Skip to content

This is the source code for training and testing a three class CNN for nuclei segmentation using Torch

Notifications You must be signed in to change notification settings

abhishekvahadane/NucleiSegmentation

 
 

Repository files navigation

NucleiSegmentation

Following is a simple instruction set to test our state-of-the art deep learning based nuclei segmentation software using an AWS EC2 instance-

Step 1- Create an instance and configure it for using CUDA enable Torch (refer to goo.gl/mtQgYS)

Step 2- Get the software from Github

Step 3- Test our state-of-the art nuclei segmentation model

cd NucleiSegmentation

th predict_full_mask.lua

Results will be saved in the /data/testing-data/40x/results folder

Step 4- Zip the results folder and download in your laptop's "Downloads" folder

zip -r results.zip results

scp –i key.pem user@ip:~/NucleiSegmentation/data/testing-data/40x/results.zip ~/Downloads/

This will give you three images from CNN output 1.png, 2.png and 3.png. Please refer to nucleisegmentationbenchmark.weebly.com for post-processing and model details.

About

This is the source code for training and testing a three class CNN for nuclei segmentation using Torch

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Lua 75.7%
  • Python 15.9%
  • Shell 8.4%