ChenYingpeng / Caffe Yolov3
A real-time object detection framework of Yolov3/v4 based on caffe
Stars: ✭ 435
Projects that are alternatives of or similar to Caffe Yolov3
Mobilenet Yolo
A caffe implementation of MobileNet-YOLO detection network
Stars: ✭ 825 (+89.66%)
Mutual labels: caffe, yolov3
Darknet2caffe
Convert darknet weights to caffemodel
Stars: ✭ 127 (-70.8%)
Mutual labels: caffe, yolov3
Multi Object Tracker
Multi-object trackers in Python
Stars: ✭ 451 (+3.68%)
Mutual labels: caffe, yolov3
Caffe Yolov3 Windows
A windows caffe implementation of YOLO detection network
Stars: ✭ 210 (-51.72%)
Mutual labels: caffe, yolov3
Msnhnet
🔥 (yolov3 yolov4 yolov5 unet ...)A mini pytorch inference framework which inspired from darknet.
Stars: ✭ 357 (-17.93%)
Mutual labels: yolov3
Trainyourownyolo
Train a state-of-the-art yolov3 object detector from scratch!
Stars: ✭ 399 (-8.28%)
Mutual labels: yolov3
Mtcnn
全平台实时人脸检测和姿态估计，提供无需任何框架实现Realtime Face Detection and Head pose estimation on Windows、Ubuntu、Mac、Android and iOS
Stars: ✭ 351 (-19.31%)
Mutual labels: caffe
O Cnn
O-CNN: Octree-based Convolutional Neural Networks for 3D Shape Analysis
Stars: ✭ 432 (-0.69%)
Mutual labels: caffe
Pytorch Caffe
load caffe prototxt and weights directly in pytorch
Stars: ✭ 407 (-6.44%)
Mutual labels: caffe
Normface
NormFace: L2 HyperSphere Embedding for Face Verification, 99.21% on LFW
Stars: ✭ 359 (-17.47%)
Mutual labels: caffe
Centerx
This repo is implemented based on detectron2 and centernet
Stars: ✭ 403 (-7.36%)
Mutual labels: caffe
Cnn Models
ImageNet pre-trained models with batch normalization for the Caffe framework
Stars: ✭ 355 (-18.39%)
Mutual labels: caffe
Densenet Caffe
DenseNet Caffe Models, converted from https://github.com/liuzhuang13/DenseNet
Stars: ✭ 350 (-19.54%)
Mutual labels: caffe
Invoice
增值税发票OCR识别，使用flask微服务架构，识别type：增值税电子普通发票，增值税普通发票，增值税专用发票；识别字段为：发票代码、发票号码、开票日期、校验码、税后金额等
Stars: ✭ 381 (-12.41%)
Mutual labels: yolov3
Gocv
Go package for computer vision using OpenCV 4 and beyond.
Stars: ✭ 4,511 (+937.01%)
Mutual labels: caffe
Vpgnet
VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition (ICCV 2017)
Stars: ✭ 382 (-12.18%)
Mutual labels: caffe
caffe-yolov3
Paltform
Have tested on Ubuntu16.04LTS with Jetson-TX2 and Ubuntu16.04LTS with gtx1060;
NOTE: You need change CMakeList.txt on Ubuntu16.04LTS with GTX1060.
Install
git clone https://github.com/ChenYingpeng/caffe-yolov3
cd caffe-yolov3
mkdir build
cd build
cmake ..
make -j6
Darknet2Caffe
darknet2caffe link github
Demo
First,download model and put it into dir caffemodel.
$ ./x86_64/bin/demo ../prototxt/yolov4.prototxt ../caffemodel/yolov4.caffemodel ../images/dog.jpg
Eval
- Run
$
./x86_64/bin/eval ../prototxt/yolov4.prototxt ../caffemodel/yolov4.caffemodel /path/to/coco/val2017/
generate coco_results.json on results/.
-
Run $
python coco_eval/coco_eval.py --gt-json path/to/coco/annotations/instances_val2017.json --pred-json results/coco_results.json -
Eval results Yolov4 input size 608x608 from this repo.
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.428
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.664
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.461
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.241
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.492
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.575
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.331
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.517
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.544
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.363
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.609
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.710
- Eval results Yolov4 input size 608x608 from offical model AlexeyAB/YoloV4.
Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.505
Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.749
Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.557
Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.357
Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.559
Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.613
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.368
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.598
Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.634
Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.500
Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.680
Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.757
Download Model
Baidu link model
Note
1.Only inference on GPU platform,such as RTX2080, GTX1060,Jetson Tegra X1,TX2,nano,Xavier etc.
2.Support model such as yolov4,yolov3,yolov3-spp,yolov3-tiny etc.
References
Appreciate the great work from the following repositories:
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].