Open zhangyahu1 opened 2 years ago
resize images to 256, because originally the video in 224x224 is loaded. For example, in frames_dataset.py:
video_array = video_array[frame_idx]
video_array = [resize(frame, self.frame_shape[:2])[..., :3] for frame in video_array]
@romanvey Thanks! I will try it.
Thanks for sharing the code! I meet a problem when training the model:
Running environment: Pytorch: 1.4 Python: 3.6