Code that implements paper "End-to-End Instance Segmentation with Recurrent Attention"
Python C++ Shell C
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
data_api remove MSCOCO Nov 1, 2017
utils initial release Apr 9, 2017
.gitignore
LICENSE Initial commit Mar 25, 2017
README.md
analysis.py initial release Apr 9, 2017
assign_model_id.py initial release Apr 9, 2017
box_model.py initial release Apr 9, 2017
box_model_read.py initial release Apr 9, 2017
box_model_train.py initial release Apr 9, 2017
cityscapes_eval.py exec Jun 11, 2017
cmd_args_parser.py initial release Apr 9, 2017
evaluation.py initial release Apr 9, 2017
experiment.py initial release Apr 9, 2017
fg_model.py
fg_model_eval.py removed patch Jun 5, 2017
fg_model_pack.py removed patch Jun 5, 2017
fg_model_train.py remove option Apr 10, 2017
full_model.py
full_model_eval.py Added cityscapes Jun 11, 2017
full_model_pack.py Added cityscapes Jun 11, 2017
full_model_read.py Added cityscapes Jun 11, 2017
full_model_train.py
hungarian.cc initial release Apr 9, 2017
hungarian_build.sh initial release Apr 9, 2017
hungarian_tf_tests.py initial release Apr 9, 2017
image_ops.py initial release Apr 9, 2017
modellib.py initial release Apr 9, 2017
nnlib.py initial release Apr 9, 2017
run_cityscapes.sh confirm evaluation script works Jun 11, 2017
run_cityscapes_eval.sh
run_cvppp.sh Added cityscapes Jun 11, 2017
run_kitti.sh confirm evaluation script works Jun 11, 2017
runner.py initial release Apr 9, 2017
setup_cityscapes.py Added cityscapes Jun 11, 2017
setup_cityscapes.sh Added cityscapes Jun 11, 2017
setup_cvppp.py Added cityscapes Jun 11, 2017
setup_cvppp.sh Added cityscapes Jun 11, 2017
setup_kitti.py initial release Apr 9, 2017
setup_kitti.sh Added cityscapes Jun 11, 2017

README.md

rec-attend-public

Code that implements paper "End-to-End Instance Segmentation with Recurrent Attention".

Dependencies

  • Python 2.7
  • TensorFlow 0.12 (not compatible with TensorFlow 1.0)
  • OpenCV
  • NumPy
  • SciPy
  • PyYaml
  • hdf5 and H5Py
  • tqdm
  • Pillow (required by cityscapes evaluation)

Installation

Compile Hungarian matching module

./hungarian_build.sh

CVPPP Experiments

First modify setup_cvppp.sh with your dataset folder paths.

./setup_cvppp.sh

Run experiments:

./run_cvppp.sh

KITTI Experiments

First modify setup_kitti.sh with your dataset folder paths.

./setup_kitti.sh

Run experiments:

./run_cvppp.sh

Cityscapes Experiments

First modify setup_cityscapes.sh with your dataset folder paths.

./setup_cityscapes.sh

Run experiments:

./run_cityscapes.sh

Citation

If you use our code, please consider cite the following: End-to-End Instance Segmentation with Recurrent Attention. Mengye Ren, Richard S. Zemel. CVPR 2017.

@inproceedings{ren17recattend,
  author    = {Mengye Ren and Richard S. Zemel},
  title     = {End-to-End Instance Segmentation with Recurrent Attention},
  booktitle = {CVPR},
  year      = {2017}
}