https://github.com/zabir-nabil/covid19-few-shot-learning

https://github.com/zabir-nabil/covid19-few-shot-learning

cnn-keras coronavirus coronavirus-dataset coronavirus-real-time covid-19 covid19 few-shot-learning keras siamese-network tensorflow x-ray

Last synced: about 1 month ago
JSON representation

• Host: GitHub
• URL: https://github.com/zabir-nabil/covid19-few-shot-learning
• Owner: zabir-nabil
• Created: 2020-03-19T06:18:45.000Z (almost 5 years ago)
• Default Branch: master
• Last Pushed: 2022-12-08T03:54:58.000Z (about 2 years ago)
• Last Synced: 2023-02-27T21:13:51.339Z (almost 2 years ago)
• Topics: cnn-keras, coronavirus, coronavirus-dataset, coronavirus-real-time, covid-19, covid19, few-shot-learning, keras, siamese-network, tensorflow, x-ray
• Language: Jupyter Notebook
• Size: 226 KB
• Stars: 14
• Watchers: 0
• Forks: 0
• Open Issues: 14
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Covid-19 few shot learning from X-ray images

### Dataset

* Download dataset from https://drive.google.com/open?id=1Rrysw7QOulYnZ8PiWiYV2aBP8V4aRwnH

* positive samples are collected from https://github.com/ieee8023/covid-chestxray-dataset

* negative samples are collected from https://www.kaggle.com/paultimothymooney/chest-xray-pneumonia (only train split is used)

* positive samples are cleaned by removing images from any region except chest

### Installation

1. Install Anaconda

2. pip install -r requirements.txt

3. conda install tensorflow-gpu

### Result & Visualization

Look into `baseline_siamese` notebook