Failed to establish a new connection:[Errno 111] connection refused training GP-GAN(Pytorch)

旧城等待， 2022-02-15 06:37 4931阅读 0赞

reference :[https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/38][https_github.com_junyanz_pytorch-CycleGAN-and-pix2pix_issues_38]

[Failed to establish a new connection:\[Errno 111\] connection refused \#129][Failed to establish a new connection_Errno 111_ connection refused_129]

requests.exceptions.ConnectionError: HTTPConnectionPool(host='localhost', port=8889): Max retries exceeded with url: /env/main (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7f1ca74fb208>: Failed to establish a new connection: \[Errno 111\] Connection refused',)). Basically, visdom error. It seems visdom error is from bug.

python -m visdom.server

The `visdom` display functionality is turned on by default. To avoid the extra overhead of communicating with `visdom` set `--display_id 0`.

If you want to use the visdom server, you should change the display\_id to a non-zero value. To view training results and loss plots, run `python -m visdom.server` and click the URL [http://localhost:8097][http_localhost_8097].

**added "--display\_id 0" running train.py but I still get this error**

**example****: when I training GP-GAN**

# (Paper: GP-GAN: Gender-Preserving-GAN-for-Synthesizing-Faces-from-Landmarks ) #

# (source code: [https://github.com/DetionDX/GP-GAN-GenderPreserving-GAN-for-Synthesizing-Faces-from-Landmarks][https_github.com_DetionDX_GP-GAN-GenderPreserving-GAN-for-Synthesizing-Faces-from-Landmarks]) #

(training command: python train.py --dataroot ./datasets/lfw/ --which\_direction BtoA --fineSize 64 --loadSize 64 --no\_flip --name lfw\_gpgan)

When I alone run the training command there is a error : Failed to establish a new connection:\[Errno 111\] connection refused

So I modified the command by adding **"--display\_id 0" in end of previouse training command that result in it become:****　** python train.py --dataroot ./datasets/lfw/ --which\_direction BtoA --fineSize 64 --loadSize 64 --no\_flip --name lfw\_gpgan　**--display\_id 0**

**It run successfully**

**However, if you results are not so good that you are satisfied you can continue training**

**Adding** **"--continue"** in the end of the training command like this:

python train.py --dataroot ./datasets/lfw/ --which\_direction BtoA --fineSize 64 --loadSize 64 --no\_flip --name lfw\_gpgan **--continue**

[https_github.com_junyanz_pytorch-CycleGAN-and-pix2pix_issues_38]: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/38
[Failed to establish a new connection_Errno 111_ connection refused_129]: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/129
[http_localhost_8097]: http://localhost:8097/
[https_github.com_DetionDX_GP-GAN-GenderPreserving-GAN-for-Synthesizing-Faces-from-Landmarks]: https://github.com/DetionDX/GP-GAN-GenderPreserving-GAN-for-Synthesizing-Faces-from-Landmarks