MobileNet-YOLO Caffe
A caffe implementation of MobileNet-YOLO detection network , train on 07+12 , test on VOC2007
| Network |
mAP |
Resolution |
Download |
NetScope |
Inference time (GTX 1080) |
Inference time (i5-7500) |
| MobileNetV2-YOLOv3 |
71.5 |
352 |
caffemodel |
graph |
6.65 ms |
217 ms |
- 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
Update
CNN Analyzer
Use this tool to compare macc and param , train on 07+12 , test on VOC2007
| network |
mAP |
resolution |
macc |
param |
pruned |
IOU_THRESH |
GIOU |
| MobileNetV2-YOLOv3 |
0.707 |
352 |
1.22G |
4.05M |
N |
N |
N |
| MobileNetV2-YOLOv3 |
0.715 |
352 |
1.22G |
4.05M |
N |
Y |
Y |
| MobileNetV2-YOLOv3 |
0.702 |
352 |
1.01G |
2.88M |
Y |
N |
N |
| Pelee-SSD |
0.709 |
304 |
1.2G |
5.42M |
N |
N |
N |
| Mobilenet-SSD |
0.68 |
300 |
1.21G |
5.43M |
N |
N |
N |
| MobilenetV2-SSD-lite |
0.709 |
336 |
1.10G |
5.2M |
N |
N |
N |
- MobileNetV2-YOLOv3 and MobilenetV2-SSD-lite were not offcial model
Coverted TensorRT models
TensorRT-Yolov3-models
Pelee-Driverable_Maps, run 89 ms on jetson nano , running project
YOLO Segmentation
How to use
Windows Version
Caffe-YOLOv3-Windows
Oringinal darknet-yolov3
Converter
test on coco_minival_lmdb (IOU 0.5)
Supported on Netron , browser version
Build , Run and Training
See wiki
See docker
License and Citation
Please cite MobileNet-YOLO in your publications if it helps your research:
@article{MobileNet-YOLO,
Author = {eric612 , Avisonic , ELAN},
Year = {2018}
}
Reference
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
Acknowledgements
https://github.com/AlexeyAB/darknet
评论