Download coco dataset, place it into ./data, then run python 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 run make
run python train/train.py for training
There are certainly some bugs, please report them back, and let’s solve them together.
Anything helps this repo, including discussion, testing, promotion and of course your awesome code.
https://github.com/CharlesShang/FastMaskRCNN
https://github.com/TuSimple/mx-maskrcnn
https://github.com/CharlesShang/FastMaskRCNN
CAFFE :https://github.com/jasjeetIM/Mask-RCNN
http://blog.leanote.com/post/afanti.deng@gmail.com/b5f4f526490b
http://blog.csdn.net/xiamentingtao/article/details/78598511
http://blog.csdn.net/zchang81/article/details/78361897 Mask R-CNN的完整MXNet复现Github 项目地址:https://github.com/TuSimple/mx-maskrcnn