RVC-Project
RuntimeError: The expanded size of the tensor (17280) must match the existing size (16080) at non-singleton dimension 1.
训练过程报错并中断： Traceback (most recent call last): File "multiprocessing\process.py", line 315, in _bootstrap File "multiprocessing\process.py", line 108, in run File "E:\BaiduNetdiskDownload\RVC0813Nvidia\train_nsf_sim_cache_sid_load_pretrain.py", line 228, in run train_and_evaluate( File "E:\BaiduNetdiskDownload\RVC0813Nvidia\train_nsf_sim_cache_sid_load_pretrain.py", line 430, in train_and_evaluate wave = commons.slice_segments( File "E:\BaiduNetdiskDownload\RVC0813Nvidia\lib\infer_pack\commons.py", line 49, in slice_segments ret[i] = x[i, :, idx_str:idx_end] RuntimeError: The expanded size of the tensor (17280) must match the existing size (16080) at non-singleton dimension 1. Target sizes: [1, 17280]. Tensor sizes: [16080]
same problem. Managed to fix it? RuntimeError: The expanded size of the tensor (12800) must match the existing size (12400) at non-singleton dimension 1. Target sizes: [1, 12800]. Tensor sizes: [12400]
alright alright so turns out if you increase number of epoches and frequency it will work? i also only left one file in..it could of also been that idk
2024-07-23 01:05:48 | INFO | main | Use gpus: 0 2024-07-23 01:05:48 | INFO | main | Execute: "C:\Users\Bradley\Desktop\RVC normal\Retrieval-based-Voice-Conversion-WebUI\env\Scripts\python.exe" infer/modules/train/train.py -e "Kurisu4" -sr 40k -f0 1 -bs 12 -g 0 -te 250 -se 50 -pg assets/pretrained_v2/f0G40k.pth -pd assets/pretrained_v2/f0D40k.pth -l 0 -c 0 -sw 1 -v v2 INFO:Kurisu4:{'data': {'filter_length': 2048, 'hop_length': 400, 'max_wav_value': 32768.0, 'mel_fmax': None, 'mel_fmin': 0.0, 'n_mel_channels': 125, 'sampling_rate': 40000, 'win_length': 2048, 'training_files': './logs\Kurisu4/filelist.txt'}, 'model': {'filter_channels': 768, 'gin_channels': 256, 'hidden_channels': 192, 'inter_channels': 192, 'kernel_size': 3, 'n_heads': 2, 'n_layers': 6, 'p_dropout': 0, 'resblock': '1', 'resblock_dilation_sizes': [[1, 3, 5], [1, 3, 5], [1, 3, 5]], 'resblock_kernel_sizes': [3, 7, 11], 'spk_embed_dim': 109, 'upsample_initial_channel': 512, 'upsample_kernel_sizes': [16, 16, 4, 4], 'upsample_rates': [10, 10, 2, 2], 'use_spectral_norm': False}, 'train': {'batch_size': 12, 'betas': [0.8, 0.99], 'c_kl': 1.0, 'c_mel': 45, 'epochs': 20000, 'eps': 1e-09, 'fp16_run': False, 'init_lr_ratio': 1, 'learning_rate': 0.0001, 'log_interval': 200, 'lr_decay': 0.999875, 'seed': 1234, 'segment_size': 12800, 'warmup_epochs': 0}, 'model_dir': './logs\Kurisu4', 'experiment_dir': './logs\Kurisu4', 'save_every_epoch': 50, 'name': 'Kurisu4', 'total_epoch': 250, 'pretrainG': 'assets/pretrained_v2/f0G40k.pth', 'pretrainD': 'assets/pretrained_v2/f0D40k.pth', 'version': 'v2', 'gpus': '0', 'sample_rate': '40k', 'if_f0': 1, 'if_latest': 0, 'save_every_weights': '1', 'if_cache_data_in_gpu': 0} C:\Users\Bradley\Desktop\RVC normal\Retrieval-based-Voice-Conversion-WebUI\env\lib\site-packages\torch\nn\utils\weight_norm.py:28: UserWarning: torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm. warnings.warn("torch.nn.utils.weight_norm is deprecated in favor of torch.nn.utils.parametrizations.weight_norm.") DEBUG:infer.lib.infer_pack.models:gin_channels: 256, self.spk_embed_dim: 109 INFO:Kurisu4:loaded pretrained assets/pretrained_v2/f0G40k.pth INFO:Kurisu4:<All keys matched successfully> INFO:Kurisu4:loaded pretrained assets/pretrained_v2/f0D40k.pth INFO:Kurisu4:<All keys matched successfully> C:\Users\Bradley\Desktop\RVC normal\Retrieval-based-Voice-Conversion-WebUI\env\lib\site-packages\torch\autograd\graph.py:744: 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 ..\torch\csrc\distributed\c10d\reducer.cpp:339.) return Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass INFO:Kurisu4:Train Epoch: 1 [0%] INFO:Kurisu4:[0, 0.0001] INFO:Kurisu4:loss_disc=4.232, loss_gen=3.885, loss_fm=11.284,loss_mel=30.124, loss_kl=9.000 DEBUG:matplotlib:matplotlib data path: C:\Users\Bradley\Desktop\RVC normal\Retrieval-based-Voice-Conversion-WebUI\env\lib\site-packages\matplotlib\mpl-data DEBUG:matplotlib:CONFIGDIR=C:\Users\Bradley.matplotlib DEBUG:matplotlib:interactive is False DEBUG:matplotlib:platform is win32 INFO:Kurisu4:====> Epoch: 1 [2024-07-23 01:06:15] | (0:00:14.055517) INFO:Kurisu4:====> Epoch: 2 [2024-07-23 01:06:18] | (0:00:03.216181) INFO:Kurisu4:====> Epoch: 3 [2024-07-23 01:06:21] | (0:00:03.075652) INFO:Kurisu4:====> Epoch: 4 [2024-07-23 01:06:24] | (0:00:02.695316) INFO:Kurisu4:====> Epoch: 5 [2024-07-23 01:06:27] | (0:00:02.855017) etc i did this to 250
alright alright so turns out if you increase number of epoches and frequency it will work? i also only left one file in..it could of also been that idk
Same problem here, tho i dropped several files in and added some more later. Maybe that is causing the issue?
