This is the code for the "How to Make an Image Classifier" - Intro to Deep Learning #6 by Siraj Raval on Youtube
##Overview
This is the code for this video on Youtube by Siraj Raval as part of the Intro to Deep Learning Udacity nanodegree. The code uses Keras & Tensorflow to train a convolutional neural network on a labeled dataset of cats and dogs. Then, it will be able to classify novel cats and dogs pretty well.
##Dependencies
- keras (https://keras.io/#installation)
- tensorflow (https://www.tensorflow.org/versions/r0.10/get_started/os_setup)
Install Jupyter notebook from here.
##Usage
Run jupyter notebook in terminal when you are in the main directory, then a browser window will pop up. You can run the code in the browser easily.
The challenge for this video is to build an image classifer for 2 different animals. They can be any 2 animals. You can use Keras & Tensorflow. The demo notebook attached will act as a good guide, as well as the links i've provided in the video description.
Bonus points if you do one or both of the following.
-
Use only Tensorflow
-
You use transfer learning to improve your model.
Good luck!
##Credits
Credits go to a Wizard named Rajiv Shah! I've merely created a wrapper to get people started.