improved-diffusion
improved-diffusion copied to clipboard
openai
Release for Improved Denoising Diffusion Probabilistic Models
Hi, thanks for the excellent work. I train the model on my own CT dataset with a RTX4090 GPU, the CT is converted to 3-channel gray maps. The trained code...
When I use a pure white image as data to run scripts/image_nll.py, I get the lowest bpd 0.059...(and black 0.096...). But a normal image in CIFAR10 only gets 3.2 or...
In sampling functions, the value is clamped. Why the value range of clamp is set to (-1,1) ? Is it related to normalized image intensity value or added noise value...
How to run train crpits on multi-gpus in single node? @longouyang @welinder @JoshuaGross @jietang @esigler
fix the bug of RuntimeError: a leaf Variable that requires grad is being used in an in-place operation, detail can be seen at this [issue](https://github.com/openai/improved-diffusion/issues/23)
which is defined on [loss.py](https://github.com/openai/improved-diffusion/blob/main/improved_diffusion/losses.py#L50) and used on [gaussian_diffusion.py](https://github.com/openai/improved-diffusion/blob/main/improved_diffusion/gaussian_diffusion.py#L666) to calculate L[0](seems like)
Hi, I am trying your code to train on 3D data but so far I am having issues with which parameters to change to make it work. A sample from...
