https://huggingface.co/docs/diffusers/training/lora
I am trying to use this code to lora train,My simplified code goes like this:
accelerate launch --mixed_precision="fp16" examples/text_to_image/train_text_to_image_lora.py --pretrained_model_name_or_path=D:\PyCharm2022.1.3\PycharmProject\diffusers_txt_
images\modle_clone\Realistic_Vision_V1.4 --dataset_name="lambdalabs/pokemon-blip-captions" --dataloader_num_workers=8 --resolution=512 --center_crop --random_flip --train_batch_size=1 --gradient_accumulation_steps=4 --max_train_step
s=15000 --learning_rate=1e-04 --max_grad_norm=1 --lr_scheduler="cosine" --lr_warmup_steps=0 --output_dir="ddpm-ema-pokemon-64" --checkpointing_steps=2000 --validation_prompt="Dialogue." --seed=1337
However it gives error:
dataloader_iter = super().__iter__()
File "D:\PyCharm2022.1.3\PycharmProject\mydiffusers\venv\lib\site-packages\torch\utils\data\dataloader.py", line 441, in __iter__
return self._get_iterator()
File "D:\PyCharm2022.1.3\PycharmProject\mydiffusers\venv\lib\site-packages\torch\utils\data\dataloader.py", line 388, in _get_iterator
return _MultiProcessingDataLoaderIter(self)
File "D:\PyCharm2022.1.3\PycharmProject\mydiffusers\venv\lib\site-packages\torch\utils\data\dataloader.py", line 1042, in __init__
w.start()
File "D:\python\Python38\lib\multiprocessing\process.py", line 121, in start
self._popen = self._Popen(self)
File "D:\python\Python38\lib\multiprocessing\context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "D:\python\Python38\lib\multiprocessing\context.py", line 327, in _Popen
return Popen(process_obj)
File "D:\python\Python38\lib\multiprocessing\popen_spawn_win32.py", line 93, in __init__
reduction.dump(process_obj, to_child)
File "D:\python\Python38\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'main.<locals>.preprocess_train'
I appreciate any solution or insight to this problem. Thanks!
