Mask RCNN in TensorFlow
This repo attempts to reproduce this amazing work by Kaiming He et al. : Mask R-CNN
- Download COCO dataset, place it into
./data
, then runpython download_and_convert_data.py
to 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./data/pretrained_models/
- Go to
./libs
and runmake
- Go to
./libs/datasets/pycocotools
and runmake
- run
python train/train.py
for training - There are certainly some bugs, please report them back, and let's solve them together.
- 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
- 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.