Error while training the model on any data

[noamkatz]

hello all, im trying the get the model to train on the same data provided by the authors, I was able to recreate the results using the pre-trained weights and everything worked pretty much fine. I am using Windows and running tf on GPU. The output I am getting is as follows-

Exception in thread background: Traceback (most recent call last): File "C:\Users\admin\Documents\temp\lib\threading.py", line 917, in _bootstrap_inner self.run() File "C:\Users\admin\Documents\temp\lib\threading.py", line 865, in run self._target(*self._args, *self._kwargs) File "C:\Users\admin\Desktop\Lip2Wav-master\Lip2Wav-master\synthesizer\feeder.py", line 139, in _enqueue_next_train_group examples = [self._get_next_example() for i in range(n _batches_per_group)] File "C:\Users\admin\Desktop\Lip2Wav-master\Lip2Wav-master\synthesizer\feeder.py", line 139, in examples = [self._get_next_example() for i in range(n * _batches_per_group)] File "C:\Users\admin\Desktop\Lip2Wav-master\Lip2Wav-master\synthesizer\feeder.py", line 194, in _get_next_example input_data, mel_target = self.getitem() File "C:\Users\admin\Desktop\Lip2Wav-master\Lip2Wav-master\synthesizer\feeder.py", line 172, in getitem mel = np.load(os.path.join(os.path.dirname(img_name), 'mels.npz'))['spec'].T File "C:\Users\admin\Documents\temp\lib\site-packages\numpy\lib\npyio.py", line 416, in load fid = stack.enter_context(open(os_fspath(file), "rb")) FileNotFoundError: [Errno 2] No such file or directory: 'Dataset/chem//preprocessed/46\mels.npz'

The name of the files are numbers, so the "46" is pointing tawrds the directory where all the images are with the original .wav file. PLEASE HELP! I have been stuck on this issue for a week now:(

[prajwalkr]

Dataset/chem//preprocessed/46\mels.npz

The slashes are in the wrong direction for Windows.

[noamkatz]

Hi! thank you so much for your response! Unfortunatley, that was not the problem. I changed the slashes and could not make it to work. Furthermore, upuntil this point, I did not run into any issue with the slashes while infering the network. What I seem to be missing is the point in the code that CREATES the .npz files - they are not being created at all from merely running the train.py commend, so the issue should be somewhere in the creating the .npz and later on the .npy, right? Thanks for helping me out!

[prajwalkr]

Have you preprocessed your data? https://github.com/Rudrabha/Lip2Wav#preprocessing-the-dataset

[noamkatz]

sure, I get one directory named "preprocessed" with all the images in JPG and one .wav file made "audio", all ordered in directories for 30 seconds segments of the original video. If I run infering for that, there is no problem, I believed that this means that I did the preprocessing stage correctly. Am I suppose to get an .npz or .npy from preprocess.py?

[prajwalkr]

Am I suppose to get an .npz or .npy from preprocess.py?

Yes.

[noamkatz]

Got it! works perfectlly, thanks!