edge-connect

edge-connect copied to clipboard

Hi Thanks for your contribution! I am trying the use edge-connect on my dataset. The results is not good so far. The example results look good. I change the example...

ghost

hi! Because in other issues, you said that use hinge loss will improve. But when i change to hinge in config.yml. I see in Generator， it will produce negative adv...

2018hello

Canny sigma

1

sigma=0 and sigma=-1 ,recommend which one？If anyone can tell the differents , I would appreciate it!

1997Jessie

Replace outdated python modules with latest versions and resolved some minor issues

1

codevisioner

When training the edge network, I've seen generator and discriminator losses stay high, with generator losses reaching 100. Does anyone know why that is? Thank you very much!

TT-mouse

This PR exports models as `ONNX` files. It it possible to optimize those models using https://pypi.org/project/onnxoptimizer/ as: ``` onnxoptimizer input-model.onnx optimized-model.onnx ```

Luni-4

This PR fixes test function

Luni-4

About precision and recall during training

1

When I am training model = 1, these two values are always 1, is this correct?Which loss in the logs_edge.dat file should you pay more attention to when training model...

Ghost0405

Hello, I ran into this issue today while trying to train the Inpainting model and the Joint Model on Google Colab with a GPU. I was able to train the...

kaelyavel

When I tried to start training, I got an error：RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [1, 512, 4, 4]] is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

15

Thank you very much for your contribution. Your article helps me a lot. As mentioned in the title, I encountered an error at the beginning of my training.The detailed error...

TT-mouse