Dog Bread Classification App Algorithm using a CNN

At the end of this project, the code will accept any user-supplied image as input. If a dog is detected in the image, it will provide an estimate of the dog's breed among 133 breeds. If a human is detected, it will provide an estimate of the dog breed that is most resembling.
I built two models in this notebook; one from scratch and another one using transfer learning which provided an accuracy of 81%.

Training Data

• Download the dog dataset. Unzip the folder and place it in this project's home directory, at the location /dog_images.

• Download the human dataset. Unzip the folder and place it in the home directory, at location /lfw.