Transfer learning is a machine learning technique where a model trained on one task is re-purposed on a second related task. InceptionV3 is a transfer learning model, a convolutional neural network (CNN) which is 27 layers deep. The model itself is made up of symmetric and asymmetric building blocks, including convolutions, average pooling, max pooling, concats, dropouts, and fully connected layers.
Here we trained a dataset on IceptionV3 model classifying images of Cat and Dog with an accuracy of 97%.