CNN-NLM
Python
Python, Shell
共32个文件
py: 18
md: 3
txt: 2
yml: 2
pkl: 2
t7: 2
gitignore: 1
jpg: 1
sh: 1
Nonlocal CNN SAR Image Despeckling
CNN-NLM : Nonlocal CNN SAR Image Despeckling
Nonlocal CNN SAR Image Despeckling is
a method for SAR image despeckling which performs nonlocal filtering with a deep learning engine.
Team members
Davide Cozzolino (davide.cozzolino@unina.it);
Luisa Verdoliva (verdoliv@.unina.it);
Giuseppe Scarpa (giscarpa@.unina.it);
Giovanni Poggi (poggi@.unina.it).
License
Copyright (c) 2020 Image Processing Research Group of University Federico II of Naples ('GRIP-UNINA').
All rights reserved.
This software should be used, reproduced and modified only for informational and nonprofit purposes.
By downloading and/or using any of these files, you implicitly agree to all the
terms of the license, as specified in the document LICENSE.txt
(included in this package)
Prerequisits
All the functions and scripts were tested on Python 3.6, PyTorch 0.4.1 and Cuda 9.2,
the operation is not guaranteed with other configurations.
The command to create the CONDA environment:
conda env create -n env_cnn_nlm -f environment.yml
The command to anctivate the CONDA environment:
conda activate env_cnn_nlm
The command to install PyInn:
pip install git+https://github.com/szagoruyko/pyinn.git@master
The commands to install matmul_cuda:
svn export https://github.com/visinf/n3net.git/trunk/lib
sed -i 's/extension.h/torch.h/g' lib/matmul.cpp
cd lib; python setup.py install
Please download the datasets using the provided script:
bash download_sets.sh
python generate_noisy_synthetics.py
Usage
Demo
Use demo_sync.py to execute a demo for the network CNN-NLM on synthetic data.
coming soon: demo_real.py.
Training and Testing
The command to train the network CNN-NLM on synthetic data:
CUDA_VISIBLE_DEVICES=0 python experiment_nlmcnn.py --exp_name new_train
The command to test the network CNN-NLM on synthetic data:
CUDA_VISIBLE_DEVICES=0 python experiment_nlmcnn.py --eval --eval_epoch 50 --exp_name new_train
The script python experiment_sarcnn17.py is the implementation in Python/Torch of the paper "SAR image despeckling through convolutional neural networks".
NOTE: the SSIM of the paper is little different because it was computed using Matlab instead of Python.
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
这是一个基于Python的SAR图像去噪CNN-NLM设计,使用Python和Shell语言开发,包含32个文件。主要文件类型包括18个Python源文件、3个Markdown文档、2个TXT文件、2个YAML文件、2个Pickle文件、2个T7文件、1个gitignore文件、1个JPG图片文件和1个Shell脚本文件。该项目是一个非局部CNN用于SAR图像去噪的设计,适合用于个人学习和实践Python的开发技术。
资源推荐
资源详情
资源评论
收起资源包目录
upload.zip (33个子文件)
experiment_utility.py 14KB
LICENSE.txt 2KB
generate_noisy_synthetics.py 813B
weights
sar_sync
SAR_CNN_e50.t7 6.4MB
SAR_CNN_e50.pkl 910B
CNN_NLM_e50.pkl 1KB
CNN_NLM_e50.t7 12.27MB
utils
utils.py 2KB
__init__.py 0B
metrics.py 3KB
dataset
__init__.py 187B
sar_dataset.py 7KB
folders_data.py 253B
BSDS_val68_list.txt 739B
n3net
__init__.py 296B
non_local.py 13KB
LICENSE.md 911B
n3block.py 5KB
ops.py 7KB
docs
_config.yml 36B
header.jpg 58KB
index.md 2KB
environment.yml 2KB
experiment_sarcnn17.py 7KB
models
__init__.py 188B
NlmCNN.py 6KB
DnCNN.py 5KB
.gitignore 2KB
demo_sync.py 3KB
download_sets.sh 522B
dataloaders.py 7KB
experiment_nlmcnn.py 8KB
readme.txt 2KB
共 33 条
- 1
资源评论
沐知全栈开发
- 粉丝: 4739
- 资源: 3374
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功