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