wav2lip_train.py Sync Loss An error is reported if the value is less than 0.75

[Ezrealz]

Traceback (most recent call last): File "wav2lip_train.py", line 372, in train(device, model, train_data_loader, test_data_loader, optimizer, File "wav2lip_train.py", line 223, in train sync_loss = get_sync_loss(mel, g) File "wav2lip_train.py", line 196, in get_sync_loss a, v = syncnet(mel, g) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/root/wav2lip_288x288/models/syncnetv2.py", line 63, in forward face_embedding = self.face_encoder(face_sequences) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/container.py", line 141, in forward input = module(input) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/root/wav2lip_288x288/models/conv2.py", line 17, in forward out = self.conv_block(x) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/container.py", line 141, in forward input = module(input) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl return forward_call(*input, **kwargs) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/batchnorm.py", line 168, in forward return F.batch_norm( File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/functional.py", line 2419, in batch_norm _verify_batch_size(input.size()) File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/functional.py", line 2387, in _verify_batch_size raise ValueError("Expected more than 1 value per channel when training, got input size {}".format(size)) ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 512, 1, 1])

[lbdave94]

hi @Ezrealz , did you solve it?