n",
3888
" [153.8402 156.6737 139.7569]\n",
3889
" [152.2707 153.2707 137.2707]]\n",
3890
"\n",
3891
" [[170.8207 174.8207 175.8207]\n",
3892
" [169.5656 173.5656 174.5656]\n",
3893
" [169.7908 171.3877 171.5969]\n",
3894
" ...\n",
3895
" [154.8125 157.0064 140.4095]\n",
3896
" [154.4689 156.5634 140.0161]\n",
3897
" [154.4389 155.4389 139.4389]]\n",
3898
"\n",
3899
" [[168.8867 172.8867 173.8867]\n",
3900
" [168.1523 172.1523 173.1523]\n",
3901
" [169.1824 170.1824 172.1824]\n",
3902
" ...\n",
3903
" [152.3721 153.3721 137.3721]\n",
3904
" [155.2122 156.2122 140.2122]\n",
3905
" [151.5763 152.5763 136.5763]]]\n",
3906
"\n",
3907
"\n",
3908
" [[[180.7547 174.7547 176.7547]\n",
3909
" [179.1914 173.1914 175.1914]\n",
3910
" [178.8276 172.8276 174.8276]\n",
3911
" ...\n",
3912
" [159.7093 151.7093 149.7093]\n",
3913
" [159.9731 151.9731 149.9731]\n",
3914
" [160.5627 152.5627 150.5627]]\n",
3915
"\n",
3916
" [[182.7767 176.7767 178.7767]\n",
3917
" [181.1855 175.1855 177.1855]\n",
3918
" [179.3782 173.3782 175.3782]\n",
3919
" ...\n",
3920
" [158.4291 150.8546 148.7128]\n",
3921
" [158.4028 150.8284 148.6865]\n",
3922
" [160.4569 152.5167 150.4967]]\n",
3923
"\n",
3924
" [[181.7647 175.7647 177.7647]\n",
3925
" [182.5463 176.5463 178.5463]\n",
3926
" [181.397 175.397 177.397 ]\n",
3927
" ...\n",
3928
" [158.4604 153.4604 150.4604]\n",
3929
" [158.56 153.56 150.56 ]\n",
3930
" [159.8327 152.2539 150.1135]]\n",
3931
"\n",
3932
" ...\n",
3933
"\n",
3934
" [[139.4785 136.4785 31.4785]\n",
3935
" [138.4766 135.4766 30.4766]\n",
3936
" [136.9275 133.9275 28.9275]\n",
3937
" ...\n",
3938
" [111.9077 107.9077 20.9077]\n",
3939
" [111.5531 107.5531 20.5531]\n",
3940
" [108.2808 104.2808 17.2808]]\n",
3941
"\n",
3942
" [[136.3306 133.3306 28.3306]\n",
3943
" [138.5995 135.5995 30.5995]\n",
3944
" [137.0039 134.0039 29.0039]\n",
3945
" ...\n",
3946
" [110.668 106.668 19.668 ]\n",
3947
" [111.1356 107.1356 20.1356]\n",
3948
" [109.5726 105.5726 18.5726]]\n",
3949
"\n",
3950
" [[136.5696 133.5696 28.5696]\n",
3951
" [137.61 134.61 29.61 ]\n",
3952
" [139.7963 136.7963 31.7963]\n",
3953
" ...\n",
3954
" [109.8682 105.8682 18.8682]\n",
3955
" [110.9538 106.9538 19.9538]\n",
3956
" [111.5432 107.5432 20.5432]]]], shape=(8, 640, 640, 3), dtype=float32) {'classes': <tf.RaggedTensor [[], [6.0], [6.0], [6.0], [7.0], [7.0], [7.0], [6.0]]>, 'boxes': <tf.RaggedTensor [[], [[0.0, 0.0, 640.0, 640.0]], [[295.39124, 0.0, 640.0, 78.37842]],\n",
3957
" [[0.0, 0.0, 640.0, 640.0]], [[0.0, 0.0, 640.0, 640.0]],\n",
3958
" [[0.0, 306.2356, 640.0, 640.0]], [[0.0, 0.0, 640.0, 640.0]],\n",
3959
" [[0.0, 0.0, 607.5311, 640.0]]]>}\n"
3960
]
3961
}
3962
],
3963
"source": [
3964
"for images, labels in train_ds.take(4):\n",
3965
" print(images, labels)"
3966
]
3967
},
3968
{
3969
"cell_type": "raw",
3970
"id": "e3e8e61f-7a01-46ca-b391-a3f6fd2adf17",
3971
"metadata": {
3972
"jupyter": {
3973
"source_hidden": true
3974
},
3975
"scrolled": true
3976
},
3977
"source": [
3978
"def visualize_dataset(inputs, value_range, rows, cols, bounding_box_format):\n",
3979
" inputs = next(iter(inputs.take(1)))\n",
3980
" images, bounding_boxes = inputs[\"images\"], inputs[\"bounding_boxes\"]\n",
3981
" visualization.plot_bounding_box_gallery(\n",
3982
" images,\n",
3983
" value_range=value_range,\n",
3984
" rows=rows,\n",
3985
" cols=cols,\n",
3986
" y_true=bounding_boxes,\n",
3987
" scale=5,\n",
3988
" font_scale=0.7,\n",
3989
" bounding_box_format=bounding_box_format,\n",
3990
" class_mapping=class_mapping,\n",
3991
" )\n",
3992
"\n",
3993
"\n",
3994
"visualize_dataset(\n",
3995
" train_ds, bounding_box_format=\"xyxy\", value_range=(0, 255), rows=2, cols=2\n",
3996
")\n",
3997
"\n",
3998
"visualize_dataset(\n",
3999
" val_ds, bounding_box_format=\"xyxy\", value_range=(0, 255), rows=2, cols=2\n",
4000
")"
4001
]
4002
},
4003
{
4004
"cell_type": "code",
4005
"execution_count": null,
4006
"id": "3103113b-041e-44fd-b86d-083b2be43ef2",
4007
"metadata": {},
4008
"outputs": [],
4009
"source": []
4010
},
4011
{
4012
"cell_type": "code",
4013
"execution_count": 103,
4014
"id": "e0b69b54-a506-4d7c-817e-292e31e7ff90",
4015
"metadata": {
4016
"scrolled": true
4017
},
4018
"outputs": [
4019
{
4020
"name": "stdout",
4021
"output_type": "stream",
4022
"text": [
4023
"87/87 [==============================] - 447s 5s/step - loss: 1.7464 - box_loss: 1.4089 - class_loss: 0.3376 - val_loss: 1.9216 - val_box_loss: 1.4552 - val_class_loss: 0.4664\n"
4024
]
4025
},
4026
{
4027
"data": {
4028
"text/plain": [
4029
"<keras.callbacks.History at 0x7bbc8860f9d0>"
4030
]
4031
},
4032
"execution_count": 103,
4033
"metadata": {},
4034
"output_type": "execute_result"
4035
}
4036
],
4037
"source": [
4038
"yolo.fit(\n",
4039
" train_ds,\n",
4040
" validation_data=val_ds,\n",
4041
" epochs=1,\n",
4042
" #callbacks=[keras_cv.callbacks.PyCOCOCallback(val_ds, \"model.h5\")],\n",
4043
")"
4044
]
4045
},
4046
{
4047
"cell_type": "code",
4048
"execution_count": 104,
4049
"id": "7dd90e06",
4050
"metadata": {
4051
"scrolled": true
4052
},
4053
"outputs": [
4054
{
4055
"name": "stdout",
4056
"output_type": "stream",
4057
"text": [
4058
"WARNING:tensorflow:Found duplicated `Variable`s in Model's `weights`. This is usually caused by `Variable`s being shared by Layers in the Model. These `Variable`s will be treated as separate `Variable`s when the Model is restored. To avoid this, please save with `save_format=\"tf\"`.\n"
4059
]
4060
}
4061
],
4062
"source": [
4063
"yolo.save(\"model.keras\")"
4064
]
4065
},
4066
{
4067
"cell_type": "markdown",
4068
"id": "f23c9496",
4069
"metadata": {},
4070
"source": [
4071
"## inferencing"
4072
]
4073
},
4074
{
4075
"cell_type": "code",
4076
"execution_count": 105,
4077
"id": "c9eb4483-0ced-4e22-8a0b-99406a144ab5",
4078
"metadata": {
4079
"scrolled": true
4080
},
4081
"outputs": [],
4082
"source": [
4083
"from tensorflow.keras.models import load_model\n",
4084
"with keras.utils.custom_object_scope({'YOLOV8Detector': keras_cv.models.YOLOV8Detector}):\n",
4085
" model = load_model(\"model.keras\", custom_objects={\"YoloV8Detector\": keras_cv.models.YOLOV8Detector}, compile=False)\n",
4086
"\n",
4087
"optimizer = tf.keras.optimizers.Adam(\n",
4088
" learning_rate=0.00125,\n",
4089
" global_clipnorm=10,\n",
4090
")\n",
4091
"\n",
4092
"model.compile(\n",
4093
" optimizer=optimizer, classification_loss=\"binary_crossentropy\", box_loss=\"ciou\"\n",
4094
")"
4095
]
4096
},
4097
{
4098
"cell_type": "code",
4099
"execution_count": 106,
4100
"id": "4ee9c4c1",
4101
"metadata": {
4102
"scrolled": true
4103
},
4104
"outputs": [
4105
{
4106
"name": "stderr",
4107
"output_type": "stream",
4108
"text": [
4109
"2024-05-09 22:37:48.637258: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_1' with dtype variant and shape [927]\n",
4110
"\t [[{{node Placeholder/_1}}]]\n",
4111
"2024-05-09 22:37:48.637441: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'Placeholder/_17' with dtype resource\n",
4112
"\t [[{{node Placeholder/_17}}]]\n",
4113
"2024-05-09 22:37:52.409724: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4114
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n",
4115
"2024-05-09 22:37:52.410621: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4116
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n",
4117
"2024-05-09 22:37:52.437120: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4118
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n",
4119
"2024-05-09 22:37:52.440690: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4120
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n",
4121
"2024-05-09 22:37:52.445229: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4122
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n",
4123
"2024-05-09 22:37:52.517018: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4124
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n",
4125
"2024-05-09 22:37:52.523481: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4126
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n",
4127
"2024-05-09 22:37:52.531275: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4128
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n",
4129
"2024-05-09 22:37:52.548541: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4130
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n",
4131
"2024-05-09 22:37:52.550524: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4132
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n",
4133
"2024-05-09 22:37:52.562647: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4134
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n",
4135
"2024-05-09 22:37:52.582199: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4136
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n",
4137
"2024-05-09 22:37:52.840105: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4138
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n",
4139
"2024-05-09 22:37:52.856027: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4140
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n",
4141
"2024-05-09 22:37:52.871862: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4142
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n",
4143
"2024-05-09 22:37:53.246700: I tensorflow/core/common_runtime/executor.cc:1197] [/job:localhost/replica:0/task:0/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): CANCELLED: Loop execution was cancelled.\n",
4144
"\t [[{{function_node jittered_resize_9_map_while_body_133434}}{{node jittered_resize_9/map/while/map/while}}]]\n"
4145
]
4146
},
4147
{
4148
"name": "stdout",
4149
"output_type": "stream",
4150
"text": [
4151
"WARNING:tensorflow:5 out of the last 15 calls to <function Model.make_predict_function.<locals>.predict_function at 0x7bbbf0bba160> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.\n",
4152
"1/1 [==============================] - 2s 2s/step\n"
4153
]
4154
},
4155
{
4156
"data": {
4157
"image/png": "