This is an implementation of Mask R-CNN on Python 3, Keras, and TensorFlow. It is based on Feature Pyramid Network (FPN) and a ResNet101 backbone.
Masked RCNN applied on CD1 white mouse and C57 black mouse
There are multiple ways to do this. Below is one of it.
-
Label the animals using labelme
-
Convert .json / images generated by labelme to coco using labelm2coco.py
-
Convert coco.json to tf_record by using create_coco_tf_record
-
Run RCNN training by running model_main.py
- numpy
- scipy
- Pillow
- cython
- matplotlib
- scikit-image
- tensorflow>=1.3.0
- keras>=2.0.8
- opencv-python
- h5py
- imgaug
- IPython