HTML document, Unicode text, UTF-8 text
1
<!DOCTYPE html>
2
<html lang="en">
3
<head>
4
<meta charset="UTF-8">
5
<title>agpl</title>
6
<link rel="stylesheet" href="/static/style.css">
7
<meta name="viewport" content="width=device-width, initial-scale=1.0">
8
</head>
9
<body>
10
<header>
11
<a href="#main" id="skip-link">Skip navigation</a>
12
<nav>
13
<ul>
14
<li><a href="/">Home</a></li>
15
<li><a href="/projects">Projects</a></li>
16
<li><a href="/index">Index</a></li>
17
<li><a href="/about">About</a></li>
18
<li><a href="https://roundabout-host.com/roundabout">Roundabout-host</a></li>
19
</ul>
20
<ul>
21
<li><a href="mailto:root@roundabout-host.com" id="mail-link">root@roundabout-host.com</a></li>
22
</ul>
23
</nav>
24
</header>
25
<main id="main">
26
27
<h1>agpl</h1>
28
<div class="topic-posts">
30
31
<article class="content-area">
32
<h2><a href="/projects/gigadata.html" class="article-title">Gigadata</a></h2>
33
<div class="home-article-date">2024-10-15</div>
34
<p><p>Gigadata is an image dataset collection and annotation platform. It allows anyone
35
to easily contribute to the dataset by uploading images and annotating objects,
36
and to use the dataset for training machine learning models.
37
</p></p>
38
</article>
39
40
<article class="content-area">
41
<h2><a href="/projects/roundabout.html" class="article-title">The roundabout</a></h2>
42
<div class="home-article-date">2025-02-02</div>
43
<p><p>The roundabout is a <strong class="emphasis-2">git repository hosting</strong> server software. It is designed to be a complete
44
alternative to GitHub, GitLab, BitBucket, Gogs/Gitea/Forgejo, and other similar services. It
45
is still in development and not yet ready for production use. As of version 0.3.0 development
46
stage, it supports:
47
</p></p>
48
</article>
49
50
<article class="content-area">
51
<h2><a href="/projects/waste.html" class="article-title">Waste detection</a></h2>
52
<div class="home-article-date">2024-04-29</div>
53
<p><p>An YOLO model specifically trained to detect waste in images. We collected a custom dataset of waste,
54
classified and annotated it, and trained the model using YOLOv8 on Keras. The model is able to detect
55
the position and class of waste in images. It can separate the following classes of waste:
56
</p></p>
57
</article>
58
59
</div>
60
</main>
62
<footer>
63
<p>Page generated on Sunday, 4 May 2025 at 15:06:42</p>
64
<p xmlns:cc="http://creativecommons.org/ns#" >This work is marked with <a href="https://creativecommons.org/publicdomain/zero/1.0/?ref=chooser-v1" target="_blank" rel="license noopener noreferrer" style="display:inline-block;">CC0 1.0 Universal</a> (🄍). No rights reserved.</p>
65
<p>Hosted at <a href="https://roundabout-host.com/roundabout">Roundabout-host</a> using the static site service, and generated with <a href="/projects/ampoule.html">Ampoule</a>.</p>
66
<a href="#">Back to top</a>
67
</footer>
68
</body>
69
</html>