# Keras-WaveletTransform
This is an implementation of Wavelet Transform layer for denoising and classification from the paper
"Multi-level Wavelet Convolutional Neural Networks" by Pengju Liu, Hongzhi Zhang, Wei Lian, and Wangmeng Zuo
The paper can be found at : https://arxiv.org/abs/1907.03128
## Denoising Application
Trained on DIV2K_train and tested on DIV2K_valid, CBSD68, Set12 and Urban100
Launch init.py with parameters
* -tr : Train dataset path (Train only)
* -t : Test dataset path
* -n : Noise level
* -s : Sliding window step (Test only)
* -lw : Weight path of the model to load (Test only)
* -a : Architecture of the model
* -m : Mode (Train or Test)
Example for training a model based on Unet with Noise level 15:
```
python3 init.py -tr DIV2K/DIV2K_train_HR/ -t DIV2K/DIV2K_valid_HR/ -n 15 -a unet -m train
```
Example for testing a pretrained model based on Wavelet with Noise level 50 and Sliding window step of 50p :
```
python3 init.py -t DIV2K/DIV2K_valid_HR/ -n 50 -a wavelet -m test -lw weights/DenoisingWavelet_50.h5 -s 50
```
## Classification Application
Train and test a new model on Cifar100:
Launch classificationCifar.py or classificationCifarWavelet.py
## Benchmark
For Denoising Application only.
Compares pretrained unet-based model to wavelet-based model following noise level (15, 25, 50).
Computes mean SSIM and mean PSNR over a dataset.
dataset_path and models in benchmark_list in the script can be changed for custom benchmark.
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
DnCNN(去噪卷积神经网络)是一种用于图像和视频去噪的深度学习模型。其主要结合了CNN等深度学习技术的进步,在图像去噪方面提供了最先进的性能。 DnCNN的主要结构特点包括卷积层、批量归一化(BN)和ReLU激活函数。模型在卷积和激活函数间添加了批量归一化,有助于防止过拟合并提升模型的泛化能力。此外,DnCNN采用了残差学习的原理,其输入是噪声观察y = x + v,其中x是干净图像,v是噪声。模型并不在神经网络层之间增加连接,而是在网络的输出使用残差学习,采用残差学习公式来训练残差映射R(y) ≈ v,得到噪声图像,然后由x = y – R(y)得到原始图像。 DnCNN在进行图片去噪时,首先接收带噪图像作为输入,然后通过卷积层提取特征,并利用残差学习原理学习噪声的分布和特性。在训练过程中,模型通过优化损失函数来减小预测去噪图像与真实干净图像之间的差异。最后,模型输出去噪后的图像,实现了对带噪图像的修复和去噪。 值得注意的是,DnCNN的性能和效果可能受到训练数据、模型参数以及优化算法等多种因素的影响。因此,在实际应用中,需要根据具体情况调整模型结构和参数,以达到最佳的去噪效
资源推荐
资源详情
资源评论
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![pdf](https://img-home.csdnimg.cn/images/20210720083512.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![rar](https://img-home.csdnimg.cn/images/20210720083606.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![vsdx](https://img-home.csdnimg.cn/images/20210720083646.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![csv](https://img-home.csdnimg.cn/images/20210720083646.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![zip](https://img-home.csdnimg.cn/images/20210720083736.png)
![exe](https://img-home.csdnimg.cn/images/20210720083343.png)
收起资源包目录
![package](https://csdnimg.cn/release/downloadcmsfe/public/img/package.f3fc750b.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![folder](https://csdnimg.cn/release/downloadcmsfe/public/img/folder.005fa2e5.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/PNG.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/UNKNOWN.png)
![file-type](https://csdnimg.cn/release/download/static_files/pc/images/minetype/ZIP.png)
共 22 条
- 1
资源评论
![avatar-default](https://csdnimg.cn/release/downloadcmsfe/public/img/lazyLogo2.1882d7f4.png)
![avatar](https://profile-avatar.csdnimg.cn/default.jpg!1)
yc1111yc
- 粉丝: 24
- 资源: 164
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
![voice](https://csdnimg.cn/release/downloadcmsfe/public/img/voice.245cc511.png)
![center-task](https://csdnimg.cn/release/downloadcmsfe/public/img/center-task.c2eda91a.png)
最新资源
- C# winform置托盘图标并闪烁演示源码.zip
- 打包和分发Rust工具.pdf
- SQL中的CREATE LOGFILE GROUP 语句.pdf
- C语言-leetcode题解之第172题阶乘后的零.zip
- C语言-leetcode题解之第171题Excel列表序号.zip
- C语言-leetcode题解之第169题多数元素.zip
- ocr-图像识别资源ocr-图像识别资源
- 图像识别:基于Resnet50 + VGG16模型融合的人体细胞癌症分类模型实现-图像识别资源
- C语言-leetcode题解之第168题Excel列表名称.zip
- C语言-leetcode题解之第167题两数之和II-输入有序数组.zip
资源上传下载、课程学习等过程中有任何疑问或建议,欢迎提出宝贵意见哦~我们会及时处理!
点击此处反馈
![feedback](https://img-home.csdnimg.cn/images/20220527035711.png)
![feedback](https://img-home.csdnimg.cn/images/20220527035711.png)
![feedback-tip](https://img-home.csdnimg.cn/images/20220527035111.png)
安全验证
文档复制为VIP权益,开通VIP直接复制
![dialog-icon](https://csdnimg.cn/release/downloadcmsfe/public/img/green-success.6a4acb44.png)