search

PlayVoice / Grad-SVC

Diffusion Singing Voice Conversion based on Grad-TTS from HuaWei
https://huggingface.co/spaces/maxmax20160403/grad-svc
MIT License
123 stars 15 forks source link

Runtime error #6

Closed Desuka-art closed 11 months ago

Desuka-art commented 11 months ago

This is the error that I get when trying to do the "Training file debugging" step.

`Traceback (most recent call last): File "", line 1, in File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\spawn.py", line 122, in spawn_main exitcode = _main(fd, parent_sentinel) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\spawn.py", line 131, in _main prepare(preparation_data) File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\spawn.py", line 246, in prepare _fixup_main_from_path(data['init_main_from_path']) File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\spawn.py", line 297, in _fixup_main_from_path main_content = runpy.run_path(main_path, ^^^^^^^^^^^^^^^^^^^^^^^^^ File "", line 291, in run_path File "", line 98, in _run_module_code File "", line 88, in _run_code File "A:\GradSVC\Grad-SVC-20230925-V3-CFM\prepare\preprocess_zzz.py", line 19, in for batch in tqdm(loader): File "C:\Users\phill\AppData\Roaming\Python\Python311\site-packages\tqdm\std.py", line 1178, in iter for obj in iterable: File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\utils\data\dataloader.py", line 442, in iter return self._get_iterator() ^^^^^^^^^^^^^^^^^^^^ File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\utils\data\dataloader.py", line 388, in _get_iterator return _MultiProcessingDataLoaderIter(self) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\utils\data\dataloader.py", line 1043, in init w.start() File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\process.py", line 121, in start self._popen = self._Popen(self) ^^^^^^^^^^^^^^^^^ File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\context.py", line 224, in _Popen return _default_context.get_context().Process._Popen(process_obj) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\context.py", line 336, in _Popen return Popen(process_obj) ^^^^^^^^^^^^^^^^^^ File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\popen_spawn_win32.py", line 45, in init prep_data = spawn.get_preparation_data(process_obj._name) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\spawn.py", line 164, in get_preparation_data _check_not_importing_main() File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\spawn.py", line 140, in _check_not_importing_main raise RuntimeError(''' RuntimeError: An attempt has been made to start a new process before the current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.

    To fix this issue, refer to the "Safe importing of main module"
    section in https://docs.python.org/3/library/multiprocessing.html

0%| | 0/5 [00:05<?, ?it/s] Traceback (most recent call last): File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\utils\data\dataloader.py", line 1133, in _try_get_data data = self._data_queue.get(timeout=timeout) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\queues.py", line 114, in get raise Empty _queue.Empty

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "A:\GradSVC\Grad-SVC-20230925-V3-CFM\prepare\preprocess_zzz.py", line 19, in for batch in tqdm(loader): File "C:\Users\phill\AppData\Roaming\Python\Python311\site-packages\tqdm\std.py", line 1178, in iter for obj in iterable: File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\utils\data\dataloader.py", line 634, in next data = self._next_data() ^^^^^^^^^^^^^^^^^ File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\utils\data\dataloader.py", line 1329, in _next_data idx, data = self._get_data() ^^^^^^^^^^^^^^^^ File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\utils\data\dataloader.py", line 1295, in _get_data success, data = self._try_get_data() ^^^^^^^^^^^^^^^^^^^^ File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\utils\data\dataloader.py", line 1146, in _try_get_data raise RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly'.format(pids_str)) from e RuntimeError: DataLoader worker (pid(s) 14904) exited unexpectedly`

Please help!

MaxMax2016 commented 11 months ago

you can skip this step, I can't find the cause of the problem now.

Desuka-art commented 11 months ago

When I train, I get this big error, what did I do wrong?

Traceback (most recent call last): File "A:\GradSVC\Grad-SVC-20230925-V3-CFM\gvc_trainer.py", line 30, in train(hps, args.checkpoint_path) File "A:\GradSVC\Grad-SVC-20230925-V3-CFM\grad_extend\train.py", line 46, in train load_model(model, checkpoint['model']) File "A:\GradSVC\Grad-SVC-20230925-V3-CFM\grad_extend\utils.py", line 24, in load_model model.load_state_dict(new_state_dict) File "C:\Users\phill\AppData\Local\Programs\Python\Python311\Lib\site-packages\torch\nn\modules\module.py", line 2041, in load_state_dict raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for GradTTS: size mismatch for decoder.estimator.mlp.0.weight: copying a param with shape torch.Size([256, 64]) from checkpoint, the shape in current model is torch.Size([384, 96]). size mismatch for decoder.estimator.mlp.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.mlp.2.weight: copying a param with shape torch.Size([64, 256]) from checkpoint, the shape in current model is torch.Size([96, 384]). size mismatch for decoder.estimator.mlp.2.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.0.mlp.1.weight: copying a param with shape torch.Size([64, 64]) from checkpoint, the shape in current model is torch.Size([96, 96]). size mismatch for decoder.estimator.downs.0.0.mlp.1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.0.block1.block.0.weight: copying a param with shape torch.Size([64, 3, 3, 3]) from checkpoint, the shape in current model is torch.Size([96, 3, 3, 3]). size mismatch for decoder.estimator.downs.0.0.block1.block.0.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.0.block1.block.1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.0.block1.block.1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.0.block2.block.0.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([96, 96, 3, 3]). size mismatch for decoder.estimator.downs.0.0.block2.block.0.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.0.block2.block.1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.0.block2.block.1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.0.res_conv.weight: copying a param with shape torch.Size([64, 3, 1, 1]) from checkpoint, the shape in current model is torch.Size([96, 3, 1, 1]). size mismatch for decoder.estimator.downs.0.0.res_conv.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.1.mlp.1.weight: copying a param with shape torch.Size([64, 64]) from checkpoint, the shape in current model is torch.Size([96, 96]). size mismatch for decoder.estimator.downs.0.1.mlp.1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.1.block1.block.0.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([96, 96, 3, 3]). size mismatch for decoder.estimator.downs.0.1.block1.block.0.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.1.block1.block.1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.1.block1.block.1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.1.block2.block.0.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([96, 96, 3, 3]). size mismatch for decoder.estimator.downs.0.1.block2.block.0.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.1.block2.block.1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.1.block2.block.1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.2.fn.fn.to_qkv.weight: copying a param with shape torch.Size([384, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([384, 96, 1, 1]). size mismatch for decoder.estimator.downs.0.2.fn.fn.to_out.weight: copying a param with shape torch.Size([64, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([96, 128, 1, 1]). size mismatch for decoder.estimator.downs.0.2.fn.fn.to_out.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.0.3.conv.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([96, 96, 3, 3]). size mismatch for decoder.estimator.downs.0.3.conv.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.downs.1.0.mlp.1.weight: copying a param with shape torch.Size([128, 64]) from checkpoint, the shape in current model is torch.Size([192, 96]). size mismatch for decoder.estimator.downs.1.0.mlp.1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.0.block1.block.0.weight: copying a param with shape torch.Size([128, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([192, 96, 3, 3]). size mismatch for decoder.estimator.downs.1.0.block1.block.0.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.0.block1.block.1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.0.block1.block.1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.0.block2.block.0.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([192, 192, 3, 3]). size mismatch for decoder.estimator.downs.1.0.block2.block.0.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.0.block2.block.1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.0.block2.block.1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.0.res_conv.weight: copying a param with shape torch.Size([128, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([192, 96, 1, 1]). size mismatch for decoder.estimator.downs.1.0.res_conv.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.1.mlp.1.weight: copying a param with shape torch.Size([128, 64]) from checkpoint, the shape in current model is torch.Size([192, 96]). size mismatch for decoder.estimator.downs.1.1.mlp.1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.1.block1.block.0.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([192, 192, 3, 3]). size mismatch for decoder.estimator.downs.1.1.block1.block.0.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.1.block1.block.1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.1.block1.block.1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.1.block2.block.0.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([192, 192, 3, 3]). size mismatch for decoder.estimator.downs.1.1.block2.block.0.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.1.block2.block.1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.1.block2.block.1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.2.fn.fn.to_qkv.weight: copying a param with shape torch.Size([384, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([384, 192, 1, 1]). size mismatch for decoder.estimator.downs.1.2.fn.fn.to_out.weight: copying a param with shape torch.Size([128, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([192, 128, 1, 1]). size mismatch for decoder.estimator.downs.1.2.fn.fn.to_out.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.1.3.conv.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([192, 192, 3, 3]). size mismatch for decoder.estimator.downs.1.3.conv.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.downs.2.0.mlp.1.weight: copying a param with shape torch.Size([256, 64]) from checkpoint, the shape in current model is torch.Size([384, 96]). size mismatch for decoder.estimator.downs.2.0.mlp.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.downs.2.0.block1.block.0.weight: copying a param with shape torch.Size([256, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([384, 192, 3, 3]). size mismatch for decoder.estimator.downs.2.0.block1.block.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.downs.2.0.block1.block.1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.downs.2.0.block1.block.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.downs.2.0.block2.block.0.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([384, 384, 3, 3]). size mismatch for decoder.estimator.downs.2.0.block2.block.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.downs.2.0.block2.block.1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.downs.2.0.block2.block.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.downs.2.0.res_conv.weight: copying a param with shape torch.Size([256, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([384, 192, 1, 1]). size mismatch for decoder.estimator.downs.2.0.res_conv.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.downs.2.1.mlp.1.weight: copying a param with shape torch.Size([256, 64]) from checkpoint, the shape in current model is torch.Size([384, 96]). size mismatch for decoder.estimator.downs.2.1.mlp.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.downs.2.1.block1.block.0.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([384, 384, 3, 3]). size mismatch for decoder.estimator.downs.2.1.block1.block.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.downs.2.1.block1.block.1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.downs.2.1.block1.block.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.downs.2.1.block2.block.0.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([384, 384, 3, 3]). size mismatch for decoder.estimator.downs.2.1.block2.block.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.downs.2.1.block2.block.1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.downs.2.1.block2.block.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.downs.2.2.fn.fn.to_qkv.weight: copying a param with shape torch.Size([384, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([384, 384, 1, 1]). size mismatch for decoder.estimator.downs.2.2.fn.fn.to_out.weight: copying a param with shape torch.Size([256, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([384, 128, 1, 1]). size mismatch for decoder.estimator.downs.2.2.fn.fn.to_out.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.ups.0.0.mlp.1.weight: copying a param with shape torch.Size([128, 64]) from checkpoint, the shape in current model is torch.Size([192, 96]). size mismatch for decoder.estimator.ups.0.0.mlp.1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.0.block1.block.0.weight: copying a param with shape torch.Size([128, 512, 3, 3]) from checkpoint, the shape in current model is torch.Size([192, 768, 3, 3]). size mismatch for decoder.estimator.ups.0.0.block1.block.0.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.0.block1.block.1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.0.block1.block.1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.0.block2.block.0.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([192, 192, 3, 3]). size mismatch for decoder.estimator.ups.0.0.block2.block.0.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.0.block2.block.1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.0.block2.block.1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.0.res_conv.weight: copying a param with shape torch.Size([128, 512, 1, 1]) from checkpoint, the shape in current model is torch.Size([192, 768, 1, 1]). size mismatch for decoder.estimator.ups.0.0.res_conv.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.1.mlp.1.weight: copying a param with shape torch.Size([128, 64]) from checkpoint, the shape in current model is torch.Size([192, 96]). size mismatch for decoder.estimator.ups.0.1.mlp.1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.1.block1.block.0.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([192, 192, 3, 3]). size mismatch for decoder.estimator.ups.0.1.block1.block.0.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.1.block1.block.1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.1.block1.block.1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.1.block2.block.0.weight: copying a param with shape torch.Size([128, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([192, 192, 3, 3]). size mismatch for decoder.estimator.ups.0.1.block2.block.0.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.1.block2.block.1.weight: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.1.block2.block.1.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.2.fn.fn.to_qkv.weight: copying a param with shape torch.Size([384, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([384, 192, 1, 1]). size mismatch for decoder.estimator.ups.0.2.fn.fn.to_out.weight: copying a param with shape torch.Size([128, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([192, 128, 1, 1]). size mismatch for decoder.estimator.ups.0.2.fn.fn.to_out.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.0.3.conv.weight: copying a param with shape torch.Size([128, 128, 4, 4]) from checkpoint, the shape in current model is torch.Size([192, 192, 4, 4]). size mismatch for decoder.estimator.ups.0.3.conv.bias: copying a param with shape torch.Size([128]) from checkpoint, the shape in current model is torch.Size([192]). size mismatch for decoder.estimator.ups.1.0.mlp.1.weight: copying a param with shape torch.Size([64, 64]) from checkpoint, the shape in current model is torch.Size([96, 96]). size mismatch for decoder.estimator.ups.1.0.mlp.1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.0.block1.block.0.weight: copying a param with shape torch.Size([64, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([96, 384, 3, 3]). size mismatch for decoder.estimator.ups.1.0.block1.block.0.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.0.block1.block.1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.0.block1.block.1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.0.block2.block.0.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([96, 96, 3, 3]). size mismatch for decoder.estimator.ups.1.0.block2.block.0.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.0.block2.block.1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.0.block2.block.1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.0.res_conv.weight: copying a param with shape torch.Size([64, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([96, 384, 1, 1]). size mismatch for decoder.estimator.ups.1.0.res_conv.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.1.mlp.1.weight: copying a param with shape torch.Size([64, 64]) from checkpoint, the shape in current model is torch.Size([96, 96]). size mismatch for decoder.estimator.ups.1.1.mlp.1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.1.block1.block.0.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([96, 96, 3, 3]). size mismatch for decoder.estimator.ups.1.1.block1.block.0.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.1.block1.block.1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.1.block1.block.1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.1.block2.block.0.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([96, 96, 3, 3]). size mismatch for decoder.estimator.ups.1.1.block2.block.0.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.1.block2.block.1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.1.block2.block.1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.2.fn.fn.to_qkv.weight: copying a param with shape torch.Size([384, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([384, 96, 1, 1]). size mismatch for decoder.estimator.ups.1.2.fn.fn.to_out.weight: copying a param with shape torch.Size([64, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([96, 128, 1, 1]). size mismatch for decoder.estimator.ups.1.2.fn.fn.to_out.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.ups.1.3.conv.weight: copying a param with shape torch.Size([64, 64, 4, 4]) from checkpoint, the shape in current model is torch.Size([96, 96, 4, 4]). size mismatch for decoder.estimator.ups.1.3.conv.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.mid_block1.mlp.1.weight: copying a param with shape torch.Size([256, 64]) from checkpoint, the shape in current model is torch.Size([384, 96]). size mismatch for decoder.estimator.mid_block1.mlp.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.mid_block1.block1.block.0.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([384, 384, 3, 3]). size mismatch for decoder.estimator.mid_block1.block1.block.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.mid_block1.block1.block.1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.mid_block1.block1.block.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.mid_block1.block2.block.0.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([384, 384, 3, 3]). size mismatch for decoder.estimator.mid_block1.block2.block.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.mid_block1.block2.block.1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.mid_block1.block2.block.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.mid_attn.fn.fn.to_qkv.weight: copying a param with shape torch.Size([384, 256, 1, 1]) from checkpoint, the shape in current model is torch.Size([384, 384, 1, 1]). size mismatch for decoder.estimator.mid_attn.fn.fn.to_out.weight: copying a param with shape torch.Size([256, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([384, 128, 1, 1]). size mismatch for decoder.estimator.mid_attn.fn.fn.to_out.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.mid_block2.mlp.1.weight: copying a param with shape torch.Size([256, 64]) from checkpoint, the shape in current model is torch.Size([384, 96]). size mismatch for decoder.estimator.mid_block2.mlp.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.mid_block2.block1.block.0.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([384, 384, 3, 3]). size mismatch for decoder.estimator.mid_block2.block1.block.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.mid_block2.block1.block.1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.mid_block2.block1.block.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.mid_block2.block2.block.0.weight: copying a param with shape torch.Size([256, 256, 3, 3]) from checkpoint, the shape in current model is torch.Size([384, 384, 3, 3]). size mismatch for decoder.estimator.mid_block2.block2.block.0.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.mid_block2.block2.block.1.weight: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.mid_block2.block2.block.1.bias: copying a param with shape torch.Size([256]) from checkpoint, the shape in current model is torch.Size([384]). size mismatch for decoder.estimator.final_block.block.0.weight: copying a param with shape torch.Size([64, 64, 3, 3]) from checkpoint, the shape in current model is torch.Size([96, 96, 3, 3]). size mismatch for decoder.estimator.final_block.block.0.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.final_block.block.1.weight: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.final_block.block.1.bias: copying a param with shape torch.Size([64]) from checkpoint, the shape in current model is torch.Size([96]). size mismatch for decoder.estimator.final_conv.weight: copying a param with shape torch.Size([1, 64, 1, 1]) from checkpoint, the shape in current model is torch.Size([1, 96, 1, 1]).

MaxMax2016 commented 11 months ago

use this code: https://github.com/PlayVoice/Grad-SVC/tree/20230920-V2-96 and this pretrain https://github.com/PlayVoice/Grad-SVC/releases/tag/20230920