deepupe_tensorflow

deepupe_tensorflow copied to clipboard

About the trained model parameters

1

Do you have a model trained in this article? I want to test it with my test set. Can you give me a copy? Thank you checkpoints,About the trained model...

18827513379

I get an error when running 'test.py' too

3

It looks like your restore process is wrong. The detailed information is below: NotFoundError (see above for traceback): Restoring from checkpoint failed. This is most likely due to a Variable...

diamond0910

the paper writer has released test code, you can update according to it

2

Sent from PPHub For GitHub

jiangxuetao0823

I get an error when I run the (test.py).

2

It looks like that the saver.restore() could not get the correct variables from saved_models..

hw331

hi, thank you for your work. Would you please share your dataset?

tuvovan

The smoothness loss is also different: I kept getting nan with the logarithmic operation so I deleted that part, the left part could be seen as total-variation loss (tv-loss)

1

You normalize the data in (-1,1) and the parameter of tf. log () is greater than 0, so loss is nan.

lilin-git

Thanks for your implementation, I read your code and find some your implementation bugs about our cvpr work. The network's output should be an illumination map, you should use input...

wangruixing