Commit ·
80a2432
1
Parent(s): 2ba2064
Improve HopitAI organization card
Browse files
README.md
CHANGED
|
@@ -1,12 +1,89 @@
|
|
| 1 |
---
|
| 2 |
title: README
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
license: mit
|
| 9 |
-
short_description:
|
| 10 |
---
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
title: README
|
| 3 |
+
emoji: 🧥
|
| 4 |
+
colorFrom: indigo
|
| 5 |
+
colorTo: green
|
| 6 |
sdk: static
|
| 7 |
pinned: false
|
| 8 |
license: mit
|
| 9 |
+
short_description: Open-source fashion intelligence and visual search.
|
| 10 |
---
|
| 11 |
|
| 12 |
+
<section>
|
| 13 |
+
<h1>HopitAI</h1>
|
| 14 |
+
<p>
|
| 15 |
+
HopitAI builds open-source fashion intelligence models for visual search,
|
| 16 |
+
product matching, catalog retrieval, and ecommerce discovery.
|
| 17 |
+
</p>
|
| 18 |
+
</section>
|
| 19 |
+
|
| 20 |
+
<section>
|
| 21 |
+
<h2>MODA Fashion Retrieval</h2>
|
| 22 |
+
<p>
|
| 23 |
+
MODA is a family of fashion image retrieval models designed to turn product
|
| 24 |
+
and outfit images into useful embeddings for similarity search.
|
| 25 |
+
</p>
|
| 26 |
+
<p>
|
| 27 |
+
<a href="https://huggingface.co/spaces/HopitAI/moda-fashion-search">Try the interactive demo</a>
|
| 28 |
+
·
|
| 29 |
+
<a href="https://github.com/hopit-ai/Moda">View the GitHub repo</a>
|
| 30 |
+
·
|
| 31 |
+
<a href="https://huggingface.co/HopitAI/moda-fashion-deepfashion2">Start with DeepFashion2</a>
|
| 32 |
+
</p>
|
| 33 |
+
</section>
|
| 34 |
+
|
| 35 |
+
<section>
|
| 36 |
+
<h2>Featured Models</h2>
|
| 37 |
+
<table>
|
| 38 |
+
<tr>
|
| 39 |
+
<th>Model</th>
|
| 40 |
+
<th>Best for</th>
|
| 41 |
+
</tr>
|
| 42 |
+
<tr>
|
| 43 |
+
<td><a href="https://huggingface.co/HopitAI/moda-fashion-distilled">MODA-Fashion-Distilled</a></td>
|
| 44 |
+
<td>Best overall quality</td>
|
| 45 |
+
</tr>
|
| 46 |
+
<tr>
|
| 47 |
+
<td><a href="https://huggingface.co/HopitAI/moda-fashion-distilled-512d">MODA-Fashion-Distilled-512d</a></td>
|
| 48 |
+
<td>Compact vector search indexes</td>
|
| 49 |
+
</tr>
|
| 50 |
+
<tr>
|
| 51 |
+
<td><a href="https://huggingface.co/HopitAI/moda-fashion-deepfashion2">MODA-Fashion-DeepFashion2</a></td>
|
| 52 |
+
<td>Simple reproducible recipe</td>
|
| 53 |
+
</tr>
|
| 54 |
+
<tr>
|
| 55 |
+
<td><a href="https://huggingface.co/HopitAI/moda-fashion-vision-fp16">MODA-Fashion-Vision-FP16</a></td>
|
| 56 |
+
<td>Smaller edge and mobile deployment</td>
|
| 57 |
+
</tr>
|
| 58 |
+
<tr>
|
| 59 |
+
<td><a href="https://huggingface.co/HopitAI/moda-fashion-matryoshka">MODA-Fashion-Matryoshka</a></td>
|
| 60 |
+
<td>Flexible embedding dimensions</td>
|
| 61 |
+
</tr>
|
| 62 |
+
</table>
|
| 63 |
+
</section>
|
| 64 |
+
|
| 65 |
+
<section>
|
| 66 |
+
<h2>Quick Start</h2>
|
| 67 |
+
|
| 68 |
+
```bash
|
| 69 |
+
huggingface-cli download HopitAI/moda-fashion-deepfashion2 --local-dir ./moda-fashion-deepfashion2
|
| 70 |
+
```
|
| 71 |
+
|
| 72 |
+
```python
|
| 73 |
+
import open_clip
|
| 74 |
+
|
| 75 |
+
model, preprocess_train, preprocess_val = open_clip.create_model_and_transforms(
|
| 76 |
+
"hf-hub:HopitAI/moda-fashion-deepfashion2"
|
| 77 |
+
)
|
| 78 |
+
```
|
| 79 |
+
</section>
|
| 80 |
+
|
| 81 |
+
<section>
|
| 82 |
+
<h2>Use Cases</h2>
|
| 83 |
+
<ul>
|
| 84 |
+
<li>Find visually similar products in a fashion catalog.</li>
|
| 85 |
+
<li>Match street-style looks to shoppable items.</li>
|
| 86 |
+
<li>Deduplicate product images across marketplaces.</li>
|
| 87 |
+
<li>Build embedding indexes for ecommerce search and recommendations.</li>
|
| 88 |
+
</ul>
|
| 89 |
+
</section>
|