DigitClassifier | A Convolutional Deep Neural Network Using Theano | Machine Learning library

DigitClassifier is a Python library typically used in Artificial Intelligence, Machine Learning, Deep Learning applications. DigitClassifier has no bugs, it has no vulnerabilities and it has low support. However DigitClassifier build file is not available. You can download it from GitHub.

#Deep Convolutional Neural Networks on MNIST. This repository features python code for a Deep Convolutional Neural Network. This network allows its weights and biases to be saved allowing for the network to be cached and used without having to train on start-up. This class has methods which are identical to the main methods found in Sklearn classifiers. This means much of those tools can be used on this. Getting the app to run is pretty easy, just clone the repo, install requirements, and then run! The number of threads that Theano uses can be controlled via the OMP_NUM_THREADS enviromental variable, below it is set to 8 threads. This package uses Theano, so it can train on a GPU if the CUDA Toolkit is installed on the system. Information on the installation process can be found on their website.