Update README.md

README.md

@@ -1,11 +1,11 @@
 ---
+datasets:
+- imagenet-1k
+library_name: timm
 tags:
 - image-classification
 - timm
 - rdnet
-library_name: timm
-datasets:
-- imagenet-1k
 ---
 # Model card for rdnet_large.nv_in1k
 
@@ -29,6 +29,7 @@ from urllib.request import urlopen
 from PIL import Image
 import timm
 import torch
+import rdnet  # register rdnet models to timm
 
 img = Image.open(urlopen(
     'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
@@ -51,6 +52,7 @@ top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100,
 from urllib.request import urlopen
 from PIL import Image
 import timm
+import rdnet  # register rdnet models to timm
 
 img = Image.open(urlopen(
     'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
@@ -72,12 +74,10 @@ output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batc
 for o in output:
     # print shape of each feature map in output
     # e.g.:
-    #  torch.Size([1, 64, 224, 224])
-    #  torch.Size([1, 128, 112, 112])
-    #  torch.Size([1, 256, 56, 56])
-    #  torch.Size([1, 512, 28, 28])
-    #  torch.Size([1, 512, 14, 14])
-    #  torch.Size([1, 512, 7, 7])
+    # torch.Size([1, 528, 56, 56])
+    # torch.Size([1, 840, 28, 28])
+    # torch.Size([1, 1528, 14, 14])
+    # torch.Size([1, 2000, 7, 7])
 
     print(o.shape)
 ```
@@ -87,6 +87,7 @@ for o in output:
 from urllib.request import urlopen
 from PIL import Image
 import timm
+import rdnet  # register rdnet models to timm
 
 img = Image.open(urlopen(
     'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
@@ -108,7 +109,7 @@ output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_featu
 # or equivalently (without needing to set num_classes=0)
 
 output = model.forward_features(transforms(img).unsqueeze(0))
-# output is unpooled, a (1, 512, 7, 7) shaped tensor
+# output is unpooled, a (1, 2000, 7, 7) shaped tensor
 
 output = model.forward_head(output, pre_logits=True)
 # output is a (1, num_features) shaped tensor