Transfer Learning on Images with Tensorflow 2 – Predictive Hacks

In this tutorial, we will provide you an example of how you can build a powerful neural network model to classify images of cats and dogs using transfer learning by considering as base model a pre-trained model trained on ImageNet and then we will train additional new layers for our cats and dogs classification model. We will work with a sample of 600 images from the Dogs vs Cats dataset, which was used for a 2013 Kaggle competition. Our base model will be the pre-trained MobileNet V2 model. We will remove the final layer of the network and replace it with new, untrained classifier layers for our task. We will create a new model that has the same input tensor as the MobileNetV2 model, and uses the output tensor from the layer with name global_average_pooling2d_6 as the model output.