Faster-RCNN_TF

This is an experimental Tensorflow implementation of Faster RCNN - a convnet for object detection with a region proposal network. For details about R-CNN please refer to the paper Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks by Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun.

Requirements: software

1. Requirements for Tensorflow (see: Tensorflow)

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

Requirements: hardware

1. For training the end-to-end version of Faster R-CNN with VGG16, 3G of GPU memory is sufficient (using CUDNN)

Installation (sufficient for the demo)

1. Clone the Faster R-CNN repository

# Make sure to clone with --recursive
git clone --recursive https://github.com/smallcorgi/Faster-RCNN_TF.git

2. Build the Cython modules

   cd $FRCN_ROOT/lib
   make

Demo

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

Download model training on PASCAL VOC 2007 [Google Drive] [Dropbox]

To run the demo

cd $FRCN_ROOT
python ./tools/demo.py --model model_path

The demo performs detection using a VGG16 network trained for detection on PASCAL VOC 2007.

Training Model

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

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

2. Extract all of these tars into one directory named VOCdevkit

   tar xvf VOCtrainval_06-Nov-2007.tar
   tar xvf VOCtest_06-Nov-2007.tar
   tar 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 $FRCN_ROOT/data
   ln -s $VOCdevkit VOCdevkit2007

5. Download pre-trained ImageNet models

   Download the pre-trained ImageNet models (https://github.com/tensorlayer/pretrained-models/blob/master/models/vgg16_weights.npz)

   mv vgg16_weights.npz $FRCN_ROOT/data/pretrain_model/vgg16_weights.npz

6. Run script to train and test model #Shell #cd $FRCN_ROOT #./experiments/scripts/faster_rcnn_end2end.sh $DEVICE $DEVICE_ID VGG16 pascal_voc # Train code python ./tools/main_train.py --device DEVICE --device_id 0 --weights data/pretrain_model/vgg16_weights.npz --imdb voc_2007_trainval --iters 70000 --cfg experiments/cfgs/faster_rcnn_end2end.yml --network VGGnet_train

Test code python ./tools/main_test.py --device DEVICE --device_id 0 --weights weights_file --cfg experiments/cfgs/faster_rcnn_end2end.yml --imdb voc_2007_test --network VGGnet_test

DEVICE is either cpu/gpu

The result of testing on PASCAL VOC 2007

Classes	AP
aeroplane	0.698
bicycle	0.788
bird	0.657
boat	0.565
bottle	0.478
bus	0.762
car	0.797
cat	0.793
chair	0.479
cow	0.724
diningtable	0.648
dog	0.803
horse	0.797
motorbike	0.732
person	0.770
pottedplant	0.384
sheep	0.664
sofa	0.650
train	0.766
tvmonitor	0.666
mAP	0.681

###References Faster R-CNN caffe version

A tensorflow implementation of SubCNN (working progress)