try swin

models.py

@@ -893,7 +893,7 @@ class PoolFormerBlock(nn.Module):
         self.norm1 = norm_layer(dim)
         #self.token_mixer = Pooling(pool_size=pool_size)
         # self.token_mixer = FNetBlock()
-        self.window_size = 7
+        self.window_size = 8
         self.attn_mask = None
         self.token_mixer = WindowAttention(dim=dim, window_size=to_2tuple(self.window_size), num_heads=10)
         self.norm2 = norm_layer(dim)