Convolutional Neural Networks
Anomaly Detection with R
Keras implementations of Generative Adversarial Networks.
Topic Modelling for Humans
Models built with TensorFlow
Fast Style Transfer in TensorFlow
Learning to Communicate with Deep Multi-Agent Reinforcement Learning
Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition based on DeepMind's WaveNet and tensorflow
Python implementation of stacked generalization classifier. Plays nice with sklearn.
Keras WaveNet implementation
Efficient implementation of Wavenet generation.
Turn your two-bit doodles into fine artworks with deep neural networks, generate seamless textures from photos, transfer style from one image to another, perform example-based upscaling, but wait... there's more! (An implementation of Semantic Style Transfer.)
Implementation of character based convolutional neural network
Deep learning with dynamic computation graphs in TensorFlow
A Flow-based Generative Network for Speech Synthesis
Image-to-image translation using conditional adversarial nets
An unofficial and partial Keras implementation of "Noise2Noise: Learning Image Restoration without Clean Data"
PyTorch implementation of "InstaGAN: Instance-aware Image Translation" (ICLR 2019)
An attempt at reproducing the paper Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection
Real-time object detection and classification
Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset
PyTorch version of Google AI's BERT model with script to load Google's pre-trained models
Striving for Simplicity: The All Convolutional Net (All-CNN-C)
Windows and Linux version of Darknet Yolo v3 & v2 Neural Networks for object detection (Tensor Cores are used)
Real-time single person pose estimation for Android and iOS.
Multi-Content GAN for Few-Shot Font Style Transfer
Efficient Neural Architecture Search coupled with Quantized CNNs to search for resource efficient and accurate architectures.
Pretrained models for TensorFlow.js
Python toolbox to create adversarial examples that fool neural networks
An efficient multi-scale training approach for instance-level recognition tasks like object detection and instance-level segmentation