Detects in real-time if the person is wearing a mask or not.
I collected dataset which already contains augmented data.
I link for the dataset is here
1. I seperated the dataset into test and train.
2. I defined the no. of epoches[10] and the batch size[32].
3. I used MobileNetV2 to classify the images either wearing mask or not wearing mask.
4. I trained the model on the dataset.
5. I then tested the model on the test dataset.
6. I then used opencv to analyse real-time video and to make real-timeprediction if the person is wearing mask or not.
Mask_detection.ipynb notebook contains the main code,you can you can download the notebook and run each cell and check the output.
1.model contained the saved model with best accuracy,so that you don't have to train every single time.