# StaNoSA

**Repository Path**: a-dot/StaNoSA

## Basic Information

- **Project Name**: StaNoSA
- **Description**: [Paper Implementation]Stain Normalization using Sparse AutoEncoders (StaNoSA): Application to digital pathology.
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2019-04-02
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# StaNoSA
[Stain Normalisation using Sparse Auto-Encoders](https://www.sciencedirect.com/science/article/abs/pii/S0895611116300404).
Implemented as close to the paper as possible.

# Environment Setup
(I use Ubuntu 16.04, so the following instructions are tailored for it. If you are using a different OS, you may have to change these accordingly)

1. If you don't have Anaconda, download and install [Anaconda](https://www.anaconda.com/download/) as per the instructions for your OS.
2. Create environment and install the dependencies

> conda create --name stanosa python=3.6 --file req.txt

3. Activate the environment

> source activate stanosa

Note: if you experience anything like "conda: command not found" then just restart your terminal.


## Training
Configuration is done in "stanosa.conf".

Ensure that your training images are all stored directory under the folder specified in the *data_path* variable in the stanosa.conf file.

When ready, simply run:

> python train.py

Model states will be saved to "$output_path/states".

## Testing
As before, ensure all testing images are under the *data_path* variable (in the [testing] section).
Make sure you set the *state_path* variable properly so the weights are loaded from training.

Testing will take each image under the testing data path and pass it through the encoder, patch-by-patch and then applies clustering to the activations.
The output of the clustering as well as the activations will be stored in a folder with the same name as the image.

When ready:

> python test.py