He-Zhenwei / MAF

The implementation of paper "Multi-adversarial Faster-RCNN for Unrestricted Object Detection"

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

MAF

The implementation of paper "Multi-adversarial Faster-RCNN for Unrestricted Object Detection"

This code is the implementation of our ICCV2019 work "Multi-adversarial Faster-RCNN for Unrestricted Object Detection". The paper can be found in "https://arxiv.org/abs/1907.10343".

Our code is based on the implementation of DA-Faster-RCNN (https://github.com/yuhuayc/da-faster-rcnn)

#Usage

  1. Build caffe and pycaffe.

  2. Build Cython modules.

    cd $FRCN_ROOT/lib

    make

  3. Prepare the training data following the da-faster-rcnn.

  4. Training and testing the model.

About

The implementation of paper "Multi-adversarial Faster-RCNN for Unrestricted Object Detection"


Languages

Language:Jupyter Notebook 54.8%Language:C++ 32.7%Language:Python 6.9%Language:Cuda 3.2%Language:CMake 1.2%Language:MATLAB 0.4%Language:Shell 0.3%Language:Makefile 0.3%Language:C 0.1%Language:CSS 0.1%Language:HTML 0.1%Language:Dockerfile 0.0%