From a121e05feb2e6e4ca02c7bc51fae7019e3005d18 Mon Sep 17 00:00:00 2001 From: Mishig Date: Thu, 20 Apr 2023 11:04:06 +0200 Subject: [PATCH] Update custom_diffusion.mdx (#3165) Add missing newlines for rendering the links correctly --- docs/source/en/training/custom_diffusion.mdx | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/source/en/training/custom_diffusion.mdx b/docs/source/en/training/custom_diffusion.mdx index 1e1958e1c9..245d434ade 100644 --- a/docs/source/en/training/custom_diffusion.mdx +++ b/docs/source/en/training/custom_diffusion.mdx @@ -279,9 +279,11 @@ You can also perform inference from one of the complete checkpoint saved during TODO. ## Set grads to none + To save even more memory, pass the `--set_grads_to_none` argument to the script. This will set grads to None instead of zero. However, be aware that it changes certain behaviors, so if you start experiencing any problems, remove this argument. More info: https://pytorch.org/docs/stable/generated/torch.optim.Optimizer.zero_grad.html ## Experimental results + You can refer to [our webpage](https://www.cs.cmu.edu/~custom-diffusion/) that discusses our experiments in detail.