chaucerg Goto Github PK

pytorch.onnx.tensorrt

resnet50. pytorch->onnx->tensorrt

pytorch_classification

利用pytorch实现图像分类的一个完整的代码，训练，预测，TTA，模型融合，模型部署，cnn提取特征，svm或者随机森林等进行分类，模型蒸馏，一个完整的代码

pytorchinsight

a pytorch lib with state-of-the-art architectures, pretrained models and real-time updated results

pytorchnethub

项目注释+论文复现+算法竞赛+Pytorch指北

pytorchocr

基于pytorch的ocr算法库，包括 psenet, pan, dbnet, sast , crnn

qtguidemo

QT GUI DEMO

real-world-masked-face-dataset

Real-World Masked Face Dataset，口罩人脸数据集

repvgg_tensorrt_int8

RepVGG TensorRT int8 量化，实测推理不到1ms一帧！

research

novel deep learning research works with PaddlePaddle

sa-mobilenetv3

Shuffle Attention for MobileNetV3

simple-reid

smart_construction

Head Person Helmet Detection on Construction Sites，基于目标检测工地安全帽和禁入危险区域识别系统，🚀😆附 YOLOv5 训练自己的数据集超详细教程🚀😆2021.3新增可视化界面❗❗

smoke

SMOKE: Single-Stage Monocular 3D Object Detection via Keypoint Estimation

softmax_variants

PyTorch code for softmax variants: center loss, cosface loss, large-margin gaussian mixture, COCOLoss, ring loss

tensorflow2-machine-vision

基于tensorflow2的yolov3、yolov4、efficientdet实现

tensorrt

TensorRT-7 Network Lib 包括常用目标检测、关键点检测、人脸检测、OCR等 可训练自己数据

tensorrt7-dcnv2-plugin

基于TensorRT7实现DCNv2插件

tensorrt_cpp

C++ library based on tensorrt integration

tensorrt_ex

Deep Learning Model Optimization Using by TensorRT API

tensorrt_tutorial

tiny-tensorrt

A simple, efficient, easy-to-use Nvidia TensorRT wrapper for CNN, support c++ and python.

traffic-signs-detection-tensorflow-yolov3-yolov4

Final Project for Applications of Machine Learning in Mechatronic Systems

transformer-in-computer-vision

A paper list of some recent Transformer-based CV works.

transreid

TransReID: Transformer-based Object Re-Identification

trt-samples-for-hackathon-cn

Simple samples for TensorRT programming

tvm_mlir_learn

tvm learn

vedadet

A single stage object detection toolbox based on PyTorch

vedaseg

A semantic segmentation toolbox based on PyTorch

vehicle-distance-detection

Using Perspective Transform to leverage bird's eye view (BEV) to estimate distance between objects.

vehicle_recognition

一种运用resnet进行车型识别的方法，