Jacob Morgan

After modifying convertToIR.py, try the command `python /usr/local/lib/python3.6/site-packages/mmdnn/conversion/_script/convertToIR.py -f pytorch -d cifar_cpu_whole --inputShape 3,32,32 -n cifar_cpu_whole.pth` instead of `mmtoir -f pytorch -d cifar_cpu_whole --inputShape 3,32,32 -n cifar_cpu_whole.pth`

Found a simpler fix for this. You're drawing the text on a form with a white background (ToastOverlay), then using TransparencyKey to make all of the white transparent. This makes...

I needed to do this and I think got it working, here are the changes I made to dataloader.py: https://www.diffchecker.com/PyaP0wJ8 Change lines 185-197 depending on the structure of your dataset.

Hi, I was interested in comparing your method to ESRGAN-FS but I haven't been able to run the training code, it seems like `loss` and `mseloss` here are both undefined....

I support using an .app package if possible, since it's a lot easier for users to deal with. Made this a while ago but it doesn't work because it's trying...

This is based on the original code, so you can just use their pretrained model https://github.com/xinntao/EDVR/blob/master/docs/ModelZoo.md#edvr