xiexu666

YOLOX

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

mmocr

OpenMMLab Text Detection, Recognition and Understanding Toolbox

cs_study_plan

一份硬核(hardcore)计算机科学CS自学计划，偏向软件工程和系统架构方向

lite.ai.toolkit

🛠 A lite C++ toolkit of awesome AI models, support ONNXRuntime, MNN. Contains YOLOv5, YOLOv6, YOLOX, YOLOR, FaceDet, HeadSeg, HeadPose, Matting etc. Engine: ONNXRuntime, MNN.

mmdeploy

OpenMMLab Model Deployment Framework

micronet

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

face-parsing.PyTorch

Using modified BiSeNet for face parsing in PyTorch

proxylessnas

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

mmrazor

OpenMMLab Model Compression Toolbox and Benchmark.

MPRNet

[CVPR 2021] Multi-Stage Progressive Image Restoration. SOTA results for Image deblurring, deraining, and denoising.

awesome-algorithm-question-solution

LeetCode，《剑指offer》中的算法题的题目和解法以及常见算法的实现

YOLOv5-Multibackbone-Compression

YOLOv5 Series Multi-backbone(TPH-YOLOv5, Ghostnet, ShuffleNetv2, Mobilenetv3Small, EfficientNetLite, PP-LCNet, SwinTransformer YOLO), Module(CBAM, DCN), Pruning (EagleEye, Network Slimming), Quantization (MQBench) and Deployment (TensorRT, ncnn) Compression Tool Box.

MNN-APPLICATIONS

MNN applications by MNN, JNI exec, RK3399. Support tflite\tensorflow\caffe\onnx models.

Segmentation-Pytorch

Semantic Segmentation in Pytorch. Network include: FCN、FCN_ResNet、SegNet、UNet、BiSeNet、BiSeNetV2、PSPNet、DeepLabv3_plus、 HRNet、DDRNet

United-Perception

United Perception

imagecorruptions

Python package to corrupt arbitrary images.

ArmNeonOptimization

Arm neon optimization practice

Attention_ocr.pytorch

This repository implements the the encoder and decoder model with attention model for OCR

BRECQ

Pytorch implementation of BRECQ, ICLR 2021

yolov5

YOLOv5 in PyTorch > ONNX > CoreML > iOS

RMNet

RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

PyAnomaly

Useful Toolbox for Anomaly Detection

mmdetection

OpenVINO Training Extensions Object Detection

SOLOV2_ncnn

the C++ version of solov2 with ncnn

segmentation-learning-experiment-pytorch

基于Pytorch实现优秀的自然图像分割框架！(包括FCN、U-Net和Deeplab)

mqbench-paper

model-quantization

Collections of model quantization algorithms. Any issues, please contact Peng Chen (blueardour@gmail.com)

ONNX-to-TFLite

Converting the ONNX model representation to the TensorFlow Lite representation.

mnn-yolov5

Imported from https://gitee.com/techshoww/mnn-yolov5.

simple-int8-pytorch-implement

int8 calibration implement and inference (help you understand int8 Q)