Single-Shot Refinement Neural Network for Object Detection
By Shifeng Zhang, Longyin Wen, Xiao Bian, Zhen Lei, Stan Z. Li.
Introduction
We propose a novel single-shot based detector, called RefineDet, that achieves better accuracy than two-stage methods and maintains comparable efficiency of one-stage methods. You can use the code to train/evaluate the RefineDet method for object detection. For more details, please refer to our paper.
| System | VOC2007 test mAP | FPS (Titan X) | Number of Boxes | Input resolution |
|---|---|---|---|---|
| Faster R-CNN (VGG16) | 73.2 | 7 | ~6000 | ~1000 x 600 |
| YOLO (GoogLeNet) | 63.4 | 45 | 98 | 448 x 448 |
| YOLOv2 (Darknet-19) | 78.6 | 40 | 1445 | 544 x 544 |
| SSD300* (VGG16) | 77.2 | 46 | 8732 | 300 x 300 |
| SSD512* (VGG16) | 79.8 | 19 | 24564 | 512 x 512 |
| RefineDet320 (VGG16) | 80.0 | 40 | 6375 | 320 x 320 |
| RefineDet512 (VGG16) | 81.8 | 24 | 16320 | 512 x 512 |
Note: RefineDet300+ and RefineDet512+ are evaluated with the multi-scale testing strategy. The code of the multi-scale testing has also been released in this repository.
Citing RefineDet
Please cite our paper in your publications if it helps your research:
@inproceedings{zhang2018single,
title = {Single-Shot Refinement Neural Network for Object Detection},
author = {Zhang, Shifeng and Wen, Longyin and Bian, Xiao and Lei, Zhen and Li, Stan Z.},
booktitle = {CVPR},
year = {2018}
}
Contents
Installation
- Get the code. We will call the cloned directory as
$RefineDet_ROOT.
git clone https://github.com/sfzhang15/RefineDet.git- Build the code. Please follow Caffe instruction to install all necessary packages and build it.
cd $RefineDet_ROOT
# Modify Makefile.config according to your Caffe installation.
# Make sure to include $RefineDet_ROOT/python to your PYTHONPATH.
cp Makefile.config.example Makefile.config
make all -j && make pyPreparation
-
Download fully convolutional reduced (atrous) VGGNet. By default, we assume the model is stored in
$RefineDet_ROOT/models/VGGNet/. -
Download ResNet-101. By default, we assume the model is stored in
$RefineDet_ROOT/models/ResNet/. -
Follow the data/VOC0712/README.md to download VOC2007 and VOC2012 dataset and create the LMDB file for the VOC2007 training and testing.
-
Follow the data/VOC0712Plus/README.md to download VOC2007 and VOC2012 dataset and create the LMDB file for the VOC2012 training and testing.
-
Follow the data/coco/README.md to download MS COCO dataset and create the LMDB file for the COCO training and testing.
Training
- Train your model on PASCAL VOC.
# It will create model definition files and save snapshot models in:
# - $RefineDet_ROOT/models/VGGNet/VOC0712{Plus}/refinedet_vgg16_{size}x{size}/
# and job file, log file, and the python script in:
# - $RefineDet_ROOT/jobs/VGGNet/VOC0712{Plus}/refinedet_vgg16_{size}x{size}/
python examples/refinedet/VGG16_VOC2007_320.py
python examples/refinedet/VGG16_VOC2007_512.py
python examples/refinedet/VGG16_VOC2012_320.py
python examples/refinedet/VGG16_VOC2012_512.py- Train your model on COCO.
# It will create model definition files and save snapshot models in:
# - $RefineDet_ROOT/models/{Network}/coco/refinedet_{network}_{size}x{size}/
# and job file, log file, and the python script in:
# - $RefineDet_ROOT/jobs/{Network}/coco/refinedet_{network}_{size}x{size}/
python examples/refinedet/VGG16_COCO_320.py
python examples/refinedet/VGG16_COCO_512.py
python examples/refinedet/ResNet101_COCO_320.py
python examples/refinedet/ResNet101_COCO_512.py- Train your model form COOC to VOC (Based on VGG16).
# It will extract a VOC model from a pretrained COCO model.
ipython notebook convert_model_320.ipynb
ipython notebook convert_model_512.ipynb
# It will create model definition files and save snapshot models in:
# - $RefineDet_ROOT/models/VGGNet/VOC0712{Plus}/refinedet_vgg16_{size}x{size}_ft/
# and job file, log file, and the python script in:
# - $RefineDet_ROOT/jobs/VGGNet/VOC0712{Plus}/refinedet_vgg16_{size}x{size}_ft/
python examples/refinedet/finetune_VGG16_VOC2007_320.py
python examples/refinedet/finetune_VGG16_VOC2007_512.py
python examples/refinedet/finetune_VGG16_VOC2012_320.py
python examples/refinedet/finetune_VGG16_VOC2012_512.pyEvaluation
- Build the Cython modules.
cd $RefineDet_ROOT/test/lib
make -j-
Change the ‘self._devkit_path’ in
test/lib/datasets/pascal_voc.pyto yours. -
Change the ‘self._data_path’ in
test/lib/datasets/coco.pyto yours. -
Check out
test/refinedet_demo.pyon how to detect objects using the RefineDet model and how to plot detection results.
# For GPU users
python test/refinedet_demo.py
# For CPU users
python test/refinedet_demo.py --gpu_id -1- Evaluate the trained models via
test/refinedet_test.py.
# You can modify the parameters in refinedet_test.py for different types of evaluation:
# - single_scale: True is single scale testing, False is multi_scale_testing.
# - test_set: 'voc_2007_test', 'voc_2012_test', 'coco_2014_minival', 'coco_2015_test-dev'.
# - voc_path: where the trained voc caffemodel.
# - coco_path: where the trained voc caffemodel.
# For 'voc_2007_test' and 'coco_2014_minival', it will directly output the mAP results.
# For 'voc_2012_test' and 'coco_2015_test-dev', it will save the detections and you should submitted it to the evaluation server to get the mAP results.
python test/refinedet_test.pyModels
We have provided the models that are trained from different datasets. To help reproduce the results in Table 1, Table 2, Table 4, most models contain a pretrained .caffemodel file, many .prototxt files, and python scripts.
-
PASCAL VOC models (VGG-16):
- 07+12: RefineDet320, RefineDet512
- 07++12: RefineDet320, RefineDet512
- COCO: RefineDet320, RefineDet512
- 07+12+COCO: RefineDet320, RefineDet512
- 07++12+COCO: RefineDet320, RefineDet512
-
COCO models:
- trainval35k (VGG-16): RefineDet320, RefineDet512
- trainval35k (ResNet101): RefineDet320, RefineDet512
Note: If you can not download pre-trained models through the above links, you can download them through BaiduYun.