-
Notifications
You must be signed in to change notification settings - Fork 442
Home
The purpose of this project was provide a platform which can change backbone easily. So I select the caffe framework and write down my training history here.
Enjoy it
- Install dependency
- Following below command
> git clone https://github.com/eric612/MobileNet-YOLO.git
> cd $MobileNet-YOLO_root/
> mkdir build`
> cd build
> cmake ..
> make -j4
> make pycaffe
docker pull eric612/mobilenet-yolo
docker run -it eric612/mobilenet-yolo
> cd $caffe_root/
> sh scripts/demo_yolo_lite.sh
Download lmdb
Unzip into $caffe_root/
Please check the path exist
"$caffe_root\examples\VOC0712\VOC0712_trainval_lmdb"
"$caffe_root\examples\VOC0712\VOC0712_test_lmdb"
Download pre-trained weights, and save at $caffe_root\models\MobileNet
> cd $caffe_root/
> sh scripts/train_yolov3_lite.sh
Modify classes , thanks for PiyalGeorge
Generate anchors to increase performance
An example python code to generate yolo prototxt
https://github.com/eric612/MobileNet-YOLO/issues/167
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) How to use
- 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)
See issue #16
ncnn,tensortRT,jetson tx 2 , ... , my collection link
undefined reference to `TIFFReadRGBAStrip@LIBTIFF_4.0' and others