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.

segment_anything/modeling/sam.py

@@ -85,8 +85,8 @@ class Sam(nn.Module):
           (list(dict)): A list over input images, where each element is
             as dictionary with the following keys.
               'masks': (torch.Tensor) Batched binary mask predictions,
-                with shape BxCxHxW, where B is the number of input promts,
-                C is determiend by multimask_output, and (H, W) is the
+                with shape BxCxHxW, where B is the number of input prompts,
+                C is determined by multimask_output, and (H, W) is the
                 original size of the image.
               'iou_predictions': (torch.Tensor) The model's predictions
                 of mask quality, in shape BxC.

segment_anything/modeling/transformer.py

@@ -96,7 +96,7 @@ class TwoWayTransformer(nn.Module):
                 key_pe=image_pe,
             )
 
-        # Apply the final attenion layer from the points to the image
+        # Apply the final attention layer from the points to the image
         q = queries + point_embedding
         k = keys + image_pe
         attn_out = self.final_attn_token_to_image(q=q, k=k, v=keys)