Update README.md

README.md

@@ -39,12 +39,16 @@ Images are normalized with mean=[0.5] and std=[0.5]
 Input tensor shape: (batch_size, 1, 32, 32)
 
 ### Preprocessing
-pythonCopytransforms.Compose([
+```python
+from torchvision import transforms
+
+transforms.Compose([
     transforms.Grayscale(),
     transforms.Resize((32, 32)),
     transforms.ToTensor(),
     transforms.Normalize(mean=[0.5], std=[0.5])
 ])
+```
 
 ## Training Procedure