This is a fork of MX Mask R-CNN,for convenience to test a single file
Before start, you need to download pretrained model from Mask R-CNN, and put it in directory model
.
Second, you should run make in this folder and follow instructions in Mask R-CNN to recompile mxnet.
And in the last, just run bash bash scripts/demo.sh
to show the result you want.
You can find all changes in source rcnn/tools/demo_maskrcnn.py
Enjoy!
A MXNet implementation of Mask R-CNN.
This repository is largely based on the mx-rcnn implementation of Faster RCNN available here.
Method | Training data | Test data | Average | person | rider | car | truck | bus | train | motorcycle | bicycle |
---|---|---|---|---|---|---|---|---|---|---|---|
Ours | fine-only | test | 26.9 | 33.0 | 25.7 | 47.7 | 21.6 | 27.4 | 23.0 | 19.9 | 16.9 |
Reference[5] | fine-only | test | 26.2 | 30.5 | 23.8 | 46.9 | 22.8 | 32.2 | 18.6 | 19.1 | 16.0 |
Ours | fine-only | val | 31.3 | 32.6 | 26.6 | 49.5 | 26.5 | 45.4 | 32.1 | 17.6 | 20.4 |
Reference[5] | fine-only | val | 31.5 | - | - | - | - | - | - | - | - |
- Backbone: Resnet-50-FPN
Comming soon, please stay tune.
We tested our code on:
Ubuntu 16.04, Python 2.7
numpy(1.12.1), cv2(2.4.9), PIL(4.3), matplotlib(2.1.0), cython(0.26.1), easydict
- Download Cityscapes data (gtFine_trainvaltest.zip, leftImg8bit_trainvaltest.zip). Extract them into 'data/cityscape/'. The folder then look like below:
data/cityscape/
��������� leftImg8bit/
��� ��������� train/
��� ��������� val/
��� ��������� test/
��������� gtFine/
��� ��������� train/
��� ��������� val/
��� ��������� test/
��������� imglists/
��������� train.lst
��������� val.lst
��������� test.lst
- Download Resnet-50 pretrained model.
bash scripts/download_res50.sh
- Build MXNet with ROIAlign operator.
cp rcnn/CXX_OP/* incubator-mxnet/src/operator/
To build MXNet from source, please refer to the tutorial.
- Build related cython code.
make
- Kick off training
bash scripts/train_alternate.sh
- Prepare Cityscapes evaluation scripts.
bash scripts/download_cityscapescripts.sh
- Eval
bash scripts/eval.sh
- Download model, available at Dropbox/BaiduYun, and place it in model folder.
- Make sure that you have placed cityscapes data in 'data/cityscapes' folder.
bash scripts/demo.sh
- Tianqi Chen, Mu Li, Yutian Li, Min Lin, Naiyan Wang, Minjie Wang, Tianjun Xiao, Bing Xu, Chiyuan Zhang, and Zheng Zhang. MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems. In Neural Information Processing Systems, Workshop on Machine Learning Systems, 2015
- Ross Girshick. "Fast R-CNN." In Proceedings of the IEEE International Conference on Computer Vision, 2015.
- Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. "Faster R-CNN: Towards real-time object detection with region proposal networks." In IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016.
- Tsung-Yi Lin, Piotr Doll��r, Ross Girshick, Kaiming He, Bharath Hariharan, Serge Belongie. "Feature Pyramid Networks for Object Detection." In Computer Vision and Pattern Recognition, IEEE Conference on, 2017.
- Kaiming He, Georgia Gkioxari, Piotr Doll��r, Ross Girshick. "Mask R-CNN." In Proceedings of the IEEE International Conference on Computer Vision, 2017.
- Yangqing Jia, Evan Shelhamer, Jeff Donahue, Sergey Karayev, Jonathan Long, Ross Girshick, Sergio Guadarrama, and Trevor Darrell. "Caffe: Convolutional architecture for fast feature embedding." In Proceedings of the ACM International Conference on Multimedia, 2014.
- Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. "ImageNet: A large-scale hierarchical image database." In Computer Vision and Pattern Recognition, IEEE Conference on, 2009.
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. "Deep Residual Learning for Image Recognition". In Computer Vision and Pattern Recognition, IEEE Conference on, 2016.
- Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus Enzweiler, Rodrigo Benenson, Uwe Franke, Stefan Roth, Bernt Schiele. "The Cityscapes Dataset for Semantic Urban Scene Understanding." In Computer Vision and Pattern Recognition, IEEE Conference on, 2016.