dogs_vs_cats

dogs_vs_cats, a keras code which sets up a convolutional neural network to classify jpeg images as being of dogs or of cats.

Licensing:

The information on this web page is distributed under the MIT license.

Related Data and Programs:

dogs_vs_cats_data, a keras code which sets up test, train, and valid directories with data for the dogs versus cats example.

imdb, a keras code which sets up a neural network to classify movie reviews as positive or negative. This is similar to the "movie_review" script, but is designed to be run on a remote computing node which does not have internet access at run time.

mnist, a keras code which sets up a neural network to classify the MNIST digit image data.

mnist_convnet, a keras code which sets up a convolutional neural network to classify the MNIST digit image data.

movie_review, a keras code which sets up a neural network to classify movie reviews from the IMDB database.

newswire, a keras code which sets up a neural network for the classification of Reuters newswire texts into one of 46 categories.

Author:

Original keras version by Francois Chollet; This version by John Burkardt.

Reference:

1. Francois Chollet,
   Deep Learning with Python,
   Second Edition,
   Manning, 2021,
   ISBN: 9781617296864.

Source Code:

• dogs_vs_cats.py, the script.
• dogs_vs_cats.sh, runs the script.
• dogs_vs_cats.txt, the output file.

• dogs_vs_cats.h5, a saved copy of the model
• dogs_vs_cats_tvloss.png, a plot of the training and validation loss.
• dogs_vs_cats_tvacc.png, a plot of the training and validation accuracy.