From d7c113715430ea3cc01057a7660c6b4bc41507d2 Mon Sep 17 00:00:00 2001 From: Matteo Pentassuglia Date: Fri, 9 Jan 2026 10:57:01 +0100 Subject: [PATCH] Update model download link in README.md Update the broken UCL dropbox link for models download with the new MIT sharepoint link provided in the issue 114: https://github.com/BBillot/SynthSeg/issues/114#issuecomment-3542056924 --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index c398be5f..212c6d79 100644 --- a/README.md +++ b/README.md @@ -156,7 +156,7 @@ pip install tensorflow-gpu==2.0.0 keras==2.3.1 nibabel==3.2.2 matplotlib==3.3.4 pip install tensorflow-gpu==2.2.0 keras==2.3.1 protobuf==3.20.3 numpy==1.23.5 nibabel==5.0.1 matplotlib==3.6.2 ``` -3. Go to this link [UCL dropbox](https://liveuclac-my.sharepoint.com/:f:/g/personal/rmappmb_ucl_ac_uk/EtlNnulBSUtAvOP6S99KcAIBYzze7jTPsmFk2_iHqKDjEw?e=rBP0RO), and download the missing models. Then simply copy them to [models](models). +3. Go to this link [MIT sharepoint](https://mitprod-my.sharepoint.com/:u:/g/personal/bbillot_mit_edu/Ebqxo6YgUmBJkOML0m8NSXgBrhaHG7iqClFXRXPinS6FGw?e=DzKf1p), download the zip file and unzip it. Then simply copy the models in the unzipped folder into [models](models). 4. If you wish to run on the GPU, you will also need to install Cuda (10.0 for Python 3.6, 10.1 for Python 3.8), and CUDNN (7.6.5 for both). Note that if you used conda, these were already automatically installed.