A caffe implementation of MobileNet-YOLO detection network , train on 07 12 , test on VOC2007

• inference time was log from script , does not include pre-processing
• the benchmark of cpu performance on Tencent/ncnn framework
• the deploy model was made by merge_bn.py, set eps = your prototxt batchnorm eps
• old models please see here

This project also support ssd framework , and here lists the difference from ssd caffe

• Multi-scale training , you can select input resoluton when inference
• Modified from last update caffe (2018)
• Support multi-task model
• pelee driverable map

• The pytorch version was released Mobilenet-YOLO-Pytorch

Use this tool to compare macc and param , train on 07 12 , test on VOC2007

• MobileNetV2-YOLOv3 and MobilenetV2-SSD-lite were not offcial model

TensorRT-Yolov3-models

Pelee-Driverable_Maps, run 89 ms on jetson nano , running project

How to use

Caffe-YOLOv3-Windows

Converter

test on coco_minival_lmdb (IOU 0.5)

Supported on Netron , browser version

See wiki

See docker

Please cite MobileNet-YOLO in your publications if it helps your research:

@article{MobileNet-YOLO,
  Author = {eric612 , Avisonic , ELAN},
  Year = {2018}
}

https://github.com/weiliu89/caffe/tree/ssd

https://pjreddie.com/darknet/yolo/

https://github.com/chuanqi305/MobileNet-SSD

https://github.com/gklz1982/caffe-yolov2

https://github.com/yonghenglh6/DepthwiseConvolution

https://github.com/alexgkendall/caffe-segnet

https://github.com/BVLC/caffe/pull/6384/commits/4d2400e7ae692b25f034f02ff8e8cd3621725f5c

https://www.cityscapes-dataset.com/

https://github.com/TuSimple/tusimple-benchmark/wiki

https://github.com/Robert-JunWang/Pelee

https://github.com/hujie-frank/SENet

https://github.com/lusenkong/Caffemodel_Compress

Cudnn convolution

https://github.com/chuanqi305/MobileNetv2-SSDLite/tree/master/src

https://github.com/AlexeyAB/darknet