search

Rudrabha / Lip2Wav

This is the repository containing codes for our CVPR, 2020 paper titled "Learning Individual Speaking Styles for Accurate Lip to Speech Synthesis"
MIT License
692 stars 152 forks source link

Encountered ValueError during training #14

Closed rita-zeng closed 4 years ago

rita-zeng commented 4 years ago

Hi! It's really a nice work! But I'm facing a problem while training: image When training train.py with the command: python train.py chem --data_root Dataset/chem/ --preset synthesizer/presets/chem.json, it occurs to the ValueError: 'Multi-valued hyperparameters cannot be empty: all_test_images.' I can't find the hyperparameter throughout the code that named 'all_test_images'. Am I Assigning the wrong values of 'name of run'? Is it a directory like '/Dataset/chem' or the random name that we gave such as 'chem'? I have tried the training with different 'name' values, such as 'chem', '/Dataset/chem' or '/Dataset/chem/preprocessed/', it didn't work, still report the same error. Looking forward to your answer! Thanks a lot!

prajwalkr commented 4 years ago

Hello

Can you please print the variable `all_test_images' and run your command and paste the printed output here?

I am suspecting that the data_root path specified is incorrect. That is, the script was unable to find test images. So, could you also do an ls inside the Dataset folder and the Dataset/chem folder and paste it here?

rita-zeng commented 4 years ago

Thanks for your reply! I'm afraid that the variable `all_test_images' is not defined in the code, it appeared out of the blue. image

The contents of Dataset and Dataset/chem are as below: image

prajwalkr commented 4 years ago

I'm afraid that the variable `all_test_images' is not defined in the code, it appeared out of the blue.

https://github.com/Rudrabha/Lip2Wav/blob/5247a82aef611059fb8c176422e8bbd64f5d0bef/train.py#L19

Please also verify if there are images in the subfolders of the preprocessed folder.

rita-zeng commented 4 years ago

Ohhh! I noticed that the code was downloaded in June 2nd, and now I have downloaded the latest version, there's no more question. Thanks for your patience again!!!