ValueError: too many values to unpack (expected 3)
the-praxs opened this issue · comments
While running the main.py file for visual model training, there is an error regarding the unpacking of the frames array. On printing the shape of the frames array, there are 4 values in the tuple rather than 3. I am passing the LRW directory (with .mp4 and .txt files) as a value to the argument --annotation-direc. Kindly help asap!
Hi, the sequence of mouth ROIs (before cropping) is saved with grayscale video. data
should have a shape of (T, H, W), where T is the amount of frames. H and W denote the height and width, respectively. Can you print the filename self.list[idx][0]
at dataset.py#L109 and data
at dataset.py#L115 to target the problematic file and check its shape?
Hi, I did not use the --convert-grayscale option hence this issue had arisen. The issue is resolved now. Thank you so much for your help!
Hey,can you tell how to use the --convert-grayscale option
Hello @rohith-crypto you can pass the argument --convert-grayscale
to the command line when running crop_mouth_from_video.py. Please check an example at preprocessing/README.md
Hi, I did not use the --convert-grayscale option hence this issue had arisen. The issue is resolved now. Thank you so much for your help!
please can you show as how you are solve in code ?