In this project, built a pipeline that can be used within a web or mobile app to process real-world, user-supplied images. Given an image of a dog, the model will identify an estimate of the canine’s breed. If supplied an image of a human, the model will identify the resembling dog breed.
The dataset contains 8352 images in total, divided across 133 breeds and already split in training, validation, and test sets. On average, there are 50 training images per breed, with a minimum of 26 for the Norwegian buhund and a maximum of 77 for the Alaskan malamute.
Download the https://s3-us-west-1.amazonaws.com/udacity-aind/dog-project/dogImages.zip dog dataset. Unzip the folder and place it in this project's home directory, at the location /dogImages. Download the https://s3-us-west-1.amazonaws.com/udacity-aind/dog-project/lfw.zip human dataset. Unzip the folder and place it in the home directory, at location /lfw.