Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,29 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
We provide the models used in our data curation pipeline to assist with constructing the Surg-3M dataset, including video storyboard classification models, frame classification models, and non-surgical object detection models. The model loader file can be found at [src/model_loader.py](https://github.com/visurg-ai/surg-3m/blob/main/src/model_loader.py)
|
| 5 |
+
|
| 6 |
+
<div align="center">
|
| 7 |
+
<table style="margin-left: auto; margin-right: auto;">
|
| 8 |
+
<tr>
|
| 9 |
+
<th>Model</th>
|
| 10 |
+
<th>Architecture</th>
|
| 11 |
+
<th colspan="5">Download</th>
|
| 12 |
+
</tr>
|
| 13 |
+
<tr>
|
| 14 |
+
<td>Video storyboard classification models</td>
|
| 15 |
+
<td>ResNet-18</td>
|
| 16 |
+
<td><a href="">Full ckpt</a></td>
|
| 17 |
+
</tr>
|
| 18 |
+
<tr>
|
| 19 |
+
<td>Frame classification models</td>
|
| 20 |
+
<td>ResNet-18</td>
|
| 21 |
+
<td><a href="">Full ckpt</a></td>
|
| 22 |
+
</tr>
|
| 23 |
+
<tr>
|
| 24 |
+
<td>Non-surgical object detection models</td>
|
| 25 |
+
<td>Yolov8-Nano</td>
|
| 26 |
+
<td><a href="">Full ckpt</a></td>
|
| 27 |
+
</tr>
|
| 28 |
+
</table>
|
| 29 |
+
</div>
|