level 1
鸡你太美哦哦😄
楼主
扩散模型训练不了怎么办，我用的是Webui
我用gptsovits训练的时候出现了问题，扩散模型无法进行训练
2025-07-17 16:51:56.562 | INFO | __main__:<module>:51 - > Now model timesteps is 1000, and k_step_max is 1000
[lbk]*[rbk] restoring model from logs/44k/diffusion\网页链接
Traceback (most recent call last):
File "train_diff.py", line 55, in <module>
initial_global_step, model, optimizer = utils.load_model(args.env.expdir, model, optimizer, device=args.device)
File "C:\baidunetdiskdownload\So-VITS-SVC 4.1-Stable v2.3.18官方稳定版本\diffusion\logger\utils.py", line 124, in load_model
model.load_state_dict(ckpt[lbk]'model'[rbk], strict=False)
File "C:\baidunetdiskdownload\So-VITS-SVC 4.1-Stable v2.3.18官方稳定版本\workenv\lib\site-packages\torch\nn\modules\module.py", line 1671, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for Unit2Mel:
size mismatch for unit_embed.weight: copying a param with shape torch.Size([lbk]256, 768[rbk]) from checkpoint, the shape in current model is torch.Size([lbk]256, 256[rbk]).
2025年07月17日 09点07分
1
我用gptsovits训练的时候出现了问题，扩散模型无法进行训练
2025-07-17 16:51:56.562 | INFO | __main__:<module>:51 - > Now model timesteps is 1000, and k_step_max is 1000
[lbk]*[rbk] restoring model from logs/44k/diffusion\网页链接
Traceback (most recent call last):
File "train_diff.py", line 55, in <module>
initial_global_step, model, optimizer = utils.load_model(args.env.expdir, model, optimizer, device=args.device)
File "C:\baidunetdiskdownload\So-VITS-SVC 4.1-Stable v2.3.18官方稳定版本\diffusion\logger\utils.py", line 124, in load_model
model.load_state_dict(ckpt[lbk]'model'[rbk], strict=False)
File "C:\baidunetdiskdownload\So-VITS-SVC 4.1-Stable v2.3.18官方稳定版本\workenv\lib\site-packages\torch\nn\modules\module.py", line 1671, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for Unit2Mel:
size mismatch for unit_embed.weight: copying a param with shape torch.Size([lbk]256, 768[rbk]) from checkpoint, the shape in current model is torch.Size([lbk]256, 256[rbk]).