krummrey
krummrey
I was able to get it running under Ubuntu 18.04.5 using `pip install tf-nightly`. Had to restart my environment from scratch due to some dependency issues.
I've tried that and pip seems to install it fine, but then I get this error: ``` Traceback (most recent call last): File "/Users/jan/Documents/ML/Real-ESRGAN/inference_realesrgan.py", line 128, in main() File "/Users/jan/Documents/ML/Real-ESRGAN/inference_realesrgan.py",...
Very unlikely. I'm trying to train a photo to line art model and it struggles really hard to maintain even the basic style. But give it a try. You'll spend...
I've gone through all preprocessors and found these as not working: - **depth-leres** - RuntimeError: Input type (MPSFloatType) and weight type (torch.FloatTensor) should be the same - **scribble-pidinet** - RuntimeError:...
Maybe one can patch it in the colab itself?
Calling cuda directly makes it hard to switch to cpu or mps. I guess there is a general DEVICE variable set somewhere. Can we use that in those two instances?
I have the same issue, rerun after disconnect so all settings are exactly the same - but the previous model isn't found and training starts all over.
The SVGs came all from Illustrator CS6. I had ungrouped them but for some reason I had to do the Path > Object to path to get it to work....
Doesn't work for me either. It's in the folder but doesn't show up in the menu. --api is running.
Your sister project for restoring photos works great. Would love to try this one also. So here is my +1