Awesome
caffe-yolov3-windows
A caffe implementation of MobileNet-YOLO detection network , first train on COCO trainval35k then fine-tune on 07+12 , test on VOC2007
| Network | mAP | Resolution | Download | NetScope | Inference time (GTX 1080) | Inference time (i5-4440) |
|---|---|---|---|---|---|---|
| MobileNet-YOLOv3-Lite | 0.747 | 320 | caffemodel | graph | 6 ms | 150 ms |
| MobileNet-YOLOv3-Lite | 0.757 | 416 | caffemodel | graph | 11 ms | 280 ms |
- the benchmark of cpu performance on Tencent/ncnn framework
- the deploy model was made by merge_bn.py , or you can try my custom version
- bn_model download here
Linux Version
Performance
Compare with YOLO , (IOU 0.5)
| Network | mAP | Weight size | Resolution | NetScope |
|---|---|---|---|---|
| MobileNet-YOLOv3-Lite | 34.0* | 21.5 mb | 320 | graph |
| MobileNet-YOLOv3-Lite | 37.3* | 21.5 mb | 416 | graph |
| MobileNet-YOLOv3 | 40.3* | 22.5 mb | 416 | graph |
| YOLOv3-Tiny | 33.1 | 33.8 mb | 416 |
- (*) testdev-2015 server was closed , here use coco 2014 minival
Oringinal darknet-yolov3
test on coco_minival_lmdb (IOU 0.5)
| Network | mAP | Resolution | Download | NetScope |
|---|---|---|---|---|
| yolov3 | 54.4 | 416 | caffemodel | graph |
| yolov3-spp | 59.3 | 608 | caffemodel | graph |
Other models
You can find non-depthwise convolution network here , Yolo-Model-Zoo
| network | mAP | resolution | macc | param |
|---|---|---|---|---|
| PVA-YOLOv3 | 0.703 | 416 | 2.55G | 4.72M |
| Pelee-YOLOv3 | 0.703 | 416 | 4.25G | 3.85M |
Configuring and Building Caffe
Requirements
- Visual Studio 2013 or 2015
- CMake 3.4 or higher (Visual Studio and Ninja generators are supported)
- Anaconda
The build step was the same as MobileNet-SSD-windows
> cd $caffe_root
> script/build_win.cmd
Mobilenet-YOLO Demo
> cd $caffe_root/
> examples\demo_yolo_lite.cmd
If load success , you can see the image window like this
Trainning Prepare
Download lmdb
Unzip into $caffe_root/
Please check the path exist "$caffe_root\examples\VOC0712\VOC0712_trainval_lmdb"
Trainning Mobilenet-YOLOv3
> cd $caffe_root/
> examples\train_yolov3_lite.cmd
Reference
License and Citation
Please cite MobileNet-YOLO in your publications if it helps your research:
@article{MobileNet-YOLO,
Author = {eric612,Avisonic},
Year = {2018}
}