zj463261929

darknet_mAP

测试mAP、计算anchors ./darknet detector calc_anchors ./cfg/voc_2class.data -width 960 -height 512 -num_of_clusters 12 -show ; ./darknet detector map ./cfg/voc_2class.data ./cfg/yolov3-voc_2class.cfg /opt/zhangjing/darknet/darknet-master/backup/2class_4anchor_70362_new/yolov3-voc_2class_100000.weights

detectron2-restful

detectron2-restful : pip install -U 'git+https://github.com/facebookresearch/fvcore'

image_augment-master

image augment script，python test_detect_multi_process.py 备注：数据增强后还需要删除不太好的数据，有的bbox有偏移

3D-ResNets-PyTorch

3D ResNets for Action Recognition (CVPR 2018)

caffe2_old

CHINESE-OCR

[python3.6] 运用tf实现自然场景文字检测,keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别

cocoapi

COCO API - Dataset @ http://cocodataset.org/

darknet

Convolutional Neural Networks、计算mAP、技术文档

Detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet. 作者更新了代码，用新代码训练、旧代码测试mAP。

detectron2

Detectron2 is FAIR's next-generation research platform for object detection and segmentation.

EasyDarwin

open source、high performance、industrial rtsp streaming server,a lot of optimization on streaming relay,KeyFrame cache,RESTful,and web management,also EasyDarwin support distributed load balancing,a simple streaming media cloud platform architecture.高性能开源RTSP流媒体服务器，基于go语言研发，维护和优化：RTSP推模式转发、RTSP拉模式转发、录像、检索、回放、关键帧缓存、秒开画面、RESTful接口、WEB后台管理、分布式负载均衡，基于EasyDarwin构建出了一套基础的流媒体云视频平台架构！

face_recognition

The world's simplest facial recognition api for Python and the command line

FairMOT

A simple baseline for one-shot multi-object tracking

imgaug

Image augmentation for machine learning experiments.

M2Det

M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network

mmdetection

OpenMMLab Detection Toolbox and Benchmark

mmyolo_tensorrt

models

Models and examples built with TensorFlow

Object_Detection_Tracking

Out-of-the-box code and models for CMU's object detection and tracking system for surveillance videos. Speed optimized Faster-RCNN model. Tensorflow based. Also supports EfficientDet. WACVW'20

PCN

Progressive Calibration Networks (PCN) is an accurate rotation-invariant face detector running at real-time speed on CPU, published in CVPR 2018.

Person-Attribute-Recognition-MarketDuke

A simple baseline implemented in PyTorch for pedestrian attribute recognition task, evaluating on Market-1501 and DukeMTMC-reID dataset.

pytorch-CycleGAN-and-pix2pix

Image-to-Image Translation in PyTorch

selective_search_py

Python-based implementation of the Selective Search for Object Recognition, back ported from Python 3 to Python 2.7

tensorrtx

Implementation of popular deep learning networks with TensorRT network definition API

text-detection-ctpn

text detection mainly based on ctpn model in tensorflow, id card detect, connectionist text proposal network

tinyengine

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory

tools

各种脚本

ultralytics

YOLOv8 🚀 in PyTorch > ONNX > CoreML > TFLite

websockets

Library for building WebSocket servers and clients in Python

YOWO

You Only Watch Once: A Unified CNN Architecture for Real-Time Spatiotemporal Action Localization