Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Octobrist 894f01a55e | 2 years ago | |
---|---|---|
.. | ||
.idea | 2 years ago | |
dataset | 2 years ago | |
docs | 2 years ago | |
models | 2 years ago | |
n3net | 2 years ago | |
utils | 2 years ago | |
weights/sar_sync | 2 years ago | |
.gitignore | 2 years ago | |
LICENSE.txt | 2 years ago | |
README.md | 2 years ago | |
dataloaders.py | 2 years ago | |
demo_sync.py | 2 years ago | |
download_sets.sh | 2 years ago | |
environment.yml | 2 years ago | |
experiment_nlmcnn.py | 2 years ago | |
experiment_sarcnn17.py | 2 years ago | |
experiment_utility.py | 2 years ago | |
generate_noisy_synthetics.py | 2 years ago | |
output.txt | 2 years ago |
Nonlocal CNN SAR Image Despeckling is
a method for SAR image despeckling which performs nonlocal filtering with a deep learning engine.
Davide Cozzolino (davide.cozzolino@unina.it);
Luisa Verdoliva (verdoliv@.unina.it);
Giuseppe Scarpa (giscarpa@.unina.it);
Giovanni Poggi (poggi@.unina.it).
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)
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
Use demo_sync.py
to execute a demo for the network CNN-NLM on synthetic data.
coming soon: demo_real.py
.
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.
This is an analysis about the evolution of DL model based on the community data of Github. The application scenario of all models is the analysis of synthetic aperture images.
CSV Python Text SVG
MIT
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》