amd@amd-MS-7B33:/media/amd/balsl/RVC/RVC$ export ROCM_PATH=/opt/rocm amd@amd-MS-7B33:/media/amd/balsl/RVC/RVC$ export HSA_OVERRIDE_GFX_VERSION=10.3.0 amd@amd-MS-7B33:/media/amd/balsl/RVC/RVC$ python web.py 2024-07-26 01:50:59.173740: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. 2024-07-26 01:51:06 | INFO | configs.config | Found GPU AMD Radeon RX 6600 2024-07-26 01:51:06 | INFO | configs.config | Half-precision floating-point: True, device: cuda:0 2024-07-26 01:51:08 | INFO | httpx | HTTP Request: GET https://api.gradio.app/gradio-messaging/en "HTTP/1.1 200 OK" 2024-07-26 01:51:08 | INFO | infer.lib.rvcmd | checking hubret & rmvpe... 2024-07-26 01:51:16 | INFO | infer.lib.rvcmd | checking pretrained models... 2024-07-26 01:51:27 | INFO | infer.lib.rvcmd | checking pretrained models v2... 2024-07-26 01:51:42 | INFO | infer.lib.rvcmd | checking uvr5_weights... 2024-07-26 01:51:47 | INFO | infer.lib.rvcmd | all assets are already latest. 2024-07-26 01:51:47 | INFO | __main__ | Language: en_US 2024-07-26 01:52:14 | INFO | __main__ | Use gpus: 0 2024-07-26 01:52:14 | INFO | __main__ | Execute: "/usr/bin/python" infer/modules/train/train.py -e "Huohuo" -sr 40k -f0 1 -bs 6 -te 20 -se 5 -pg "assets/pretrained_v2/f0G40k.pth" -pd "assets/pretrained_v2/f0D40k.pth" -l 0 -c 0 -sw 1 -v v2 -a "Ecstatify" -g "0" 2024-07-26 01:52:16.025610: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. DEBUG:tensorflow:Falling back to TensorFlow client; we recommended you install the Cloud TPU client directly with pip install cloud-tpu-client. DEBUG:h5py._conv:Creating converter from 7 to 5 DEBUG:h5py._conv:Creating converter from 5 to 7 DEBUG:h5py._conv:Creating converter from 7 to 5 DEBUG:h5py._conv:Creating converter from 5 to 7 INFO:faiss.loader:Loading faiss with AVX2 support. INFO:faiss.loader:Successfully loaded faiss with AVX2 support. 2024-07-26 01:52:24.961641: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. DEBUG:tensorflow:Falling back to TensorFlow client; we recommended you install the Cloud TPU client directly with pip install cloud-tpu-client. DEBUG:h5py._conv:Creating converter from 7 to 5 DEBUG:h5py._conv:Creating converter from 5 to 7 DEBUG:h5py._conv:Creating converter from 7 to 5 DEBUG:h5py._conv:Creating converter from 5 to 7 INFO:faiss.loader:Loading faiss with AVX2 support. INFO:faiss.loader:Successfully loaded faiss with AVX2 support. INFO:Huohuo:{'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/Huohuo/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': 6, '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/Huohuo', 'experiment_dir': './logs/Huohuo', 'save_every_epoch': 5, 'name': 'Huohuo', 'total_epoch': 20, '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, 'author': 'Ecstatify'} /home/amd/.local/lib/python3.10/site-packages/torch/nn/utils/weight_norm.py:134: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`. WeightNorm.apply(module, name, dim) DEBUG:root:./logs/Huohuo/D_725.pth /media/amd/balsl/RVC/RVC/infer/lib/train/utils.py:74: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. checkpoint_dict = torch.load(checkpoint_path, map_location="cpu") INFO:root:Loaded model weights INFO:root:Loaded checkpoint './logs/Huohuo/D_725.pth' (epoch 5) INFO:Huohuo:loaded D DEBUG:root:./logs/Huohuo/G_725.pth INFO:root:Loaded model weights INFO:root:Loaded checkpoint './logs/Huohuo/G_725.pth' (epoch 5) /media/amd/balsl/RVC/RVC/infer/modules/train/train.py:273: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead. scaler = GradScaler(enabled=hps.train.fp16_run) 2024-07-26 01:52:52.781896: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. DEBUG:tensorflow:Falling back to TensorFlow client; we recommended you install the Cloud TPU client directly with pip install cloud-tpu-client. DEBUG:h5py._conv:Creating converter from 7 to 5 DEBUG:h5py._conv:Creating converter from 5 to 7 DEBUG:h5py._conv:Creating converter from 7 to 5 DEBUG:h5py._conv:Creating converter from 5 to 7 INFO:faiss.loader:Loading faiss with AVX2 support. INFO:faiss.loader:Successfully loaded faiss with AVX2 support. 2024-07-26 01:52:56.935360: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. DEBUG:tensorflow:Falling back to TensorFlow client; we recommended you install the Cloud TPU client directly with pip install cloud-tpu-client. DEBUG:h5py._conv:Creating converter from 7 to 5 DEBUG:h5py._conv:Creating converter from 5 to 7 DEBUG:h5py._conv:Creating converter from 7 to 5 DEBUG:h5py._conv:Creating converter from 5 to 7 INFO:faiss.loader:Loading faiss with AVX2 support. INFO:faiss.loader:Successfully loaded faiss with AVX2 support. 2024-07-26 01:53:01.105415: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. DEBUG:tensorflow:Falling back to TensorFlow client; we recommended you install the Cloud TPU client directly with pip install cloud-tpu-client. DEBUG:h5py._conv:Creating converter from 7 to 5 DEBUG:h5py._conv:Creating converter from 5 to 7 DEBUG:h5py._conv:Creating converter from 7 to 5 DEBUG:h5py._conv:Creating converter from 5 to 7 INFO:faiss.loader:Loading faiss with AVX2 support. INFO:faiss.loader:Successfully loaded faiss with AVX2 support. 2024-07-26 01:53:05.265279: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. DEBUG:tensorflow:Falling back to TensorFlow client; we recommended you install the Cloud TPU client directly with pip install cloud-tpu-client. DEBUG:h5py._conv:Creating converter from 7 to 5 DEBUG:h5py._conv:Creating converter from 5 to 7 DEBUG:h5py._conv:Creating converter from 7 to 5 DEBUG:h5py._conv:Creating converter from 5 to 7 INFO:faiss.loader:Loading faiss with AVX2 support. INFO:faiss.loader:Successfully loaded faiss with AVX2 support. /media/amd/balsl/RVC/RVC/infer/lib/train/data_utils.py:114: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. spec = torch.load(spec_filename) /media/amd/balsl/RVC/RVC/infer/lib/train/data_utils.py:114: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. spec = torch.load(spec_filename) /media/amd/balsl/RVC/RVC/infer/lib/train/data_utils.py:114: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. spec = torch.load(spec_filename) /media/amd/balsl/RVC/RVC/infer/lib/train/data_utils.py:114: FutureWarning: You are using `torch.load` with `weights_only=False` (the current default value), which uses the default pickle module implicitly. It is possible to construct malicious pickle data which will execute arbitrary code during unpickling (See https://github.com/pytorch/pytorch/blob/main/SECURITY.md#untrusted-models for more details). In a future release, the default value for `weights_only` will be flipped to `True`. This limits the functions that could be executed during unpickling. Arbitrary objects will no longer be allowed to be loaded via this mode unless they are explicitly allowlisted by the user via `torch.serialization.add_safe_globals`. We recommend you start setting `weights_only=True` for any use case where you don't have full control of the loaded file. Please open an issue on GitHub for any issues related to this experimental feature. spec = torch.load(spec_filename) /media/amd/balsl/RVC/RVC/infer/modules/train/train.py:450: FutureWarning: `torch.cuda.amp.autocast(args...)` is deprecated. Please use `torch.amp.autocast('cuda', args...)` instead. with autocast(enabled=hps.train.fp16_run): MIOpen Error: /long_pathname_so_that_rpms_can_package_the_debug_info/src/extlibs/MLOpen/src/lock_file.cpp:73: Error creating file for locking. Process Process-1: Traceback (most recent call last): File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/media/amd/balsl/RVC/RVC/infer/modules/train/train.py", line 278, in run train_and_evaluate( File "/media/amd/balsl/RVC/RVC/infer/modules/train/train.py", line 457, in train_and_evaluate ) = net_g(phone, phone_lengths, spec, spec_lengths, sid, pitch, pitchf) File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl return forward_call(*args, **kwargs) File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1636, in forward else self._run_ddp_forward(*inputs, **kwargs) File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1454, in _run_ddp_forward return self.module(*inputs, **kwargs) # type: ignore[index] File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl return forward_call(*args, **kwargs) File "/media/amd/balsl/RVC/RVC/rvc/layers/synthesizers.py", line 159, in forward m_p, logs_p, x_mask = self.enc_p(phone, pitch, phone_lengths) File "/media/amd/balsl/RVC/RVC/rvc/layers/encoders.py", line 128, in __call__ return super().__call__( File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl return forward_call(*args, **kwargs) File "/media/amd/balsl/RVC/RVC/rvc/layers/encoders.py", line 152, in forward x = self.encoder(x * x_mask, x_mask) File "/media/amd/balsl/RVC/RVC/rvc/layers/encoders.py", line 62, in __call__ return super().__call__(x, x_mask) File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl return forward_call(*args, **kwargs) File "/media/amd/balsl/RVC/RVC/rvc/layers/encoders.py", line 73, in forward y = attn(x, x, attn_mask) File "/media/amd/balsl/RVC/RVC/rvc/layers/attentions.py", line 69, in __call__ return super().__call__(x, c, attn_mask=attn_mask) File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl return forward_call(*args, **kwargs) File "/media/amd/balsl/RVC/RVC/rvc/layers/attentions.py", line 77, in forward q = self.conv_q(x) File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1553, in _wrapped_call_impl return self._call_impl(*args, **kwargs) File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1562, in _call_impl return forward_call(*args, **kwargs) File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 308, in forward return self._conv_forward(input, self.weight, self.bias) File "/home/amd/.local/lib/python3.10/site-packages/torch/nn/modules/conv.py", line 304, in _conv_forward return F.conv1d(input, weight, bias, self.stride, RuntimeError: miopenStatusUnknownError