Pinned Repositories
Action-Recognition
Action Recongition Using STIP and BoW/SVM pipeline
blitznet
Deep neural network for object detection and semantic segmentation in real-time. Official code for the paper "BlitzNet: A Real-Time Deep Network for Scene Understanding"
deepframeworks
Evaluation of Deep Learning Frameworks
deepstream-occupancy-analytics
This is a sample application for counting people entering/leaving in a building using NVIDIA Deepstream SDK, Transfer Learning Toolkit (TLT), and pre-trained models. This application can be used to build real-time occupancy analytics applications for smart buildings, hospitals, retail, etc. The application is based on deepstream-test5 sample application.
Face
Face
FacialExpressions
Comparison of classification algorithms for the task of Facial Expression Recognition. Also includes real-time Facial Expression Recognition via screen capture (Dlib 18.18, OpenCV 2.4.11/3.1, SVM+MLP+AdaBoost+NBayes).
FairMOT_TensorRT
FairMOT_TensorRT_C
MpRL-for-person-re-ID
Code for paper "Multi-Pseudo Regularized Label for Generated Data in Person Re-Identification"
tensorRT_cpp
C++ library based on tensorrt integration
xjsxujingsong's Repositories
xjsxujingsong/FairMOT_TensorRT
xjsxujingsong/FairMOT_TensorRT_C
xjsxujingsong/tensorRT_cpp
C++ library based on tensorrt integration
xjsxujingsong/A-series-of-CV
xjsxujingsong/AerialDetection
xjsxujingsong/Awesome-Crowd-Counting
Awesome Crowd Counting
xjsxujingsong/BeyondBoundingBox
xjsxujingsong/cpp-learning
xjsxujingsong/Cpp17
本书为《C++17 the complete guide》的个人中文翻译，仅供学习和交流使用，侵删
xjsxujingsong/CTracker
xjsxujingsong/EffectiveModernCppChinese
《Effective Modern C++》翻译 - 已完成
xjsxujingsong/FIDTM
Focal Inverse Distance Transform Maps for Crowd Localization and Counting in Dense Crowd
xjsxujingsong/infer
A new tensorrt integrate.
xjsxujingsong/jetson-utils
C++/CUDA/Python multimedia utilities for NVIDIA Jetson
xjsxujingsong/K-Net
[NeurIPS2021] Code Release of K-Net: Towards Unified Image Segmentation
xjsxujingsong/learning-cuda-trt
A large number of cuda/tensorrt cases . 大量案例来学习cuda/tensorrt
xjsxujingsong/LSNet
Location-Sensitive Visual Recognition with Cross-IOU Loss
xjsxujingsong/MLOps-Basics
xjsxujingsong/pytorch-image-models
PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, EfficientNetV2, NFNet, Vision Transformer, MixNet, MobileNet-V3/V2, RegNet, DPN, CSPNet, and more
xjsxujingsong/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
xjsxujingsong/ReDet
Official code of the paper "ReDet: A Rotation-equivariant Detector for Aerial Object Detection" (CVPR 2021)
xjsxujingsong/Rotated_IoU
Differentiable IoU of rotated bounding boxes using Pytorch
xjsxujingsong/shufflev2-yolov5
🍅🍅🍅shufflev2-yolov5: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 1.7M (int8) and 3.3M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~
xjsxujingsong/spsg
xjsxujingsong/tensorRT_Pro-YOLOv8
This repository is based on shouxieai/tensorRT_Pro, with adjustments to support YOLOv8.
xjsxujingsong/tensorRT_Pro_co-comments
xjsxujingsong/TraDeS
Track to Detect and Segment: An Online Multi-Object Tracker (CVPR 2021)
xjsxujingsong/yolor
implementation of paper - You Only Learn One Representation: Unified Network for Multiple Tasks (https://arxiv.org/abs/2105.04206)
xjsxujingsong/YOLOv8-TensorRT-CPP
YOLOv8 TensorRT C++ Implementation
xjsxujingsong/yoltv4
Better, faster, peering over yonder. Improved large scale object detection in aerial/satellite imagery.