Upload 3dvascnetV2.0.zip
Browse files# 3DVascNetV2.0 release notes - Software Update: GPU Support and Segmentation Efficiency
We’ve made several updates to improve the software. Here’s what’s new:
### GPU Compatibility
The software should now work on all GPUs, but users need to install **CUDA 11.2** and **cuDNN 8.1**:
- [CUDA 11.2](https://developer.nvidia.com/cuda-11.2.0-download-archive)
- [cuDNN v8.1.0 (January 26th, 2021), for CUDA 11.0, 11.1, and 11.2](https://developer.nvidia.com/rdp/cudnn-archive) [cuDNN Library for Windows (x86)]
### GPU Availability Check
At startup, the terminal will display either:
- **"GPU is available"**
- **"GPU is not available"**
If you have an NVIDIA GPU and see *"GPU is not available"*, feel free to contact me hemaxi.narotamo[at]tecnico.ulisboa.pt
### Monitoring GPU Usage
During segmentation, you can verify if the GPU is being utilized by running the `nvidia-smi` command in a terminal window.
### Segmentation Efficiency
If segmentation masks for certain images already exist in the results folder, those images will be skipped during the segmentation step. This feature is especially useful for CPU-based users, as it saves time by reusing previously generated masks.
- 3dvascnetV2.0.zip +3 -0
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2964af0ea60c78410056b2979df8ac5406d8f7e5c2dc248924d8d8f14b628739
|
| 3 |
+
size 1091286716
|