From 2bafa6e56f4aee920c9f56b1dc52c0816cba7aaa Mon Sep 17 00:00:00 2001 From: "Lucille A. Moore" Date: Mon, 26 Aug 2024 15:59:54 -0700 Subject: [PATCH] Update usage.md clarified that GPU is not a hard dependency --- docs/usage.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/usage.md b/docs/usage.md index c58b48d..aa6b6e6 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -1,6 +1,6 @@ ## Usage -We reccommend running [BIBSnet](https://github.com/DCAN-Labs/BIBSnet) with a GPU (e.g. Volta (v), Ampere (a), Turing (t) NVIDIA), but a CPU is also sufficient. +BIBSNet utilizies nnU-Net for model training and inference, i.e. deploying the trained model to generate image segmentations for new data. We recommened running [BIBSnet](https://github.com/DCAN-Labs/BIBSnet) on a GPU if possible (e.g. Volta (v), Ampere (a), Turing (t) NVIDIA) as the [nnU-Net installation instructions](https://github.com/MIC-DKFZ/nnUNet/tree/nnunetv1?tab=readme-ov-file#installation) note that running inference requires a GPU with 4 GB of VRAM. However, please note that this may not be a hard dependency as we have also had success running BIBSNet on a CPU with 40 GB of RAM. ### Command-Line Arguments