I'm running the torchvision==0.17.1 specified in the requirements.txt document but that seems to be missing a required attribute. Is there another version of tourch/tourchvision that I should be targeting?
Traceback (most recent call last):
File "train_realfill.py", line 955, in
main(args)
File "train_realfill.py", line 695, in main
train_dataset = RealFillDataset(
File "train_realfill.py", line 449, in init
transforms_v2.ToImageTensor(),
AttributeError: module 'torchvision.transforms.v2' has no attribute 'ToImageTensor'
Hi @thrakazog , due to some breaking changes of pytorch. Either you change the code to transforms_v2.PILToTensor() like @dae-sun said or try the old environment setup that I just updated
I'm running the torchvision==0.17.1 specified in the requirements.txt document but that seems to be missing a required attribute. Is there another version of tourch/tourchvision that I should be targeting?
Traceback (most recent call last): File "train_realfill.py", line 955, in
main(args)
File "train_realfill.py", line 695, in main
train_dataset = RealFillDataset(
File "train_realfill.py", line 449, in init
transforms_v2.ToImageTensor(),
AttributeError: module 'torchvision.transforms.v2' has no attribute 'ToImageTensor'