simplified flatten

clip/model.py

@@ -66,7 +66,7 @@ class AttentionPool2d(nn.Module):
         self.num_heads = num_heads
 
     def forward(self, x):
-        x = x.reshape(x.shape[0], x.shape[1], x.shape[2] * x.shape[3]).permute(2, 0, 1)  # NCHW -> (HW)NC
+        x = x.flatten(start_dim=2).permute(2, 0, 1)  # NCHW -> (HW)NC
         x = torch.cat([x.mean(dim=0, keepdim=True), x], dim=0)  # (HW+1)NC
         x = x + self.positional_embedding[:, None, :].to(x.dtype)  # (HW+1)NC
         x, _ = F.multi_head_attention_forward(