Giter Club home page Giter Club logo

covid_mask_detection's Introduction

Covid Mask Classification Pipeline

This repository contains the necessary notebooks to traing, test, and probe different Deep Learning models in order to classify the incorrect use of face masks for COVID-19 awareness.

Structure of this repo:

📦covid_mask_detection
 ┣ 📂colab_notebooks
 ┃ ┣ 📂analyzing_results
 ┃ ┃ ┣ 📜covid_mask_classification_GradCams.ipynb
 ┃ ┃ ┣ 📜mask_classification_analysis_2classes.ipynb
 ┃ ┃ ┗ 📜mask_classification_analysis_3classes.ipynb
 ┃ ┣ 📂make_detections
 ┃ ┃ ┣ 📜detect_on_video_facenet.ipynb
 ┃ ┃ ┗ 📜detect_on_video_retinaface.ipynb
 ┃ ┗ 📂trainings
 ┃ ┃ ┗ 📜training_covid_mask_models.ipynb
 ┣ 📜.gitignore
 ┣ 📜LICENSE
 ┗ 📜README.md

Description of main files

  • training_covid_mask_models.ipynb : This notebook let us to make trainings using different Deep Learning models available in TorchHub. Here, we used Resnet, ResneSt and Efficienet architecture. In the same way, we can test the models obtained after the training.

  • detect_on_video_retinaface.ipynb : This notebook allow us to make detections in custom videos using RetinaFace as the detection model.

  • detect_on_video_facenet.ipynb : This notebook allow us to make detections in custom videos using Facenet as the detection model. FaceNet is an alternative detection model to the RetinaFace used on this work but. Facenet is less accurate.

  • mask_classification_analysis_2classes.ipynb and mask_classification_analysis_3classes.ipynb are notebooks with the neccesary code to analyze the predictions made by a classification model. Some useful tools presented in these notebooks are code to plot filters, feature maps, the architecture of a model and the wrong predictions by class.

  • covid_mask_classification_GradCams.ipynb : This notebook let us to plot the Grad-CAMS for the wrong predictions. Grad-CAMS are useful to determine the regions of an image the model focus on to make a prediction.

Datasets

The dataset is publicy available on Google Drive. It is a merge between the FMLD dataset and the Medical Mask Dataset.

covid_mask_detection's People

Contributors

fabriciocrespo avatar

Watchers

James Cloos avatar  avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.