Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
zhuzheyi cb78b07132 | 1 year ago | |
---|---|---|
.. | ||
.github | 1 year ago | |
docs | 1 year ago | |
highresnet | 1 year ago | |
images | 1 year ago | |
tests | 1 year ago | |
.editorconfig | 1 year ago | |
.gitignore | 1 year ago | |
.pylintrc | 1 year ago | |
.travis.yml | 1 year ago | |
AUTHORS.rst | 1 year ago | |
CONTRIBUTING.rst | 1 year ago | |
GIFNiftyNet.ctbl | 1 year ago | |
HISTORY.rst | 1 year ago | |
LICENSE | 1 year ago | |
MANIFEST.in | 1 year ago | |
Makefile | 1 year ago | |
README.rst | 1 year ago | |
hubconf.py | 1 year ago | |
requirements_dev.txt | 1 year ago | |
setup.cfg | 1 year ago | |
setup.py | 1 year ago | |
tox.ini | 1 year ago |
==========
highresnet
==========
.. image:: https://img.shields.io/pypi/v/highresnet.svg
:target: https://pypi.python.org/pypi/highresnet
.. image:: https://img.shields.io/travis/fepegar/highresnet.svg
:target: https://travis-ci.org/fepegar/highresnet
.. image:: https://zenodo.org/badge/DOI/10.5281/zenodo.3349989.svg
:target: https://doi.org/10.5281/zenodo.3349989
.. image:: https://readthedocs.org/projects/highresnet/badge/?version=latest
:target: https://highresnet.readthedocs.io/en/latest/?badge=latest
:alt: Documentation Status
.. image:: https://pyup.io/repos/github/fepegar/highresnet/shield.svg
:target: https://pyup.io/repos/github/fepegar/highresnet/
:alt: Updates
::
$ NII_FILE=`download_oasis`
$ deepgif $NII_FILE
.. image:: https://raw.githubusercontent.com/fepegar/highresnet/master/images/slicer_screenshot.png
:alt: 3D Slicer screenshot
PyTorch implementation of HighRes3DNet from `Li et al. 2017,
*On the Compactness, Efficiency, and Representation of
3D Convolutional Networks: Brain Parcellation as a
Pretext Task* <https://arxiv.org/pdf/1707.01992.pdf>`_.
All the information about how the weights were ported from NiftyNet can be found
in `my submission to the MICCAI Educational Challenge
2019 <https://nbviewer.jupyter.org/github/fepegar/miccai-educational-challenge-2019/blob/master/Combining_the_power_of_PyTorch_and_NiftyNet.ipynb?flush_cache=true>`_.
Usage
-----
Command line interface
^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: shell
(deepgif) $ deepgif t1_mri.nii.gz
Using cache found in /home/fernando/.cache/torch/hub/fepegar_highresnet_master
100%|███████████████████████████████████████████| 36/36 [01:13<00:00, 2.05s/it]
`PyTorch Hub <https://pytorch.org/hub>`_
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
If you are using `pytorch>=1.1.0`, you can import the model
directly from this repository using
`PyTorch Hub <https://pytorch.org/hub>`_.
.. code-block:: python
import torch
repo = 'fepegar/highresnet'
model_name = 'highres3dnet'
print(torch.hub.help(repo, model_name))
"HighRes3DNet by Li et al. 2017 for T1-MRI brain parcellation"
"pretrained (bool): load parameters from pretrained model"
model = torch.hub.load(repo, model_name, pretrained=True)
Installation
------------
1. Create a `conda <https://docs.conda.io/en/latest/>`_ environment (recommended)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.. code-block:: shell
ENVNAME="gifenv" # for example
conda create -n $ENVNAME python -y
conda activate $ENVNAME
2. Install PyTorch and `highresnet`
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Within the `conda` environment:
.. code-block:: shell
pip install light-the-torch # to get the best PyTorch
ltt install torch # to get the best PyTorch
pip install highresnet
Now you can do
.. code-block:: python
from highresnet import HighRes3DNet
model = HighRes3DNet(in_channels=1, out_channels=160)
No Description
Jupyter Notebook Python Unity3D Asset Text other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》