Marcelo5444
Marcelo5444
Hi! looking at ffc.py i found that it does not follow precisely the implementation from https://github.com/pkumivision/FFC/blob/main/model_zoo/ffc.py Something that surprises me is in the forward of FourierUnit, the use of stack,...
With current code, ONNX export fails miserably due to list creation. This work around allows to correclty trace torch model and export to ONNX
Please could you share the conf used to train the checkpoints provided? Thanks for your work
Hi, First of all thanks for you work. Working with vit small, I see that results are far away from VQGAN, did you stop training when reached convergence? Do you...
You work is awesome and the speed on Apple devices with ANE is blasting fast. However, AFAIK and reading the paper, 3x3 depthwise convs help the ANE to parallelize alot...
Just found out that, Any intuition behind that? The coreml models provided are the non-reparametrized right?
Hi, I am trying to use the wsegnet_vgg19() model but want to use as input 1D images (grayscale) what parameters of the cfg do I need to change?
The stabilization layer were it can be found? is the here: https://github.com/pmh9960/iColoriT/blob/8a02415aea6f6cc144650b47f38e58476f4e2a0f/iColoriT_demo/modeling.py#L244