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 | 74.6 | 320 | caffemodel | graph | 4.79 ms | 150 ms |
MobileNet-YOLOv3-Lite | 76.3 | 416 | caffemodel | graph | 6.52 ms | 280 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 , or you can try my custom version
- bn_model download here
Currently , the fatest model in caffe of this project
Network | Resolution | Inference time (GTX 1080) |
---|---|---|
MobileNet-YOLOv3-trt | 416 | 4.78 ms |
MobileNet-YOLOv3-trt | 320 | 3.20 ms |
Note :
not test in tensorRT yet , contribution is welcome , if you can help me to test
I use the following training path to improve accuracy , and decrease lite version trainning time
- First , train MobileNet-YOLOv3 on coco dataset (IOU_0.5 : 40.2 mAP)
- Second , train MobileNet-YOLOv3-Lite on coco dataset , pretrain weights use the first step output (IOU_0.5 : 38.9 mAP)
- Finally , train MobileNet-YOLOv3-Lite on voc dataset , pretrain weights use the second step output (76.3 mAP)
test on coco_minival_lmdb (IOU 0.5)
Network | mAP | Resolution | Download | NetScope |
---|---|---|---|---|
yolov3 | 54.2 | 416 | caffemodel | graph |
yolov3-spp | 59.8 | 608 | caffemodel | graph |
- I haven't implement correct_yolo_boxes and relative function , so here only support square input resolution
Train on COCO trainval35k (2014) , and compare with YOLO , (IOU 0.5)
Network | IOU 0.5:0.95 | IOU 0.5 | IOU 0.75 | Weight size | Resolution | NetScope | Resize Mode |
---|---|---|---|---|---|---|---|
MobileNet-YOLOv3-Lite | 19.9 | 35.5 | 19.6 | 22.0 mb | 320 | graph | WARP |
MobileNet-YOLOv3-Lite | 21.5 | 38.9 | 21.2 | 22.0 mb | 416 | graph | WARP |
MobileNet-YOLOv3 | 22.7 | 40.2 | 22.6 | 22.5 mb | 416 | graph | LetterBox |
YOLOv3-Tiny | 33.1 | 33.8 mb | 416 | ||||
MobileNet-YOLOv3-Lite-trt | 37.5 | 23.5 mb | 416 | graph | WARP |
- (*) testdev-2015 server was closed , here use coco 2014 minival
- MobileNet-YOLOv3-Lite-trt was the fastest model
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 |
Supported on Netron , browser version
See wiki
Please cite MobileNet-YOLO in your publications if it helps your research:
@article{MobileNet-YOLO,
Author = {eric612 , Avisonic , ELAN},
Year = {2018}
}
https://github.com/BVLC/caffe/pull/6384/commits/4d2400e7ae692b25f034f02ff8e8cd3621725f5c
Cudnn convolution
https://github.com/chuanqi305/MobileNetv2-SSDLite/tree/master/src