BVRA
/

legacy_seresnext101_32x4d.in1k_ft_df20m_384

Image Classification

Model card Files Files and versions Community

MHanzl commited on Feb 1

Commit

d50701c

•

1 Parent(s): b2e9b97

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -31,7 +31,7 @@ model = timm.create_model("hf-hub:BVRA/legacy_seresnext101_32x4d.in1k_ft_df20m_3
 model = model.eval()
 train_transforms = T.Compose([T.Resize((384, 384)),
                               T.ToTensor(),
-                              T.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])
 img = Image.open(PATH_TO_YOUR_IMAGE)
 output = model(train_transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor
 ```

 model = model.eval()
 train_transforms = T.Compose([T.Resize((384, 384)),
                               T.ToTensor(),
+                              T.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])])
 img = Image.open(PATH_TO_YOUR_IMAGE)
 output = model(train_transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor
 ```