https://github.com/charlesshang/fastmaskrcnn

Mask RCNN in TensorFlow
https://github.com/charlesshang/fastmaskrcnn

coco detection fasterrcnn maskrcnn pfn rcnn segmentation tensorflow

Last synced: 3 days ago
JSON representation

Mask RCNN in TensorFlow

• Host: GitHub
• URL: https://github.com/charlesshang/fastmaskrcnn
• Owner: CharlesShang
• License: apache-2.0
• Created: 2017-03-25T15:33:21.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2021-01-05T04:08:12.000Z (over 3 years ago)
• Last Synced: 2024-10-01T00:24:16.309Z (3 days ago)
• Topics: coco, detection, fasterrcnn, maskrcnn, pfn, rcnn, segmentation, tensorflow
• Language: Python
• Size: 498 KB
• Stars: 3,096
• Watchers: 223
• Forks: 1,101
• Open Issues: 142
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Mask RCNN

Mask RCNN in TensorFlow

This repo attempts to reproduce this amazing work by Kaiming He et al. : 

[Mask R-CNN](https://arxiv.org/abs/1703.06870)

## Requirements

- [Tensorflow (>= 1.0.0)](https://www.tensorflow.org/install/install_linux)

- [Numpy](https://github.com/numpy/numpy/blob/master/INSTALL.rst.txt)

- [COCO dataset](http://mscoco.org/dataset/#download)

- [Resnet50](http://download.tensorflow.org/models/resnet_v1_50_2016_08_28.tar.gz)

## How-to

1. Go to `./libs/datasets/pycocotools` and run `make`

2. Download [COCO](http://mscoco.org/dataset/#download) 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:

- [x] ROIAlign

- [x] COCO Data Provider

- [x] Resnet50

- [x] Feature Pyramid Network

- [x] Anchor and ROI layer

- [x] Mask layer

- [x] Speedup anchor layer with cython

- [x] Combining all modules together.

- [x] 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 

- [TFFRCNN](https://github.com/CharlesShang/TFFRCNN)

- [py-faster-rcnn](https://github.com/rbgirshick/py-faster-rcnn) 

- [faster_rcnn](https://github.com/ShaoqingRen/faster_rcnn)

- [tf-models](https://github.com/tensorflow/models)

## License

See [LICENSE](https://github.com/CharlesShang/FastMaskRCNN/blob/master/LICENSE) for details.