Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ pipeline_tag: keypoint-detection
|
|
| 14 |
• SuperAnimal-Quadruped model(s) developed by the [M.W.Mathis Lab](http://www.mackenziemathislab.org/) in 2023, trained to predict quadruped pose from images.
|
| 15 |
Please see [Shaokai Ye et al. 2023](https://arxiv.org/abs/2203.07436) for details.
|
| 16 |
|
| 17 |
-
• The there are three models:
|
| 18 |
- `pose_model.pth` is an HRNet-w32 compatable for DLC3.0+ Pytorch code, trained on our Quadruped-80K dataset.
|
| 19 |
- `detector.pt` is a Faster R-CNN that can be used as a detector for top-down detection.
|
| 20 |
- `hrnet_w32_quadruped80k.pth` is an HRNet-w32 trained with mmpose on our Quadruped-80K dataset.
|
|
|
|
| 14 |
• SuperAnimal-Quadruped model(s) developed by the [M.W.Mathis Lab](http://www.mackenziemathislab.org/) in 2023, trained to predict quadruped pose from images.
|
| 15 |
Please see [Shaokai Ye et al. 2023](https://arxiv.org/abs/2203.07436) for details.
|
| 16 |
|
| 17 |
+
• The there are three main models (and several auxiliary model checkpoints):
|
| 18 |
- `pose_model.pth` is an HRNet-w32 compatable for DLC3.0+ Pytorch code, trained on our Quadruped-80K dataset.
|
| 19 |
- `detector.pt` is a Faster R-CNN that can be used as a detector for top-down detection.
|
| 20 |
- `hrnet_w32_quadruped80k.pth` is an HRNet-w32 trained with mmpose on our Quadruped-80K dataset.
|