Closed Jxu-Thu closed 4 years ago
I find the warning as follows:
UserWarning: Detected call of lr_scheduler.step()
before optimizer.step()
. In PyTorch 1.1.0 and later, you should call them in the opposite order: optimizer.step()
before lr_scheduler.step()
. Failure to do this will result in PyTorch skipping the first value of the learning rate schedule.See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
So I suspect you use the pytorch version <1.1.0.
Indeed, for the experiments of the paper we were using PyTorch 1.0. We are currently in the process of restructuring the repo and will an updated requirements.txt then!
but when I change to pytorch==1.0.1 (torchvision==0.2.2) will find the error as follows:
from torchvision.datasets import VisionDataset ImportError: cannot import name 'VisionDataset'
the VisionDataset in repo requires torchvision>=0.3.0 and torch>=1.1.0
Maybe we should use pytorch >=1.1 ?
Thanks for your kind reply!
Can you provide the necessary info for building the environment? e.g. pytorch version