search

NVIDIA / flowtron

Flowtron is an auto-regressive flow-based generative network for text to speech synthesis with control over speech variation and style transfer
https://nv-adlr.github.io/Flowtron
Apache License 2.0
887 stars 177 forks source link

ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 512, 1]) #136

Open azman-i opened 2 years ago

azman-i commented 2 years ago

I got this error after running python train.py -c config.json -p train_config.output_directory=outdir data_config.use_attn_prior=1. Don't know how to solve this.Is there anyone who faced this problem before? raceback (most recent call last): File "train.py", line 415, in <module> train(n_gpus, rank, **train_config) File "train.py", line 294, in train attn_logprob, mean, log_var, prob) = model( File "/home/azman/miniconda3/envs/ming_tts/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/azman/codes/flowtron/flowtron/flowtron.py", line 818, in forward text = self.encoder(text, in_lens) File "/home/azman/miniconda3/envs/ming_tts/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/azman/codes/flowtron/flowtron/flowtron.py", line 436, in forward F.relu(conv(curr_x)), File "/home/azman/miniconda3/envs/ming_tts/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/azman/miniconda3/envs/ming_tts/lib/python3.8/site-packages/torch/nn/modules/container.py", line 117, in forward input = module(input) File "/home/azman/miniconda3/envs/ming_tts/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/azman/miniconda3/envs/ming_tts/lib/python3.8/site-packages/torch/nn/modules/instancenorm.py", line 55, in forward return F.instance_norm( File "/home/azman/miniconda3/envs/ming_tts/lib/python3.8/site-packages/torch/nn/functional.py", line 2077, in instance_norm _verify_batch_size(input.size()) File "/home/azman/miniconda3/envs/ming_tts/lib/python3.8/site-packages/torch/nn/functional.py", line 2037, 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])