Project - Mini Project

What is Mobile Net Architecture?

MobileNets are a class of small, low-latency, low-power models that can be used for classification, detection, and other common tasks convolutional neural networks are good for. Because of their small size, these are considered great deep learning models to be used on mobile devices.

How does it work?

MobileNet uses depth wise convolutions to significantly reduce the number of parameters compared to other networks, resulting in a lightweight deep neural network.

Why MobileNetV2 is used for image classification?

MobilenetV2 is a pre-trained model for image classification. Pre-trained models are deep neural networks that are trained using a large images dataset. In our challenge we used multiple images of cats and Dogs to train our model. This trained model is then used by the program to predict the image that was passed through it.

What are the advantages of MobileNet architecture?

Less complexity. Faster performance and being useful for mobile applications. Small, low-latency convolutional neural network.