Repository files navigation

Structure Inference Net: Object Detection Using Scene-level Context and Instance-level Relationships. In CVPR 2018.(http://vipl.ict.ac.cn/uploadfile/upload/2018041318013480.pdf)

1. Requirements for Tensorflow 1.3.0 (see:Tensorflow)

2. Python packages you might not have:cython,python-opencv,easydict

1. Clone the SIN repository

# Make sure to clone with --recursivegit clone --recursive https://github.com/choasUp/SIN.git

2. Build the Cython modules

cd$SIN_ROOT/libmake

After successfully completingbasic installation, you'll be ready to run the demo.

Wait ...

1. Download the training, validation, test data and VOCdevkit

   wget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtrainval_06-Nov-2007.tarwget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCtest_06-Nov-2007.tarwget http://host.robots.ox.ac.uk/pascal/VOC/voc2007/VOCdevkit_08-Jun-2007.tar

2. Extract all of these tars into one directory namedVOCdevkit

   tar xvf VOCtrainval_06-Nov-2007.tartar xvf VOCtest_06-Nov-2007.tartar xvf VOCdevkit_08-Jun-2007.tar

3. It should have this basic structure

   $VOCdevkit/# development kit$VOCdevkit/VOCcode/# VOC utility code$VOCdevkit/VOC2007# image sets, annotations, etc.# ... and several other directories ...

4. Create symlinks for the PASCAL VOC dataset

   cd$SIN_ROOT/dataln -s$VOCdevkit VOCdevkit

5. Download the pre-trained ImageNet models[Google Drive][Dropbox]

    mv VGG_imagenet.npy$SIN_ROOT/data/pretrain_model/VGG_imagenet.npy

6. [optional] Set learning rate and max iter

   vim experiments/scripts/faster_rcnn_end2end.sh# ITERSvim lib/fast/config.py# LRcd lib# if you edit the code, make bestmake

7. Set your GPU id, then run script to train and test model

   cd$SIN_ROOTexport CUDA_VISIBLE_DEVICSE=0./train.sh

8. Test your dataset

   ./test_all.sh

AP for aeroplane = 0.7853AP for bicycle = 0.8045AP for bird = 0.7456AP for boat = 0.6657AP for bottle = 0.6144AP for bus = 0.8424AP for car = 0.8663AP for cat = 0.8894AP for chair = 0.5803AP for cow = 0.8466AP for diningtable = 0.7171AP for dog = 0.8578AP for horse = 0.8626AP for motorbike = 0.7802AP for person = 0.7857AP for pottedplant = 0.4869AP for sheep = 0.7599AP for sofa = 0.7351AP for train = 0.8199AP for tvmonitor = 0.7683Mean AP = 0.7607

Faster R-CNN caffe version

Faster R-CNN tf version

Yong Liu, Ruiping Wang, Shiguang Shan, and Xilin Chen. Structure Inference Net: Object Detection Using Scene-level Context and Instance-level Relationships. In CVPR 2018.