Due to ongoing Corona pandemic, wearing mask has become an integral part of our lives. Nowadays it is important to wear a face mask to ensure the safety of ourself and others.I have created a simple object detection model that can detect whether you are wearing a mask or not. I have utilized the object detection API and tensorflow framework and used a pretrained model RetinaNet50 from "Model Zoo". I have used face mask detection datasets from "kaggle". The model has achieved 90% accuracy with testing data.
1 . Installation of necessary libraries
-
Preparing dataset for Custom Training
-
Using a Pretrained Model
-
Creating a Labelmap.pbtxt
-
Creating xml to csv
-
Creating tensorflow records files from csv
-
Getting the config file and do the necessary changes
-
Start the training
-
Model Evaluation
-
Exporting the graph
-
Doing prediction on trained model
-
Using webcam for Prediction
Link : https://blog.tensorflow.org/2020/07/tensorflow-2-meets-object-detection-api.html
object detection repo: https://github.com/tensorflow/models/tree/master/research/object_detection
Tensorflow Models Repo : https://github.com/tensorflow/models
Tensorflow Model Selection : https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md