search

jaywalnut310 / vits

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
https://jaywalnut310.github.io/vits-demo/index.html
MIT License
6.53k stars 1.22k forks source link

RuntimeError: The expanded size of the tensor (8192) must match the existing size (448) at non-singleton dimension 1. Target sizes: [1, 8192]. Tensor sizes: [448] #77

Open zgfjzs opened 1 year ago

zgfjzs commented 1 year ago

I meet this question when it train to epoch 2 or epoch 4,I use dataset collocated by myself

INFO:baker_base:====> Epoch: 1 INFO:baker_base:====> Epoch: 2 Traceback (most recent call last): File "train.py", line 291, in main() File "train.py", line 47, in main mp.spawn(run, nprocs=n_gpus, args=(n_gpus, hps,)) File "D:\anaconda\anaconda1\envs\torch\lib\site-packages\torch\multiprocessing\spawn.py", line 240, in spawn return start_processes(fn, args, nprocs, join, daemon, start_method='spawn') File "D:\anaconda\anaconda1\envs\torch\lib\site-packages\torch\multiprocessing\spawn.py", line 198, in start_processes while not context.join(): File "D:\anaconda\anaconda1\envs\torch\lib\site-packages\torch\multiprocessing\spawn.py", line 160, in join raise ProcessRaisedException(msg, error_index, failed_process.pid) torch.multiprocessing.spawn.ProcessRaisedException:

-- Process 0 terminated with the following error: Traceback (most recent call last): File "D:\anaconda\anaconda1\envs\torch\lib\site-packages\torch\multiprocessing\spawn.py", line 69, in _wrap fn(i, args) File "D:\vits_chinese-Yae\train.py", line 116, in run train_and_evaluate(rank, epoch, hps, [net_g, net_d], [optim_g, optim_d], [scheduler_g, scheduler_d], scaler, [train_loader, eval_loader], logger, [writer, writer_eval]) File "D:\vits_chinese-Yae\train.py", line 164, in train_and_evaluate y = commons.slice_segments(y, ids_slice hps.data.hop_length, hps.train.segment_size) # slice File "D:\vits_chinese-Yae\commons.py", line 54, in slice_segments ret[i] = x[i, :, idx_str:idx_end] RuntimeError: The expanded size of the tensor (8192) must match the existing size (448) at non-singleton dimension 1. Target sizes: [1, 8192]. Tensor sizes: [448]