paleomoon's repositories
darknet-ncnn-android
Android demo to use darknet model in ncnn.
lite-hrnet-trt
Run Lite-HRNet pose-estimation with TensorRT and C++.
BoTSORT-cpp
C++ implementation of BoT-SORT MOT algorithm
CUDA-PointPillars
A project demonstrating how to use CUDA-PointPillars to deal with cloud points data from lidar.
deep_sort_pytorch
MOT using deepsort and yolov3 with pytorch
design_patterns
图说设计模式
DrakeTyporaTheme
Drake Light Dark Vue Ayu Material Black Purple Juejin Google style for typora-theme
GreedySnake
c++经典项目贪吃蛇游戏控制台版,详细注释
hyperpose
Library for Fast and Flexible Human Pose Estimation
insightface
State-of-the-art 2D and 3D Face Analysis Project
kapao
KAPAO is a state-of-the-art single-stage human pose estimation model that detects keypoints and poses as objects and fuses the detections to predict human poses.
mobile-yolov5-pruning-distillation
mobilev2-yolov5s剪枝、蒸馏,支持ncnn,tensorRT部署。ultra-light but better performence!
MyTinySTL
Achieve a tiny STL in C++11
nanodet
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
network-slimming
Network Slimming (Pytorch) (ICCV 2017)
OpenPCDet
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
openpifpaf
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and Spatio-Temporal Association" in PyTorch.
paleomoon.github.io
paleomoon's blog
pyskl
A toolbox for skeleton-based action recognition.
spdlog
Fast C++ logging library.
tensorrtx
Implementation of popular deep learning networks with TensorRT network definition API
TinyWebServer
:fire: Linux下C++轻量级WebServer服务器
yolov3
YOLOv3 in PyTorch > ONNX > CoreML > TFLite
YOLOv3-complete-pruning
提供对YOLOv3及Tiny的多种剪枝版本,以适应不同的需求。
YOLOv3-model-pruning
在 oxford hand 数据集上对 YOLOv3 做模型剪枝(network slimming)
yolov5
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
YOLOv5-Multibackbone-Compression
YOLOv5 Series Multi-backbone(TPH-YOLOv5, Ghostnet, ShuffleNetv2, Mobilenetv3Small, EfficientNetLite, PP-LCNet, SwinTransformer YOLO), Module(CBAM, DCN), Pruning (EagleEye, Network Slimming) and Quantization (MQBench) Compression Tool Box.
yolov7
Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors