Skip to content

love-mishra/Face-Mask-Detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 

Repository files navigation

FACE MASK PREDICTION USING DEEP LEARNING

Inspiration:

we know that covid time has gone . But I am focusing on that time what is more important thing which is focused , yeah that is mask . Government had ordered that everybody applied mask on face to prevent yourself from covid-19. And face mask is not only necessary in the covid time but its need is also in some busy cities like Delhi where lots of population due to vehicles.

Introduction:

This project involve building a model that is trained using some data set by applying deep learning concept and then make it for predicting the output for a face input that it is masked or not . This project involve deep learning ,CNN ,transfer learning and gradcam visualization and other concept of machine learning .

Methodology:

This project has several step :

  • Convert the images into numeric form
  • Then preprocessing the data
  • I will use transfer learning and for it I will use mobilenetv2 and make a base model
  • And after we use deep learning concept and make hidden layer.
  • Make our model
  • Regularized our model
  • And then train it
  • Predict the test output
  • Then check the accuracy
  • And there are also many other steps in above

Goals:

Mid Evaluation:

  • To acquire the required skillset to build model .

  • Gain greater experience of using ML algorithms,deep learning and transfer learning and CNN and other concept on practical datasets(from huggingface)

  • Performing necessary data collection and data cleaning.

    ULTIMATE GOAL:

  • To increase the accuracy of the prediction of the model.

  • And make the model better so that its performance could become good .

Reference:

(1)https://www.sciencedirect.com/science/article/pii/S1532046421001775 (2)https://huggingface.co/datasets/hydramst/face_mask_wearing

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published