Revert asymmetric padding. Raise error if block size is not even.

Author: dcasbol

torchvision/ops/drop_block.py

@@ -36,17 +36,16 @@ def drop_block2d(
 
     N, C, H, W = input.size()
     block_size = min(block_size, W, H)
+    if block_size % 2 == 0:
+        raise ValueError(f"block size should be odd. Got {block_size} which is even.")
+
     # compute the gamma of Bernoulli distribution
     gamma = (p * H * W) / ((block_size**2) * ((H - block_size + 1) * (W - block_size + 1)))
     noise = torch.empty((N, C, H - block_size + 1, W - block_size + 1), dtype=input.dtype, device=input.device)
     noise.bernoulli_(gamma)
 
     noise = F.pad(noise, [block_size // 2] * 4, value=0)
-    left_pad = right_pad = block_size // 2
-    if left_pad > 0 and block_size % 2 == 0:
-        left_pad -= 1
-    noise = F.pad(noise, pad=(left_pad, right_pad, left_pad, right_pad))
-    noise = F.max_pool2d(noise, stride=1, kernel_size=block_size)
+    noise = F.max_pool2d(noise, stride=(1, 1), kernel_size=(block_size, block_size), padding=block_size // 2)
     noise = 1 - noise
     normalize_scale = noise.numel() / (eps + noise.sum())
     if inplace:
@@ -86,6 +85,9 @@ def drop_block3d(
 
     N, C, D, H, W = input.size()
     block_size = min(block_size, D, H, W)
+    if block_size % 2 == 0:
+        raise ValueError(f"block size should be odd. Got {block_size} which is even.")
+
     # compute the gamma of Bernoulli distribution
     gamma = (p * D * H * W) / ((block_size**3) * ((D - block_size + 1) * (H - block_size + 1) * (W - block_size + 1)))
     noise = torch.empty(