lainwired

Looking at the link below I was able to successfully run the following command: pip install spatial-correlation-sampler How do I get your program to work? https://github.com/ClementPinard/Pytorch-Correlation-extension

I don't know your detailed environment, so I can't answer. did you run it according to the jupyter-notebook file? did you successfully convert the weights before facial_exchange.py?

umm...It looks like facial_exchange.py is running in pytorch and not calling dnnlib. Can you show me the error log so that I can see at what stage the error is...

I'm sorry, I don't know why you get the error in facial_exchange.py but not in image_crossover.py. The two codes should be the same until line 37. Did you try it...

https://github.com/RangiLyu/nanodet/blob/0b78ebabfaec0edabb4e6ca629fc51130f1505d5/nanodet/model/head/nanodet_plus_head.py#L552-L554 https://github.com/RangiLyu/nanodet/blob/0b78ebabfaec0edabb4e6ca629fc51130f1505d5/nanodet/model/head/nanodet_plus_head.py#L497 I was struggling with the same reproducibility, but realized that the sigmoid function was already applied to the forward function of onnx. This is similar to what is...

I'm not familiar with tensorflow2, so I don't know. Sorry

You can download the official styleGAN weights at this time. You can find stylegan-ffhq-1024x1024.pkl in the Resource section of the README below. https://github.com/NVlabs/stylegan or https://drive.google.com/uc?id=1MEGjdvVpUsu1jB4zrXZN7Y4kBBOzizDQ If you can't use google...

The environment at the time of development has been discarded, but it should be possible to convert it using tensorflow-gpu==1.15.　 The paper "Unconstrained Facial Expression Transfer using Style-based Generator" corresponds...

Hmmm. Maybe it's the version of pyotrch. I'm sorry but I can't experiment right away in my environment. is it possible to try with an older version such as pytoch...

Thanks for your questions. As you say, optimizing n should produce better images. However, I was satisfied with the quality of the image by the optimization of w only ....