Fixed some typos in comments

scripts/export_onnx_model.py

@@ -149,7 +149,7 @@ def run_export(
         warnings.filterwarnings("ignore", category=torch.jit.TracerWarning)
         warnings.filterwarnings("ignore", category=UserWarning)
         with open(output, "wb") as f:
-            print(f"Exporing onnx model to {output}...")
+            print(f"Exporting onnx model to {output}...")
             torch.onnx.export(
                 onnx_model,
                 tuple(dummy_inputs.values()),

segment_anything/automatic_mask_generator.py

@@ -73,10 +73,10 @@ class SamAutomaticMaskGenerator:
             calculated the stability score.
           box_nms_thresh (float): The box IoU cutoff used by non-maximal
             suppression to filter duplicate masks.
-          crops_n_layers (int): If >0, mask prediction will be run again on
+          crop_n_layers (int): If >0, mask prediction will be run again on
             crops of the image. Sets the number of layers to run, where each
             layer has 2**i_layer number of image crops.
-          crops_nms_thresh (float): The box IoU cutoff used by non-maximal
+          crop_nms_thresh (float): The box IoU cutoff used by non-maximal
             suppression to filter duplicate masks between different crops.
           crop_overlap_ratio (float): Sets the degree to which crops overlap.
             In the first crop layer, crops will overlap by this fraction of

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)

segment_anything/predictor.py

@@ -186,7 +186,7 @@ class SamPredictor:
           point_labels (torch.Tensor or None): A BxN array of labels for the
             point prompts. 1 indicates a foreground point and 0 indicates a
             background point.
-          box (np.ndarray or None): A Bx4 array given a box prompt to the
+          boxes (np.ndarray or None): A Bx4 array given a box prompt to the
             model, in XYXY format.
           mask_input (np.ndarray): A low resolution mask input to the model, typically
             coming from a previous prediction iteration. Has form Bx1xHxW, where

segment_anything/utils/amg.py

@@ -162,7 +162,7 @@ def calculate_stability_score(
     the predicted mask logits at high and low values.
     """
     # One mask is always contained inside the other.
-    # Save memory by preventing unnecesary cast to torch.int64
+    # Save memory by preventing unnecessary cast to torch.int64
     intersections = (
         (masks > (mask_threshold + threshold_offset))
         .sum(-1, dtype=torch.int16)

segment_anything/utils/transforms.py

@@ -15,7 +15,7 @@ from typing import Tuple
 
 class ResizeLongestSide:
     """
-    Resizes images to longest side 'target_length', as well as provides
+    Resizes images to the longest side 'target_length', as well as provides
     methods for resizing coordinates and boxes. Provides methods for
     transforming both numpy array and batched torch tensors.
     """