Something wrong in train.py line 396 "wav_spec = val_data.inverse_spec(gs[:, :, :, :mel_len[0]].detach(), stft)"

[Zhengyan-Sheng]

Traceback (most recent call last):
File "train.py", line 479, in
train_net(args)
File "train.py", line 122, in train_net
_ = validate(v_front, gen, post, fast_validate=True)
File "train.py", line 396, in validate
wav_spec = val_data.inverse_spec(gs[:, :, :, :mel_len[0]].detach(), stft)
File "XXXX/vid_aud_grid.py", line 216, in inverse_spec
wav = griffin_lim(spec.squeeze(1), stft.stft_fn, 60).squeeze(1) # B,L
File "XXXX/audio_processing.py", line 63, in griffin_lim
signal = stft_fn.inverse(magnitudes, angles).squeeze(1)
File "XXXX/Visual-Context-Attentional-GAN/src/data/stft.py", line 108, in inverse
padding=0)
RuntimeError: Given transposed=1, weight of size [1026, 1, 1024], expected input[44, 642, 298] to have 1026 channels, but got 642 channels instead

[ms-dot-k]

I have changed the src.data.vid_aud_grid.py.
There was a mismatch between hyperparameters.