Jason Hu

Number of out channels

1

I am trying to use the pretrained LSUN neural networks to write my own sampling algorithm. When I call model.forward on an image of size 1x3x256x256 with some time, I...

I am trying to use the DDIM sampling method to decrease the number of sampling steps required. When I change the sampler to ddim in diffusion_config.yaml (and change nothing else)...

Format of ImageFolder

2

I am wondering what is the file format/structure of ImageFolder? When I downloaded a zip file from imagenet 1k, I just get a folder containing 50000 JPEG images, but it...

I am wondering why in layers.py, the DCT is used like so: sq_error = dct(model_output - target) ** 2 In contrast to many other diffusion model papers where the loss...

I am checking the dropbox for the pretrained checkpoints and I noticed there is an ellipse checkpoint for the single channel experiments (CT) as well as complex checkpoints for knee...