Shift-Net_pytorch
Shift-Net_pytorch copied to clipboard
Error in training
Hello, when I try to train I get this error ...
[Errno 99] Cannot assign requested address on_close() takes 1 positional argument but 3 were given
How can a solve it ? Thanks
try your display_id=0
to disable the visualization during training. Maybe it is the incompatibility of visdom?
Thanks, now it works but when I finish the training I can't see the results by entering the URL.
try display_port=9001
, if it still occurs an error, post the error message here.
Hi, I made the change you suggested in options/train_options.py but it keeps sending me to address 8097.
Hello, I'm still waiting for your help
Are you sure when you change https://github.com/Zhaoyi-Yan/Shift-Net_pytorch/blob/master/options/train_options.py#L12 to something like 9001
, it still sends you address 8097 even if your running script does not contains display_port
item?
Yes, I changed the port number and retrained the code but it still appears that port number 8097 is not found.
Hi again, I retrained the code and I still can't see the results, I get the following message in the training ...
Could not connect to Visdom server. Trying to start a server.... Command: /usr/bin/python3 -m visdom.server -p 8097 &>/dev/null & create web directory ./log/exp/web... [Errno 99] Cannot assign requested address
Maybe you are running the code on a server which contains no screens, you may try https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix , and ask for help there.