Ankit Shah's Projects
Hands-on Deep Reinforcement Learning, published by Packt
Deep neural networks for voice conversion (voice style transfer) in Tensorflow
A PyTorch implementation of the Deep Audio-Visual Speech Recognition paper.
videos, lectures, blogs for Deep Learning
Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology
Implements the unsupervised pre-training of convolutional neural networks
DeepFaceLab is the leading software for creating deepfakes.
DeepFocus: Learned Image Synthesis for Computational Displays
Course projects for CMU Deep Learning Class by Ruslan Salakhutdinov
A list of deep learning implementations in biology
A collection of various deep learning architectures, models, and tips
Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).
Example code from the book "Deep Learning for the Life Sciences"
Deep Learning Tutorial notes and code. See the wiki for more info.
This repository contains implementations and illustrative code to accompany DeepMind publications
Code repository for Model-based Deep Hand Pose Estimation
DeepNovo workflow of neoantigen discovery by personalized de novo sequencing.
Code for the Nature Scientific Reports paper "Pathologist-level classification of histologic patterns on resected lung adenocarcinoma slides with deep neural networks." A sliding window framework for classification of high resolution whole-slide images, often microscopy or histopathology images.
Python library assists deep learning on graphs
A TensorFlow implementation of Baidu's DeepSpeech architecture
A PaddlePaddle ASR toolkit.
DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.
MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.
Samples for TensorRT/Deepstream for Tesla & Jetson
A huge list of alternatives to Google products. Privacy tips, tricks, and links.
Delay insensitive carry lookahead adder. Made using Magic Software. This is a 4-bit implementation but similar blocks can be explored to higher number of bits
Code for the paper Hybrid Spectrogram and Waveform Source Separation