[Bug] Expected Demo Input Format

Question

[Bug] Expected Demo Input Format

mohammed-amr opened this issue 4 years ago · 2 comments

I have some jpg images I'd like to run the demo on, but the output seems to be erroneous in some way.

Here's an example input image:

Here's an example output image:

I followed the instructions for the first demo and have not changed anything in the code. Using Pytorch 1.6, torchvision 0.7.0, and Python 3.6. Using the GOPRO_L1 pretrained experiment weights. Is there an assumption on type of image and range?

Answer 1 · 2020-10-20T16:12:55.000Z

Changing the blur camera response type to blur from the default of blur_gamma doesn't produce a better result.

Answer 2 · 2020-10-20T21:08:38.000Z

Fixed my own issue with a solution mentioned elsewhere. Seems like the codebase fails silently when it can't find the right model weights. Set a full explicit path instead of a relative path and it should be ok.