This is a PyTorch implementation of Faster RCNN. This project is mainly based on py-faster-rcnn and TFFRCNN.

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.

• forward pass for detecting
• using models trained by Tensorflow
• roi pooling layer implemented by python and pytorch
• roi pooling layer with C extensions on CPU (only forward)
• roi pooling layer on GPU (forward and backward)
• backward pass for training (experimental)

1. Clone the Faster R-CNN repository

   git clone [email protected]:longcw/faster_rcnn_pytorch.git

2. Build the Cython modules for nms and the roi_pooling layer

   cd faster_rcnn_pytorch/faster_rcnn
   ./make.sh

3. Download the trained model VGGnet_fast_rcnn_iter_70000.h5 and set the model path in demo.py

4. Run demo python demo.py

NOTE: The training method in this project is still experimental.

Follow this project (TFFRCNN) to download and prepare the training, validation, test data and the VGG16 model pre-trained on ImageNet.

Since the program loading the data in faster_rcnn_pytorch/data by default, you can set the data path as following.

cd faster_rcnn_pytorch
mkdir data
cd data
ln -s $VOCdevkit VOCdevkit2007

Then you can set some hyper-parameters in train.py and training parameters in the .yml file.

You may need to train RPN and the classifier separately as described in the Faster RCNN paper and tune the loss function defined in faster_rcnn/faster_rcnn.py by yourself.