医学图像分析的深度学习框架
SAMITorch的Python项目详细描述
samitorch
欢迎使用Samitorch
samitorch是利用PyTorch库对École de technologie supérieure医学成像实验室形状分析进行深入学习的框架。 它实现了一套广泛的装载机、变压器、模型和数据集，适用于医学成像的深入学习。 我们的目标是建立一个经过测试的标准框架，以便在应用于医学成像的深度学习研究中快速产生结果。
目录
作者
- 皮埃尔卢克德莱斯利-pldelisle
- 贝诺伊特·安克提尔·罗比泰尔-banctilrobitaille
参考文献
分割
@article{RN10,
author = {Çiçek, Özgün and Abdulkadir, Ahmed and Lienkamp, Soeren S. and Brox, Thomas and Ronneberger, Olaf},
title = {3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation},
journal = {eprint arXiv:1606.06650},
pages = {arXiv:1606.06650},
url = {https://ui.adsabs.harvard.edu/\#abs/2016arXiv160606650C},
year = {2016},
type = {Journal Article}
}
分类
@inproceedings{RN12,
author = {He, K. and Zhang, X. and Ren, S. and Sun, J.},
title = {Deep Residual Learning for Image Recognition},
booktitle = {2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
pages = {770-778},
ISBN = {1063-6919},
DOI = {10.1109/CVPR.2016.90},
type = {Conference Proceedings}
}
扩散成像
应用程序
设置
pip install -r [path/to/requirements.txt]
python3 <main_script>.py
项目架构
文件夹结构
── samitorch
| ├── configs - This folder contains the YAML configuration files.
| │ ├── configurations.py - This file contains the definitions of different configuration classes.
| │ |── resnet3d.yaml - Standard ResNet 3D configuration file and model definition.
| │ └── unet3d.yaml - Standard UNet 3D configuration file and model definition.
| |
| ├── initializers - This folder contains custom layer/op initializers.
| | └── initializers.py
| │
| ├── inputs - This folder contains anything relative to inputs to a network.
| | |── batch.py - Contains Batch definition object used in training.
| | |── datasets.py - Contains basic dataset definition for classification and segmentation.
| | |── images.py - Contains Enums for various methods.
| | |── patch.py - Contains Patch definition used in segmentation problems.
| | |── sample.py - Contains a Sample object.
| | |── transformers.py - Contains a series of common transformations.
| | └── utils.py - Contains various utilitary methods.
| |
| ├── models - This folder contains any standard and tested deep learning models.
| │ |── layers.py - Contains layer definitions.
| | |── resnet3d.py - Contains a standard ResNet 3D model.
| | └── unet3d.py - Contains a standard UNet 3D model.
| |
| |── parsers - This folder contains parsers definition used in SAMITorch.
| |
| ├── preprocessing - This folder contains anything relative to input preprocessing, and scripts that must be executed prior training.
| |
| └── utils - This folder contains any utils you may need.
| |── files.py - Contains file related utils methods.
| |── slice_builder.py - Contains an object to build slices out of a data sets (for image segmentation).
| └── tensors.py - Contains tensor related utils methods.
── tests - Folder containing unit tests of the standard framework api and functions.
主要部件
@inproceedings{RN12,
author = {He, K. and Zhang, X. and Ren, S. and Sun, J.},
title = {Deep Residual Learning for Image Recognition},
booktitle = {2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
pages = {770-778},
ISBN = {1063-6919},
DOI = {10.1109/CVPR.2016.90},
type = {Conference Proceedings}
}
应用程序
设置
pip install -r [path/to/requirements.txt]
python3 <main_script>.py
项目架构
文件夹结构
── samitorch
| ├── configs - This folder contains the YAML configuration files.
| │ ├── configurations.py - This file contains the definitions of different configuration classes.
| │ |── resnet3d.yaml - Standard ResNet 3D configuration file and model definition.
| │ └── unet3d.yaml - Standard UNet 3D configuration file and model definition.
| |
| ├── initializers - This folder contains custom layer/op initializers.
| | └── initializers.py
| │
| ├── inputs - This folder contains anything relative to inputs to a network.
| | |── batch.py - Contains Batch definition object used in training.
| | |── datasets.py - Contains basic dataset definition for classification and segmentation.
| | |── images.py - Contains Enums for various methods.
| | |── patch.py - Contains Patch definition used in segmentation problems.
| | |── sample.py - Contains a Sample object.
| | |── transformers.py - Contains a series of common transformations.
| | └── utils.py - Contains various utilitary methods.
| |
| ├── models - This folder contains any standard and tested deep learning models.
| │ |── layers.py - Contains layer definitions.
| | |── resnet3d.py - Contains a standard ResNet 3D model.
| | └── unet3d.py - Contains a standard UNet 3D model.
| |
| |── parsers - This folder contains parsers definition used in SAMITorch.
| |
| ├── preprocessing - This folder contains anything relative to input preprocessing, and scripts that must be executed prior training.
| |
| └── utils - This folder contains any utils you may need.
| |── files.py - Contains file related utils methods.
| |── slice_builder.py - Contains an object to build slices out of a data sets (for image segmentation).
| └── tensors.py - Contains tensor related utils methods.
── tests - Folder containing unit tests of the standard framework api and functions.
主要部件
（稍后将记录…）
型号
变压器
配置
main
贡献
main
贡献
如果您发现了一个bug或有改进的想法，请首先查看我们的contribution guideline。然后，
- [X]按功能和/或错误修复创建分支
- [X]获取代码
- [X]提交并按下
- [X]创建拉取请求
分支命名
| Instance | Branch | Description, Instructions, Notes |
|---|---|---|
| Stable | stable | Accepts merges from Development and Hotfixes |
| Development | dev/ [Short description] [Issue number] | Accepts merges from Features / Issues and Hotfixes |
| Features/Issues | feature/ [Short feature description] [Issue number] | Always branch off HEAD or dev/ |
| Hotfix | fix/ [Short feature description] [Issue number] | Always branch off Stable |
提交语法
添加代码：
+ Added [Short Description] [Issue Number]
删除代码：
- Deleted [Short Description] [Issue Number]
修改代码：
* Changed [Short Description] [Issue Number]
合并分支：
Y Merged [Short Description]
生成文档
Samitorch使用Sphinx文档。要生成doc，只需执行以下操作：
cd docs
sphinx-build -b html source build
确认
感谢École de technologie supérieure、Hervé Lombaert和Christian Desrosiers为我们提供了一个实验室并帮助我们进行研究活动。
由Freepik从www.flaticon.com制作的图标由CC 3.0 BY授权
欢迎加入QQ群-->： 979659372
