Tobias Hinz
Tobias Hinz
Hi, the error is thrown because the input image (opt.input_name) does not exist (see https://github.com/tohinz/ConSinGAN/blob/52193b494c2183784cfbf1227b2a44cf4b78552e/main_train.py#L61). It seems something with your --input_name does not work as it also does not print...
Hm, maybe you can just hardcode the paths to the two images in the code directly to get it to work for now? It might also work if you use...
Hi, we haven't tested animation and super-resolution with our model yet, but I would be interested to see how well it works. For animation I believe it should work just...
Edit: I just added code/examples (see readme) for image animation. Training is the same as for uncondtional image generation. At test time we simply add random noise to z_opt to...
Hi, we haven't spent any time on testing ConSinGAN for super resolution. There are some ways this could be implemented but we are not planning on working on this. I'm...
Hi, that looks more like a problem with your Pytorch installation. Are you sure you have the correct CUDA and CUDNN version installed for your graphic card and Pytorch version?
I haven't tested it with Pytorch 1.7 but in general it should work (I assume at least it would give you a different error message from the one above). The...
Just set `--nc_im 1` and represent your image as shape (H x W x 1), i.e. 1 channel instead of 3 for RGB
You will have to change the code slightly then to adapt to this. Another easy work-around is to just convert your gray-scale image to a "color image" with 3 channels,...
What are the problems?