so-vits-svc
so-vits-svc copied to clipboard
innnky
训练报错
PS E:\so-vits-svc> E:\python\python3.8.10\python.exe .\train.py -c .\configs\config.json -m 32k
INFO:32k:{'train': {'log_interval': 200, 'eval_interval': 1000, 'seed': 1234, 'epochs': 10000, 'learning_rate': 0.0001, 'betas': [0.8, 0.99], 'eps': 1e-09, 'batch_size': 2, 'fp16_run': False, 'lr_decay': 0.999875, 'segment_size': 17920, 'init_lr_ratio': 1, 'warmup_epochs': 0, 'c_mel': 45, 'c_kl': 1.0, 'use_sr': True, 'max_speclen': 384, 'port': '8001'}, 'data': {'training_files': 'filelists/train.txt', 'validation_files': 'filelists/val.txt', 'max_wav_value': 32768.0, 'sampling_rate': 32000, 'filter_length': 1280, 'hop_length': 320, 'win_length': 1280, 'n_mel_channels': 80, 'mel_fmin': 0.0, 'mel_fmax': None}, 'model': {'inter_channels': 192, 'hidden_channels': 192, 'filter_channels': 768, 'n_heads': 2, 'n_layers': 6, 'kernel_size': 3, 'p_dropout': 0.1, 'resblock': '1', 'resblock_kernel_sizes': [3, 7, 11], 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'upsample_rates': [10, 8, 2, 2], 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'n_layers_q': 3, 'use_spectral_norm': False, 'gin_channels': 256, 'ssl_dim': 256, 'n_speakers': 6}, 'spk': {'astolfo': 0, 'liuchan': 1, 'xiaobangguo': 2}, 'model_dir': './logs\32k'}
INFO:torch.distributed.distributed_c10d:Added key: store_based_barrier_key:1 to store for rank: 0
INFO:torch.distributed.distributed_c10d:Rank 0: Completed store-based barrier for key:store_based_barrier_key:1 with 1 nodes.
./logs\32k\G_0.pth
INFO:torch.nn.parallel.distributed:Reducer buckets have been rebuilt in this iteration.
E:\python\python3.8.10\lib\site-packages\torch\autograd_init_.py:197: UserWarning: Grad strides do not match bucket view strides. This may indicate grad was not created according to the gradient layout contract, or that the param's strides changed since DDP was constructed. This is not an error, but may impair performance.
grad.sizes() = [64, 1, 4], strides() = [4, 1, 1]
bucket_view.sizes() = [64, 1, 4], strides() = [4, 4, 1] (Triggered internally at C:\actions-runner_work\pytorch\pytorch\builder\windows\pytorch\torch\csrc\distributed\c10d\reducer.cpp:339.)
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
Traceback (most recent call last):
File ".\train.py", line 281, in
-- Process 0 terminated with the following error: Traceback (most recent call last): File "E:\python\python3.8.10\lib\site-packages\torch\multiprocessing\spawn.py", line 69, in wrap fn(i, *args) File "E:\so-vits-svc\train.py", line 108, in run train_and_evaluate(rank, epoch, hps, [net_g, net_d], [optim_g, optim_d], [scheduler_g, scheduler_d], scaler, File "E:\so-vits-svc\train.py", line 187, in train_and_evaluate scaler.step(optim_g) File "E:\python\python3.8.10\lib\site-packages\torch\cuda\amp\grad_scaler.py", line 313, in step return optimizer.step(*args, **kwargs) File "E:\python\python3.8.10\lib\site-packages\torch\optim\lr_scheduler.py", line 68, in wrapper return wrapped(*args, **kwargs) File "E:\python\python3.8.10\lib\site-packages\torch\optim\optimizer.py", line 140, in wrapper out = func(*args, **kwargs) File "E:\python\python3.8.10\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context return func(*args, **kwargs) File "E:\python\python3.8.10\lib\site-packages\torch\optim\adamw.py", line 162, in step adamw(params_with_grad, File "E:\python\python3.8.10\lib\site-packages\torch\optim\adamw.py", line 219, in adamw func(params, File "E:\python\python3.8.10\lib\site-packages\torch\optim\adamw.py", line 273, in single_tensor_adamw exp_avg.mul(beta1).add(grad, alpha=1 - beta1) RuntimeError: The size of tensor a (4) must match the size of tensor b (6) at non-singleton dimension 0
