Merge pull request #5 from eltociear/patch-1

Update video_utils.py

data/video_utils.py

@@ -52,7 +52,7 @@ def uniform_crop(images, size, spatial_idx, boxes=None, scale_size=None):
             crop if height is larger than width.
         boxes (ndarray or None): optional. Corresponding boxes to images.
             Dimension is `num boxes` x 4.
-        scale_size (int): optinal. If not None, resize the images to scale_size before
+        scale_size (int): optional. If not None, resize the images to scale_size before
             performing any crop.
     Returns:
         cropped (tensor): images with dimension of
@@ -201,4 +201,4 @@ def load_and_transform_video_data(
 if __name__ == '__main__':
     video_path = "datasets/InstructionTuning/video/music_aqa/MUSIC-AVQA-videos-Real/00000002.mp4"
     video, audio = load_and_transform_video_data(video_path, video_path, clip_duration=1, clips_per_video=5, with_audio=True)
-    import pdb;pdb.set_trace()
+    import pdb;pdb.set_trace()