shizi7677 / chexnet-mxnet

A mxnet implementation of CheXNet

ChexNet-Mxnet

Under development.This is a re-implementation of CheXNet,which is a deep learning algorithm that can detect and localize 14 kinds of diseases from chest X-ray images.

CAM

It's a weakly supervised localization.Get more information from this arxiv page

Prerequisites

1. Python 3.5
2. Mxnet
3. Numpy
4. Pandas

Preparations

1. Clone this repository.
2. Download images of ChestX-ray14 from this released page and decompress them to the directory images.
3. Modify the file 'Data_Entry_2017.csv' to a file like this.

Try the demo

python demo.py
# available options
python demo.py -h

Train the model

python train.py --gpus 0,1,2
# see advanced arguments for training
python train.py -h