Unet model with ConvNext as its encoder.
Project description
ConvNeXt-Unet
Unet model with ConvNext as its encoder.
:construction: Work in progress...
Roadmap
- Source Code
- Document
...
Install
python -m pip install convnext-unet
Usage
from convnext_unet import ConvNeXtUnet
model = ConvNeXtUnet(num_classes=1, encoder_name='convnext_tiny', activation='sigmoid', pretrained=False, in_22k=False)
num_calsses
: number of output classes.
encoder_name
: name of encoder in convnext_tiny
, convnext_small
, convnext_base
, convnext_large
, convnext_xlarge
.
activation
: activation function to call before output.
pretrained
: Whether to load ImageNet pretrained model for encoder.
in_22k
: Whether to load ImageNet-22k pretrained model for encoder.
Acknowledgement
This repository is built on top of Pytorch-UNet, ConvNeXt and segmentation_models.pytorch.
Copyright
This project is released under the GPL-3.0 license. Please see the LICENSE file for more information.
Copyright (c) 2022 Tianyi Wang.
All rights reserved.
This program incorporates a modified version of Other Program.
Copyright (c) 2022 Meta Platforms, Inc. and affiliates.
Copyright (c) 2022 milesial.
Copyright (c) 2022 Pavel Iakubovskii.
Reference
@Article{liu2022convnet,
author = {Zhuang Liu and Hanzi Mao and Chao-Yuan Wu and Christoph Feichtenhofer and Trevor Darrell and Saining Xie},
title = {A ConvNet for the 2020s},
journal = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2022},
}
@inproceedings{ronneberger2015u,
title={U-net: Convolutional networks for biomedical image segmentation},
author={Ronneberger, Olaf and Fischer, Philipp and Brox, Thomas},
booktitle={International Conference on Medical image computing and computer-assisted intervention},
pages={234--241},
year={2015},
organization={Springer}
}
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for convnext_unet-0.0.4-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 457a7596ccb6fefff566454d5dfb3e2d120c0e4286157a6710688821f796f6f0 |
|
MD5 | f0313cf39ad59ac9f8d6ab4ee87d9934 |
|
BLAKE2b-256 | 32ef178fa0f317e9ff10275d3915bfda91fb464d15c666a34d6fa4a99708cb5d |