Chengxi Ye

LightNet. Efficient, transparent deep learning in hundreds of lines of code.

deconvolution. Python

DBG2OLC. A genome assembler that reduces the computational time of human genome assembly from 400,000 CPU hours to 2,000 CPU hours, utilizing long erroneous 3GS sequencing reads and short accurate NGS sequencing reads.

LightCapsNet. A Matlab implementation of the capsule networks (or capsnet).

Sparc. C++

DVS. Python

SparseAssembler. A sparse k-mer graph based, memory-efficient genome assembler.

AssemblyUtility. C++

BlindCall. DNA base-calling using blind convolution.

Synchronized-BatchNorm-PyTorch. Synchronized Batch Normalization implementation in PyTorch.

SalsaNext. Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving

rpcaADMM. Robust Principal Component Analysis via ADMM in Python

panoptic-deeplab. This is Pytorch re-implementation of our CVPR 2020 paper "Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation" (https://arxiv.org/abs/1911.10194)

VAT-pytorch. Virtual Adversarial Training (VAT) implementation for PyTorch

apex. A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

examples. A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

active_learning_coreset. Source code for ICLR 2018 Paper: Active Learning for Convolutional Neural Networks: A Core-Set Approach

vision. Datasets, Transforms and Models specific to Computer Vision

keops. KErnel OPerationS, on CPUs and GPUs, with autodiff and without memory overflows

maskrcnn-benchmark-1. Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

pytorch-tutorial. PyTorch Tutorial for Deep Learning Researchers

capsule-networks. A PyTorch implementation of the NIPS 2017 paper "Dynamic Routing Between Capsules".

pytorch. Tensors and Dynamic neural networks in Python with strong GPU acceleration

CapsNet-Keras. A Keras implementation of CapsNet in NIPS2017 paper "Dynamic Routing Between Capsules". Now test error < 0.4%.