🛑 Note: An updated and better version of this repository can be found here. It follows a better approach with an updated dataset. I'd recommend it over this one. 🛑
This project uses the COVID-19 Radiography Database for training.
It consists of chest X-ray images for COVID-19 positive cases along with Normal and Viral Pneumonia images. There are 219
COVID-19 positive images, 1341
normal images and 1345
viral pneumonia images.
Train Accuracy Test Accuracy fine-tuning (ResNet-18) 99.32% 96.67%