Deep CNNs for Diabetic Retinopathy Detection笔记
来源:互联网 发布:word表格数据排序 编辑:程序博客网 时间:2024/06/05 22:47
Deep CNNs for Diabetic Retinopathy Detection笔记
1.主要工作
使用卷积神经网络实现DR的两种分类(都是2分类模型);
2.数据集
Kaggle
an epoch was set to 2000 training examples
number of postive(眼底正常类) and negative(1-4级非正常类) examples are equal.
3.预处理
图片大小变为256*256;
each image was rescaled to have the same radius (the eyeball) and each pixel had its color subtracted by the local average;
The edges of the images were also clipped since there is a great variation on the boundaries or edges of the images;
4.训练过程
首先是simpler task(2分类:是否with DR)
采用了两个model:都是使用了googleNet Inception V3模型(已经预训练)最后再加了两层全连接层。
模型的区别是:model1是冻结了v3部分,只训练加的两层全连接层;而model2不仅训练全连接层,而且训练V3模型的top two blocks(layer 172 to 217)
并且只从0级和4级数据集中选取总共1665张图片 80%用做training set;剩下20%用作验证和测试集。
最后训练结果表明: model2的训练集准确率和验证集准确率存在large gap(约10%),表明overfitting了。
所以增加了data augmentation(random vertical and horizontal reflections ,Gaussian nosie, random crops, random shear)。
采用data augmentation后,准确率明显提高(整体比第一次好)。
Detecting referable DR
和上面一样的两个model
referable DR: moderate or worse DR (which excludes mild DR), and corresponds to a grading of 2-4 in our dataset
两类:(0和1) &(2-4)
4.模型结果对比:
- Deep CNNs for Diabetic Retinopathy Detection笔记
- Kaggle Diabetic Retinopathy Detection 参赛攻略之一 问题分析
- Pushing the Limits of Deep CNNs for Pedestrian Detection
- DeepID-Net:multi-stage and deformable deep CNNs for object detection
- READING NOTE: Pushing the Limits of Deep CNNs for Pedestrian Detection
- Context-aware CNNs for person head detection
- Looking Beyond Appearances: Synthetic Training Data for Deep CNNs in Re-identification 学习笔记
- 【深度学习论文笔记】Deep Neural Networks for Object Detection
- 论文笔记 《Deep Neural Networks for Object Detection》
- Deep Convolutional Network Cascade for Facial Point Detection阅读笔记
- Deep Convolutional Network Cascade for Facial Point Detection阅读笔记
- 论文笔记《Deep Neural Networks for Object Detection》
- 【论文笔记】Deep Neural Networks for Object Detection
- Deep Convolutional Network Cascade for Facial Point Detection阅读笔记
- Deep Convolutional Network Cascade for Facial Point Detection阅读笔记
- Detection Algorithms for Communication Systems Using Deep Learning笔记
- Part-based R-CNNs for Fine-grained Category Detection(精读)
- deep learning for face detection
- Linux Make
- poj 2411 Mondriaan's Dream(状态压缩dp)
- 使用 Math 类操作数据
- spark学习笔记:构建独立应用并提交运行
- Redis之最大内存置换策略
- Deep CNNs for Diabetic Retinopathy Detection笔记
- 【知了堂学习笔记】JSTL的简单介绍
- Process.waitFor()的返回值含义
- P1102 A-B数对
- poj2386-lak counting
- LeetCode31. Next Permutation
- linux命令--kill
- Java_21 数据输入/输出流
- HDU 5253 连接的管道 【2015年百度之星程序设计大赛