ValueError: too many values to unpack (expected 3)

[Pratyush Shukla]

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!

[Pingchuan Ma]

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?

[Pratyush Shukla]

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!

[rohith-crypto]

Hey,can you tell how to use the --convert-grayscale option

[Pingchuan Ma]

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

[SHAIIM04]

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 ?