Add DLC3 superanimal_topviewmouse detector and pose model

README.md

@@ -2,6 +2,8 @@
 tags:
 - computer_vision
 - pose_estimation
+- animal_pose_estimation
+- deeplabcut
 ---
 # MODEL CARD:
 
@@ -11,9 +13,13 @@ tags:
 trained to predict mouse topline pose from images. 
 Please see [Shaokai Ye et al. 2023](https://arxiv.org/abs/2203.07436) for details.
 
-• The model is an DLCRNet and/or HRNet-w32 trained on our TopViewMouse-5K dataset.
+• The there are three models:
+  - `pose_model.pth` is an HRNet-w32 compatable for DLC3.0+ Pytorch code, trained on our TopViewMouse-5K dataset.
+  - `detector.pt` is a Faster R-CNN that can be used as a detector for top-down detection.
+  - `DLC_ma_supertopview5k_resnet_50_iteration-0_shuffle-1.tar.gz` is a DLCRNet trained on our TopViewMouse-5K dataset.
 
-•  It was trained within the DeepLabCut framework. Full training details can be found in Ye et al. 2023.
+
+•  Full training details can be found in Ye et al. 2023.
 You can use this model simply with our light-weight loading package called [DLCLibrary](https://github.com/DeepLabCut/DLClibrary). 
 Here is an example useage:
 
@@ -24,7 +30,7 @@ from dlclibrary import download_huggingface_model
 # Creates a folder and downloads the model to it
 model_dir = Path("./superanimal_topviewmouse_model")
 model_dir.mkdir()
-download_huggingface_model("superanimal_topviewmouse", model_dir)
+download_huggingface_model("superanimal_topviewmouse_model", model_dir)
 ```
 
 ## Intended Use

detector.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5108318a1e63dcc4103de29b98a94c5a42302e6104637a38dacf0fef0f137dea
+size 517816013

pose_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ec111e8d9a22277e3b841ecafc6159b1c6501ab7fd4af92cf60b68a7f12fdd7
+size 159594859