Skip to content
No description, website, or topics provided.
Jupyter Notebook Python C++ C Cuda Makefile
Branch: master
Clone or download
Latest commit be0d5fb Sep 17, 2018
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
configs readme Apr 16, 2018
evaluation adding pretrained models, fixed resize issue Apr 9, 2018
model_defs cleaning Mar 10, 2018
.gitignore readme Apr 16, 2018
LICENSE.txt license Sep 17, 2018
README.md Added note about Pytorch version Jul 10, 2018
__init__.py backup Oct 24, 2017
requirements.txt
test_tdid.py adding pretrained models, fixed resize issue Apr 9, 2018
test_tdid_det4class.py for updated AVD dataset processing Mar 8, 2018
train_tdid.py adding pretrained models, fixed resize issue Apr 9, 2018
utils.py adding pretrained models, fixed resize issue Apr 9, 2018

README.md

Target Driven Instance Detection

This is an implementation of the technique described in Target Driven Instance Detection. It is written in python for use with Pytorch.

External Requirements

Installation

These instructions will setup the code and data to run our experiments on the AVD dataset. More instructions will be provided to run our other experiments or use your own data.

  1. Dependencies and Data:
  • Make sure you have Pytorch (and torchvision)
  • Get the AVD processing code, and make sure it is included in your PYTHONPATH
  • Download the AVD Data into a path of your choosing, we will refer to is as AVD_ROOT_DIR.
  • Make sure to also get the instance id map and put it in the AVD_ROOT_DIR
  • Download the target images into a path of your choosing, we will refer to is as TARGET_IMAGE_DIR.
  1. Get the code
git clone https://github.com/ammirato/target_driven_instance_detection.git
  1. Install the other requirements
cd target_driven_instance_detection/
pip install -r requirements.txt
  1. Build the cython code for anchor boxes and non-max supression
cd model_defs/
./make.sh
  1. Build the coco evaluation cython code
cd ../evaluation/cocoapi/PythonAPI/
make all
cd ../../../
  1. Convert AVD annotations to COCO format yourself, or download the converted files

To Download the files:

mkdir Data
cd Data

Download the tar here

tar -xf tdid_gt_boxes.tar

Or to convert yourself:

cd  evaluation/
#Update paths in `convert_AVDgt_to_COCOgt.py` with:
#your AVD_ROOT_DIR
#a path to save the annotations, we will call it VAL_GROUND_TRUTH_BOXES
python convert_AVDgt_to_COCOgt.py

#now update the scene_list in convert_AVDgt_to_COCOgt.py 
#to make the test set
#change the path to save the annotations, we will call it TEST_GROUND_TRUTH_BOXES
python convert_AVDgt_to_COCOgt.py
  1. Set paths configs/configAVD2.py file. See configs/README.md for details on config files. Make sure to update the config with your:

    • AVD_ROOT_DIR
    • TARGET_IMAGE_DIR
    • VAL_GROUND_TRUTH_BOXES
    • TEST_GROUND_TRUTH_BOXES
  2. Start training!

#make sure you are in root directory of project, target_driven_instance_detection/
python train_tdid.py

Trained models

Here are models trained for each of the 3 splits on the AVD dataset

Citation

Please cite our paper if you find our work useful:

@article{ammiratoTDID18,
  title = {Target Driven Instance Detection},
  author = {Ammirato, Phil, and Fu, Cheng-Yang and Shvets, Mykhailo and Kosecka, Jana and Berg, Alexander C.},
  booktitle = {arXiv:1803.04610},
  year = {2018}
}

TODO

Things to clean and add

  1. Add data and configs for GMU to AVD experiment
  2. Add data and configs for RGB-D Scenes one-shot classifcation experiment
  3. Check det4class code
  4. Clean eval by object
  5. Provide trained models
  6. make a note about downloading pretrained pytorch models
  7. How to add your own data

Improvements to system

  1. How to choose target image, multiview targt image pooling thing

Acknowledgements

This code started as a modification of a Faster-RCNN Pytorch implementation here, and still uses some of that code. (In particular the nms code).

You can’t perform that action at this time.