jasonrjw Goto Github PK

binary-bert

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

bit

Code repo for the paper BiT Robustly Binarized Multi-distilled Transformer

bnn_nobn

[CVPRW 21] "BNN - BN = ? Training Binary Neural Networks without Batch Normalization", Tianlong Chen, Zhenyu Zhang, Xu Ouyang, Zechun Liu, Zhiqiang Shen, Zhangyang Wang

compact-transformers

[Preprint] Escaping the Big Data Paradigm with Compact Transformers, 2021

ddtb

Pytorch implementation of our paper accepted by ECCV2022 -- Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks

deltacnn

DeltaCNN End-to-End CNN Inference of Sparse Frame Differences in Videos

e2fif

Simple but stronge baseline for binarized super-resolution networks (BSRNs).

edsr-pytorch

PyTorch version of the paper 'Enhanced Deep Residual Networks for Single Image Super-Resolution' (CVPRW 2017)

hawq

Quantization library for PyTorch. Support low-precision and mixed-precision quantization, with hardware implementation through TVM.

installation

Datasets, Transforms and Models specific to Computer Vision

lab

The official repository for the paper LAB: Learnable Activation Binarizer for Binary Neural Networks.

lipreading_using_temporal_convolutional_networks

ICASSP'22 Training Strategies for Improved Lip-Reading; ICASSP'21 Towards Practical Lipreading with Distilled and Efficient Models; ICASSP'20 Lipreading using Temporal Convolutional Networks

loss-landscape

Code for visualizing the loss landscape of neural nets

lsq_plus

3rd place solution for NeurIPS 2019 MicroNet challenge

lsqplus

LSQ+ or LSQplus

mcunet

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning

nonuniform-to-uniform-quantization

Nonuniform-to-Uniform Quantization: Towards Accurate Quantization via Generalized Straight-Through Estimation. In CVPR 2022.

pams

PArameterized Max Scale

pytoflow

The py version of toflow → https://github.com/anchen1011/toflow

reactnet

ReActNet: Towards Precise Binary NeuralNetwork with Generalized Activation Functions. In ECCV 2020.

repoptimizers

Official repo of RepOptimizers and RepOpt-VGG

sesr

Super-Efficient Super Resolution

slowfast

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

spconv-plus

Focal Sparse Convolutional Networks for 3D Object Detection

spvnas

[ECCV 2020] Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution

tinyml

torchsparse

[MLSys'22] TorchSparse: Efficient Point Cloud Inference Engine

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

x3d

[CVPR 2020] X3D: Expanding Architectures for Efficient Video Recognition