In this task I have created face recognition model by using weights from imagenet and pre-trained mobilenet CNN model. Although I have customized the CNN model by adding some more layers to better the accuracy.
Step 1: First we have to get the dataset & put it in two separate folders of training and validation.
Step 2: In next Step we will be doing transfer Learning. Transfer learning is a machine learning method where a model developed for a task is reused as the starting point for a model on a second task.
It is a popular approach in deep learning where pre-trained models are used as the starting point on computer vision and natural language processing tasks given the vast compute and time resources required to develop neural network models on these problems and from the huge jumps in skill that they provide on related problems.
Step 3: We add MobileNet Network.
Step 4: Layers of MobileNet are shown below:-
Step 5: Here, We are adding some layers to our model.
Step 6: Here we are loading our dataset with some augmentation.
Step 7: Now, we are training the model.
Step 8: As we are getting good accuracy at this level of testing. It’s tive to validate our accuracy.
Step 9: My model finally recognized the face!!!!