666DZY666

CVPR2021-Papers-with-Code

CVPR 2021 论文和开源项目合集

norse-1

Deep learning with spiking neural networks (SNNs) in PyTorch.

AdderNet

Code for paper " AdderNet: Do We Really Need Multiplications in Deep Learning?"

automl

Google Brain AutoML

CVPR-2021-Papers

DLPerf

DeepLearning Framework Performance Profiling Toolkit

EagleEye

(ECCV'2020 Oral)EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning

EfficientNet-PyTorch

A PyTorch implementation of EfficientNet and EfficientNetV2 (coming soon!)

EWGS

An official implementation of "Network Quantization with Element-wise Gradient Scaling" (CVPR 2021) in PyTorch.

google-research

Google Research

HAWQ

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

KaTeX

Fast math typesetting for the web.

libonnx

A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.

mace

MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

MegEngine

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

Msnhnet

🔥 (yolov3 yolov4 yolov5 unet ...)A mini pytorch inference framework which inspired from darknet.

ncnnqat

quantize aware training package for NCNN on pytorch

nncf

PyTorch*-based Neural Network Compression Framework for enhanced OpenVINO™ inference

oneflow

OneFlow is a performance-centered and open-source deep learning framework.

oneflow_convert_tools

和OneFlow相关的模型转换工具包含OneFlow2ONNX，X2OneFlow等等。

onnx-simplifier

Simplify your onnx model

opencv-mobile

The minimal opencv for Android, iOS and ARM Linux

Paddle-Lite

Multi-platform high performance deep learning inference engine (『飞桨』多平台高性能深度学习预测引擎）

PaddleSlim

PaddleSlim is an open-source library for deep model compression and architecture search.

ppl.nn

A primitive library for neural network

tvm

Open deep learning compiler stack for cpu, gpu and specialized accelerators

tvm_learn

tvm learn

yolodet-pytorch

reproduce the YOLO series of papers in pytorch, including YOLOv4, PP-YOLO, YOLOv5，YOLOv3, etc.

ZAQ-code

CVPR 2021 : Zero-shot Adversarial Quantization (ZAQ)

ZQCNN

一款比mini-caffe更快的Forward库，觉得好用请点星啊，400星公布快速人脸检测模型，500星公布106点landmark，600星公布人头检测模型，700星公布人脸检测套餐（六种pnet,两种rnet随意混合使用满足各种速度/精度要求），800星公布更准的106点模型