Here are implementations for paper:
HIVE-Net: Centerline-Aware HIerarchical View-Ensemble Convolutional Network for Mitochondria Segmentation in EM Images.
Contact: Zhimin Yuan (zhimin_yuan@163.com)
- Tested with Python 3.6
- CUDA 9.0 or higher
- PyTorch 1.1.0
- numpy 1.16.4
- albumentations 0.3.0
Mitochondria segmentation
- EPFL dataset: https://www.epfl.ch/labs/cvlab/data/data-em/
- Kasthuri++ dataset: https://sites.google.com/view/connectomics/home
The data augmentation library Albumentation
Run main.py
either in your favorite Python IDE or the terminal by typing:
python main.py
Run mito_prediction.py
either in your favorite Python IDE or the terminal by typing:
python mito_prediction.py