Fixed some typos in comments

segment_anything/modeling/image_encoder.py

@@ -198,7 +198,7 @@ class Attention(nn.Module):
         Args:
             dim (int): Number of input channels.
             num_heads (int): Number of attention heads.
-            qkv_bias (bool:  If True, add a learnable bias to query, key, value.
+            qkv_bias (bool):  If True, add a learnable bias to query, key, value.
             rel_pos (bool): If True, add relative positional embeddings to the attention map.
             rel_pos_zero_init (bool): If True, zero initialize relative positional parameters.
             input_size (int or None): Input resolution for calculating the relative positional
@@ -270,7 +270,7 @@ def window_unpartition(
     """
     Window unpartition into original sequences and removing padding.
     Args:
-        x (tensor): input tokens with [B * num_windows, window_size, window_size, C].
+        windows (tensor): input tokens with [B * num_windows, window_size, window_size, C].
         window_size (int): window size.
         pad_hw (Tuple): padded height and width (Hp, Wp).
         hw (Tuple): original height and width (H, W) before padding.