Skip to content

Classification of normal and covid-19 MRI images with Convolutional Neural Network using Tensorflow Framework.

License

Notifications You must be signed in to change notification settings

uzunb/Covid-19-Detector-CNN

Repository files navigation

Covid-19-Detector-CNN

Requirements & Dependencies

Tested this code using:

  • Ubuntu 20.04.2 LTS
  • Python 3.8.5
  • Tensorflow 2.4.1
  • Keras 2.4.3
  • Opencv 4.5.2

requirements.txt consists required dependencies.
Easy way: You can install the requirements with the following commands:

cd myproject/
virtualenv venv
./venv/bin/activate
pip install -r requirements.txt

Dataset

This dataset contain 3616 COVID-19 positive cases along with 10,192 Normal, 6012 Lung Opacity (Non-COVID lung infection), and 1345 Viral Pneumonia images.
Used 1000s of normal and covid images.

NORMAL COVID19
normal covid

Model

model_plot


Train

Model trained with 1500 labeled images. Model fit parameters are:

batch_size = 16  
epochs = 20  
validation_split= 0.25
ACCURACY LOSS
accuracy_figure loss_figure

Results

pred_figure

Releases

No releases published

Packages

No packages published

Languages