hi i success to run all the code but i dont know why i got bad result of loss and accuracy. can you provide me the result that you got? thank you in advance
First, I use pip install to construct my new venv, and some designate version is not existed, so I install the lastest one instead .
and then I run "train.py", but it seems there is some thing wrong: ### train.py", line 184, in parser.add_argument("--npz_file",
......
argparse.ArgumentError: argument --npz_file: conflicting option string: --npz_file
I don't know how to fix it. Is about the version ?
Hi, I try to run your project, but when I print train_list in every epoch in python.py, only to find that all predicted labels become '3'--other gradually after at most three epoches. Can you tell me why and how to fix it.
The code you provided is very clear, but I would like to know if you have reproduced the results in the paper. If you do, how do you set the learning rate and the number of epoches?