guided-diffusion
guided-diffusion copied to clipboard
openai
Hello everyone, I am working with guided diffusion. I would like to reproduce the results of the repository for the 64->256 super resolution network. My issue is that the upsampled...
Hi, I notice when you define the **model_variance** [here](https://github.com/openai/guided-diffusion/blob/22e0df8183507e13a7813f8d38d51b072ca1e67c/guided_diffusion/gaussian_diffusion.py#L281), first item of variance is set as **posterior_variance[1].** The comment here explains that _" we set initial (log-)variance like so to...
when load ckpt (multiGPU), it is stuck in load_state_dict () in the defined dist_util.py. But it is fine for one GPU. Anybody knows about this?
how long to train 64x64, 1000steps? anybody knows?
Why the reference batch on ImageNet 512x512 only contains 1000 images? https://openaipublic.blob.core.windows.net/diffusion/jul-2021/ref_batches/imagenet/512/VIRTUAL_imagenet512.npz
When doing the evaluation, the following error accurs: ```bash tensorflow.python.framework.errors_impl.InvalidArgumentError: 2 root error(s) found. (0) INVALID_ARGUMENT: activation input is not finite. : Tensor had NaN values [[{{node 2905231348_876199450/conv_2/CheckNumerics}}]] [[strided_slice_2/_5]] (1)...
How to generate the reference dataset and the generated dataset .npz files?
Despite setting CUDA_VISIBLE_DEVICES, it continues to use GPUs from the index 0. How can I ensure that the code uses specific GPUs as intended?
