AttributeError: Can't pickle local object 'train.<locals>.<lambda>'
Opened this issue · 1 comments
D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\python.exe train.py --config configs/gnt_llff.txt --train_scenes fern --eval_scenes fern
Setting up [LPIPS] perceptual loss: trunk [alex], v[0.1], spatial [off]
D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\site-packages\torchvision\models_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' in
stead.
warnings.warn(
D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\site-packages\torchvision\models_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in th
e future. The current behavior is equivalent to passing weights=AlexNet_Weights.IMAGENET1K_V1. You can also use weights=AlexNet_Weights.DEFAULT to get the most up-to-date weights.
warnings.warn(msg)
Loading model from: D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\site-packages\lpips\weights\v0.1\alex.pth
Setting up [LPIPS] perceptual loss: trunk [vgg], v[0.1], spatial [off]
D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\site-packages\torchvision\models_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in th
e future. The current behavior is equivalent to passing weights=VGG16_Weights.IMAGENET1K_V1. You can also use weights=VGG16_Weights.DEFAULT to get the most up-to-date weights.
warnings.warn(msg)
Loading model from: D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\site-packages\lpips\weights\v0.1\vgg.pth
outputs will be saved to ./out\gnt_llff
training dataset: llff_test
loading ['fern'] for train
loading ['fern'] for validation
No ckpts found, training from scratch...
Traceback (most recent call last):
File "D:\code\3D_Reconstruction\GNT\train.py", line 319, in
train(args)
File "D:\code\3D_Reconstruction\GNT\train.py", line 97, in train
for train_data in train_loader:
File "D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\utils\data\dataloader.py", line 441, in iter
return self._get_iterator()
File "D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\utils\data\dataloader.py", line 388, in _get_iterator
return _MultiProcessingDataLoaderIter(self)
File "D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\site-packages\torch\utils\data\dataloader.py", line 1042, in init
w.start()
File "D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\multiprocessing\process.py", line 121, in start
self._popen = self._Popen(self)
File "D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\multiprocessing\context.py", line 224, in _Popen
return _default_context.get_context().Process._Popen(process_obj)
File "D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\multiprocessing\context.py", line 327, in _Popen
return Popen(process_obj)
File "D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\multiprocessing\popen_spawn_win32.py", line 93, in init
reduction.dump(process_obj, to_child)
File "D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\multiprocessing\reduction.py", line 60, in dump
ForkingPickler(file, protocol).dump(obj)
AttributeError: Can't pickle local object 'train..'
PS D:\code\3D_Reconstruction\GNT> Setting up [LPIPS] perceptual loss: trunk [alex], v[0.1], spatial [off]
D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\site-packages\torchvision\models_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' in
stead.
warnings.warn(
D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\site-packages\torchvision\models_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in th
e future. The current behavior is equivalent to passing weights=AlexNet_Weights.IMAGENET1K_V1. You can also use weights=AlexNet_Weights.DEFAULT to get the most up-to-date weights.
warnings.warn(msg)
Loading model from: D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\site-packages\lpips\weights\v0.1\alex.pth
Setting up [LPIPS] perceptual loss: trunk [vgg], v[0.1], spatial [off]
D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\site-packages\torchvision\models_utils.py:223: UserWarning: Arguments other than a weight enum or None for 'weights' are deprecated since 0.13 and may be removed in th
e future. The current behavior is equivalent to passing weights=VGG16_Weights.IMAGENET1K_V1. You can also use weights=VGG16_Weights.DEFAULT to get the most up-to-date weights.
warnings.warn(msg)
Loading model from: D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\site-packages\lpips\weights\v0.1\vgg.pth
Traceback (most recent call last):
File "", line 1, in
File "D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "D:\Users\gracejwang\AppData\Local\Programs\Python\Python39\lib\multiprocessing\spawn.py", line 126, in _main
self = reduction.pickle.load(from_parent)
EOFError: Ran out of input
set num_workers=0