Mask RCNN in TensorFlow
This repo attempts to reproduce this amazing work by Kaiming He et al. : Mask R-CNN
- Go to
- Download COCO dataset, place it into
./data, then run
python download_and_convert_data.pyto build tf-records. It takes a while.
- Download pretrained resnet50 model,
wget http://download.tensorflow.org/models/resnet_v1_50_2016_08_28.tar.gz, unzip it, place it into
- Go to
python train/train.pyfor training
- There are certainly some bugs, please report them back, and let's solve them together.
- COCO Data Provider
- 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.
This repo borrows tons of code from
See LICENSE for details.