Skip to content

evan01/Paw-sitive

Repository files navigation

McGill Computer Vision Final Project

####By Evan and Kristine

Just a program that tries to tell the difference between cats, and dogs using tensorflow, neural networks and lots of love As of now, we have a perfect score on Kaggle, it's pretty incredible just how great a massive convoluted neural network works. ##Running the Code After opening up the main.ipynb file, there are 4 sections. We would recommend playing around with the testing code in section 2 where you can supply an image of a cat or a dog. We took a random dog photo and a photo of Evan's cat Gatsby as an example.

Please note that you have to install Tensorflow (pip installable) in order to run the classification program on your own images. http://stackoverflow.com/questions/37061089/trouble-with-tensorflow-in-jupyter-notebook

  1. Testing Code that generates the labels.csv file which we submitted to the competition
  2. Testing Code where you can supply the path of any image of a cat or a dog and it will predict the animal type
  3. Training script, the script we used to call a sequence of python tensorflow programs to train the CNN
  4. Training code, the code that separates all the images of cats in dogs into respective directories in order for the tensorflow training sequence to correctly train the network

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published