CG1507

quickcnn

QuickCNN is high-level library written in Python, and backed by the Keras, TensorFlow, and Scikit-learn libraries. It was developed to exercise faster experimentation with Convolutional Neural Networks(CNN). Majorly, it is intended to use the Google-Colaboratory to quickly play with the ConvNet architectures. It also allow to train on your local system.

hair_style_transfer

3D Hair Style Transfer using a multi-model approach.

lstm_reg

LSTM based regression on weather data.

ConvNet-Vis

ConvNet-Vis helps to visualize the Deep Convolutional Neural Networks with following methods.

Artify

:art: Keras implementation of Neural Style Transfer for coloring paintings and creating art with playground

ConvNet-Zoo

:video_game: PlayGround for Convolutional Neural Networks + Layerwise Activation Map

CE_paper

Machine Learning effect on Customer Engagement

CG1507

CG1507.github.io

Portfolio

nlp_elasticsearch

Natural Language Search on ElasticSearch index.

cocoa

Framework for learning dialogue agents in a two-player game setting.

keras

Deep Learning library for Python. Runs on TensorFlow, Theano, or CNTK.

Neural-Style-Transfer

Keras Implementation of Neural Style Transfer from the paper "A Neural Algorithm of Artistic Style" (http://arxiv.org/abs/1508.06576) in Keras 2.0+

tensorflow

Computation using data flow graphs for scalable machine learning

tensorflow-densenet

Tensorflow-DenseNet with ImageNet Pretrained Models

vicharana

A python way for data analysis.