Skip to content

codemukul95/SVHN-classification-using-Tensorflow

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

15 Commits
 
 
 
 
 
 
 
 

Repository files navigation

SVHN-classification-using-Tensorflow

Attempt to implement classification of SVHN Dataset using Tensorflow

Dataset URL: http://ufldl.stanford.edu/housenumbers/

Libraries Used: NumPy, Scipy, Tensorflow and TfLearn

MNIST example tensorflow: https://www.tensorflow.org/versions/0.6.0/tutorials/mnist/pros/index.html#deep-mnist-for-experts

CIFAR-10 example tensorflow: https://www.tensorflow.org/versions/0.6.0/tutorials/deep_cnn/index.html

Description of the files:

  1. load_data.py: Reads the dataset '.mat' files from the directory and returns them in the form of Numpy arrays. The labels are converted in one_hot_encoded format to ease the process of training

2. network.py: The CNN architecture is built to train the model.
3. test_network.py: The training set is tested against the trained weights, to check the testing accuracy value.

About

Attempt to implement classificatin of SVHN Dataset using Tensorflow

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages