Update README.md

README.md

@@ -7,7 +7,7 @@ tags:
 library_name: wildlife-datasets
 license: cc-by-nc-4.0
 ---
-# Model card for MegaDescriptor-B-224
+# Model card for MegaDescriptor-L-384
 
 A Swin-L image feature model. Superwisely pre-trained on animal re-identification datasets.
 
@@ -15,12 +15,13 @@ A Swin-L image feature model. Superwisely pre-trained on animal re-identificatio
 ## Model Details
 - **Model Type:** Animal re-identification / feature backbone
 - **Model Stats:**
-  - Params (M): ??
+  - Params (M): 228.8
   - Image size: 384 x 384
+  - Architecture: swin_large_patch4_window12_384
 - **Papers:**
   - Swin Transformer: Hierarchical Vision Transformer using Shifted Windows --> https://arxiv.org/abs/2103.14030
 - **Original:** ??
-- **Pretrain Dataset:** All available re-identification datasets --> TBD
+- **Pretrain Dataset:** All available re-identification datasets --> https://github.com/WildlifeDatasets/wildlife-datasets
 
 ## Model Usage
 ### Image Embeddings
@@ -33,10 +34,10 @@ import torchvision.transforms as T
 from PIL import Image
 from urllib.request import urlopen
 
-model = timm.create_model("hf-hub:BVRA/wildlife-mega", pretrained=True)
+model = timm.create_model("hf-hub:BVRA/MegaDescriptor-L-384", pretrained=True)
 model = model.eval()
 
-train_transforms = T.Compose([T.Resize(224), 
+train_transforms = T.Compose([T.Resize(size=(384, 384)),
                               T.ToTensor(), 
                               T.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])