This is an implementation of Mask R-CNN on Python 3, Keras, and TensorFlow. The model generates bounding boxes and segmentation masks for each instance of an object in the image. It's based on Feature Pyramid Network (FPN) and a ResNet101 backbone.

use cpu ,epochs 5

Windows/Linux + Keras >= 2.0.8 + TensorFlow >= 1.3.0
pip install -r requirements.txt

pip install labelme
labelme
mkdir train_data
train_data
    |-json
    |-labelme_json
    |-pic
    |-cv2_mask

• Details:(https://www.cnblogs.com/houyong/p/10266228.html)

mask_rcnn_coco.h5

• BaiDuYun:https://pan.baidu.com/s/1CmcfVleyw7QpVZRo3JxS2w code:tf7f

python train_shape.py

python test_shape.py