Mask RCNN in TensorFlow
Switch branches/tags
Nothing to show
Clone or download
amirbar Merge pull request #114 from Anner-deJong/patch-1
add './output/mask_rcnn' dir if missing
Latest commit bdae077 Jul 20, 2017
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data Update README.md May 19, 2017
libs Merge pull request #96 from souryuu/master Jul 9, 2017
train clean up some comments Jun 27, 2017
unit_test unit test Apr 27, 2017
.gitignore ignore Apr 22, 2017
LICENSE Initial commit Mar 25, 2017
README.md Merge pull request #40 from ycjing/master Apr 29, 2017
download_and_convert_data.py add './output/mask_rcnn' dir if missing Jul 20, 2017

README.md

Mask RCNN

Mask RCNN in TensorFlow

This repo attempts to reproduce this amazing work by Kaiming He et al. : Mask R-CNN

Requirements

How-to

  1. Go to ./libs/datasets/pycocotools and run make
  2. Download COCO dataset, place it into ./data, then run python download_and_convert_data.py to build tf-records. It takes a while.
  3. Download pretrained resnet50 model, wget http://download.tensorflow.org/models/resnet_v1_50_2016_08_28.tar.gz, unzip it, place it into ./data/pretrained_models/
  4. Go to ./libs and run make
  5. run python train/train.py for training
  6. There are certainly some bugs, please report them back, and let's solve them together.

TODO:

  • ROIAlign
  • COCO Data Provider
  • Resnet50
  • Feature Pyramid Network
  • Anchor and ROI layer
  • Mask layer
  • Speedup anchor layer with cython
  • Combining all modules together.
  • Testing and debugging (in progress)
  • Training / evaluation on COCO
  • Add image summary to show some results
  • Converting ResneXt
  • Training >2 images

Call for contributions

  • Anything helps this repo, including discussion, testing, promotion and of course your awesome code.

Acknowledgment

This repo borrows tons of code from

License

See LICENSE for details.