Hi, I am trying to train a module (https://github.com/AceCoooool/DSS-pytorch) which is based on pytorch. I follow all those instructions including installing pytorch (pip3 install --no-cache-dir torchvision). However, when I try to start training I get this error:
Traceback (most recent call last):
File “main.py”, line 86, in
main(config)
File “main.py”, line 10, in main
num_thread=config.num_thread)
File “/Users/kyle/Documents/MATLAB/DSS-py/dataset.py”, line 34, in get_loader
transform = transforms.zenCompose([
AttributeError: module ‘torchvision.transforms’ has no attribute ‘zenCompose’
I’ve googled it and it is said to be caused by collision between versions. However, the error still exists after I uninstall torch & pytorch for several times. I have no idea what to do now and I am completely new to pytorch. Anyone know what could be the solution?