參考：

https://blog.csdn.net/wc781708249/article/details/79438972

Mask RCNN paper: https://arxiv.org/pdf/1703.06870.pdf

video

概述如何安裝

Step 1: create a conda virtual environment with python 3.6
Step 2: install the dependencies
Step 3: Clone the Mask_RCNN repo
Step 4: install pycocotools
Step 5: download the pre-trained weights
Step 6: Test it

Step 1: create a conda virtual environment with python 3.6

we will be using Anaconda with python 3.6.
If you don’t have Anaconda, follow this tutorial
https://www.youtube.com/watch?v=T8wK5loXkXg

conda create -n MaskRCNN python=3.6 pip

Step 2: install the dependencies

（1）place the requirements.txt in your cwdir(我使用的是下一個Mask RCNN的requirements.txt)

（2）run these commands

source actvitate MaskRCNN
pip install -r requirements.txt

Step 3: Clone the Mask_RCNN repo

git clone https://github.com/matterport/Mask_RCNN.git

Step 4: install pycocotools

（1）clone this repo

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

（2）use pip to install pycocotools

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

Step 5: download the pre-trained weights

（1）Go here https://github.com/matterport/Mask_RCNN/releases

（2）download the mask_rcnn_coco.h5 file

（3）place the file in the Mask_RCNN directory

Step 6: Test it

在jupyter中執行demo.ipynb，.ipynb只能jupyter開啟

open up the demo.ipynb and run it