ruocwang

mobile-vision

Mobile vision models and code

gaea_release

Code release to accompany paper "Geometry-Aware Gradient Algorithms for Neural Architecture Search."

pytorch-hessianfree

PyTorch implementation of Hessian Free optimisation

fisher-information-matrix

PyTorch implementation of FIM and empirical FIM

PyTorch-LBFGS

A PyTorch implementation of L-BFGS.

RobustDARTS

Understanding and Robustifying DARTS

backpack

BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.

Neural_Tangent_Kernel

Awesome-AutoDL

Automated Deep Learning: Neural Architecture Search Is Not the End (a curated list of AutoDL resources and an in-depth analysis)

nas-bench-nlp-release

Bayesian-Neural-Networks

Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more

KFAC-Pytorch

Pytorch implementation of KFAC and E-KFAC (Natural Gradient).

sgas

SGAS: Sequential Greedy Architecture Search (CVPR'2020) https://www.deepgcns.org/auto/sgas

CARS

[CVPR2020] CARS: Continuous Evolution for Efficient Neural Architecture Search

spacecutter

Ordinal regression models in PyTorch

NAS-Bench-201

NAS-Bench-201 API and Instruction

neural-collaborative-filtering

pytorch version of neural collaborative filtering

AutoAugment

Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow

dice

Exact inference for discrete probabilistic programs. (Research code, more documentation and ergonomics to come)

SNAS-Series

This repo contains the PyTorch implementation of the SNAS-Series papers

AutoDL-Projects

Automated deep learning algorithms implemented in PyTorch.

XNAS

pdarts

Codes for our paper "Progressive Differentiable Architecture Search:Bridging the Depth Gap between Search and Evaluation"

attention-is-all-you-need-pytorch

A PyTorch implementation of the Transformer model in "Attention is All You Need".

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Rainbow

Rainbow: Combining Improvements in Deep Reinforcement Learning

uda

Unsupervised Data Augmentation (UDA)

horovod

Distributed training framework for TensorFlow, Keras, PyTorch, and Apache MXNet.

MoreMNAS

models for MoreMNAS

Efficient-PyTorch

My best practice of training large dataset using PyTorch.