The easiest way is to open the colab notebook.

The following instruction is optional and only useful if you want to run locally.

Require Python 3.5+ and Jupyter notebook installed

git clone https://github.com/Tony607/colab-mask-rcnn

pip3 install -r requirements.txt

Since this notebook already contains cells to install pycocotools using Linux command. Alternatively if you are using Windows PC, you can install it manually.

• NOTE: pycocotools requires Visual C++ 2017 Build Tools
• Clone this repo.

git clone https://github.com/philferriere/cocoapi.git

• Use pip to install pycocotools.

pip install git+https://github.com/philferriere/cocoapi.git#subdirectory=PythonAPI

In the project start a command line run

jupyter notebook

In the opened browser window open

Colab_Mask_R_CNN_Demo.ipynb