Need help with DeepBox?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

128 Stars 59 Forks Other 15 Commits 10 Opened issues


Code release for DeepBox paper in ICCV 2015

Services available


Need anything else?

Contributors list

# 522,749
2 commits

DeepBox: Learning Objectness with Convolutional Networks

Created by Weicheng Kuo at UC Berkeley


Fast DeepBox is a bounding box proposal re-ranker using ConvNets. It produces state-of-the-art bounding box proposal within 0.5s using a light-weight 4-layer network. Experiments on both PASCAL and COCO showed that DeepBox performs significantly better than Edge boxes in terms of Area under Curve and that the gain carries over to detection mAP. This implementation is based on Ross's Fast-RCNN codebase, thereby written in Python and C++/Caffe.

DeepBox was initially described in an arXiv paper and later published at ICCV 2015.


Fast DeepBox is released under the MIT License (refer to the LICENSE file for details).

Citing Fast DeepBox

If you find Fast DeepBox useful in your research, please consider citing:

    Author = {Weicheng Kuo, Bharath Hariharan, Jitendra Malik},
    Title = {DeepBox:Learning Objectness with Convolutional Networks},
    Booktitle = {International Conference on Computer Vision ({ICCV})},
    Year = {2015}


  1. Requirements: software
  2. Requirements: hardware
  3. Basic installation
  4. Demo
  5. Beyond the demo: training and testing
  6. Usage
  7. Extra downloads

Requirements: software

  1. Requirements for
    (see: Caffe installation instructions)

Note: Caffe doesn't have to be built with support for Python layers!

You can download my Makefile.config for reference. 2. Python packages you might not have:

3. MATLAB (required for running COCO evaluation)

Requirements: hardware

  1. A good GPU (e.g., Titan, K20, K40, ...) with at least 3G of memory suffices

Installation (sufficient for the demo)

  1. Clone the Fast DeepBox repository

    git clone
  2. We'll call the directory that you cloned Fast DeepBox into

  3. Build the Cython modules

    cd $FDBOX_ROOT/src
  4. Build Caffe and pycaffe ```Shell cd $FDBOX_ROOT/caffe-fast-rcnn

    Now follow the Caffe installation instructions here:

    If you're experienced with Caffe and have all of the requirements installed

    and your Makefile.config in place, then simply do:

    make -j8 && make pycaffe ```

  5. Download pre-computed Fast DeepBox models

    cd $FDBOX_ROOT/output/default

    This will populate the

    folder with
    ,which contains a variety of models. These include multiscale/single-scale Fast DeepBox models and a multiscale sliding window model for training comparison.


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


To run the demo

python ./tools/
By default, visualization only shows top five proposals per image and their scores. Users can set the number of proposals they want to visualize by passing in --numboxes [Number of proposals] argument. There is another demo mode on full COCO dataset that user can choose by passing in --demo 0 argument. This allows users to visualize Fast DeepBox proposals on any frame of users' choice in COCO validation set, but requires users to download pre-computed Edge boxes proposals and install COCO dataset in full.

Beyond the basic demo: installation for full COCO demo, training and testing models

Here are the steps to set up full functionalities of DeeBox package.

  1. Download pre-computed Edge boxes proposals

    cd $FDBOX_ROOT/data
    The Edge boxes proposals are pre-computed in order to reduce installation requirements. This step is necessary for demo.
  2. Download COCO Matlab data

    cd $FDBOX_ROOT/data
    This step downloads the Matlab COCO image ordering with which Edge boxes proposals are computed. Ground truth boxes would also be downloaded to enable evaluation.
  3. Set up Microsoft COCO directory by

    cd $FDBOX_ROOT/data
    If you haven't installed COCO on your machine yet, you can follow the instructions on the following github page to download and compile all the data. -MSCOCO
  4. Download pre-trained ImageNet models

    Pretrained ImageNet model for Alex net can be downloaded to initialize the DeepBox network training.

    cd $FDBOX_ROOT
    Alternatively, users can initialize the training with our multiscale sliding window model in


Train a Fast DeepBox proposer:

python ./tools/ (Show all training options)
python ./tools/ --gpu 0 (Train on GPU 0)

Train output is written underneath


Test a Fast DeepBox proposer:

python ./tools/ (Show all testing options)
python ./tools/ --gpu 0 (Test on GPU 0)
python ./tools/ --imdb coco_test-dev2015 (Test on Test-dev split)  

Test output is written underneath

by default. If you test on test-dev, it will be underneath coco_test-dev2015 instead.

Full Demo a pre-trained Fast DeepBox proposer on COCO val set

python ./tools/ (Show all demo options)
python ./tools/ --demo 0 --frame 0 --numboxes 5 (Demo on frame 0 of COCO val set showing top 5 proposals)

Evaluate the test result. This part is written in Matlab. First launch your Matlab in $FDBOX_ROOT. Then do the following:

cd ./eval

The evaluation output will be printed and the Recall-vs-NumOfProposals plots will be shown.


Pre-computed Fast DeepBox proposals on COCO train, val, and test-dev.

  cd $FDBOX_ROOT/data

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.