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

旧城等待， 2022-02-15 06:37 5036阅读 0赞

reference //github.com/junyanz/pytorch-CycleGAN-and-pix2pix/issues/38

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(‘: 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.

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)

(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