TTyb
从`https://huggingface.co/IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Chinese-v0.1`和`https://github.com/IDEA-CCNL/Fengshenbang-LM`clone下来后： ``` git-lfs clone https://huggingface.co/IDEA-CCNL/Taiyi-Stable-Diffusion-1B-Chinese-v0.1 git clone https://github.com/IDEA-CCNL/Fengshenbang-LM ``` 进入文件夹调试： ``` cd /workspace/Fengshenbang-LM/fengshen/examples/finetune_taiyi_stable_diffusion ``` 由于路径下没有ckpt需要新建： ``` mkdir ckpt cp /workspace/Taiyi-Stable-Diffusion-1B-Chinese-v0.1/Taiyi-Stable-Diffusion-1B-Chinese-v0.1.ckpt ./ ``` 执行命令： ``` python finetune.py --model_path /workspace/Taiyi-Stable-Diffusion-1B-Chinese-v0.1 --datasets_path /workspace/Fengshenbang-LM/fengshen/examples/finetune_taiyi_stable_diffusion/demo_dataset/...
``` Traceback (most recent call last): File "finetune.py", line 194, in trainer.fit(model, datamoule, ckpt_path=args.load_ckpt_path) File "/opt/conda/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 696, in fit self._call_and_handle_interrupt( File "/opt/conda/lib/python3.8/site-packages/pytorch_lightning/trainer/trainer.py", line 650, in _call_and_handle_interrupt return trainer_fn(*args, **kwargs)...
请问测试的时候PaddlePaddle、PaddleSpeech、ppgan版本是多少，当前PaddlePaddle==2.5.0和PaddleSpeech、ppgan出现各种不兼容，光是安装就花费大量时间，如果能提供一个docker就更好了