diff --git a/models.py b/models.py
index 7b49bcd..c9cbbea 100644
--- a/models.py
+++ b/models.py
@@ -787,7 +787,7 @@ class WindowAttention(nn.Module):
             mask: (0/-inf) mask with shape of (num_windows, Wh*Ww, Wh*Ww) or None
         """
         print(x.shape)
-        B_, N, C = x.shape
+        B_, N, C, _ = x.shape
         qkv_bias = None
         if self.q_bias is not None:
             qkv_bias = torch.cat((self.q_bias, torch.zeros_like(self.v_bias, requires_grad=False), self.v_bias))