Understanding Clouds from Satellite Images比赛的discussion调研与colab数据集下载配置
colab数据集下载配置代码:
%%time
!pip install -U -q kaggle
!mkdir -p ~/.kaggle!echo '{"username":"pupil1","key":"ae776d041bf94ae1bfa9a3843797ad6d"}' > ~/.kaggle/kaggle.json!chmod 600 ~/.kaggle/kaggle.json
!mkdir -p understanding_cloud_organization
!kaggle competitions download -c understanding_cloud_organization
!mv *.zip understanding_cloud_organization/
!mv *.csv understanding_cloud_organization/
!cd /content/understanding_cloud_organization/;unzip train_images.zip
!cd /content/understanding_cloud_organization;mkdir train_images;mv *.jpg train_images/
!cd /content/understanding_cloud_organization/;unzip train.csv.zip
!cd /content/understanding_cloud_organization/;unzip test_images.zip
!cd /content/understanding_cloud_organization;mkdir test_images;mv *.jpg test_images
根据[2]的描述
The remaining area, which has not been covered by two succeeding orbits, is marked black.0
所以图片中如果出现黑色区域,就是两颗卫星都没有扫描到的地方。如下:
使用pupil1账号视角,凡是变色的都是看过的,实在极其没有意义的不予收录.
链接 | 备注 |
Train with crops, Predict with full images | 发帖子的人得分不高 |
How effective is pseudo-labeling? | (看完了)半监督 |
[LB 0.628] simple segmentation approach threshold is high? |
threshold的用法 |
Overlapping Labels in Train Data? Can a pixel be considered as multiple classes? |
(看完了) 根据第一个链接,一个像素可以属于多个类别. Each image was labeled by several people (2-4), so the labels can overlap. In addition, there was no restriction that the labels from a single labeler cannot overlap. To create the masks for this competition, we simply used the union of all labels for each class. So naturally there will be some overlap. |
AdamAccumulate | (看完了)提到了AdamAccumulate的版本兼容性问题 |
Hints for late joiners? | (看完了)提到使用steel比赛的方案 |
Bounding Boxes instead of Segmentation |
(看完了)评论中提到: 举办方不鼓励对象检测的方式,但是帖子的作者认为线性的模型比非线性的模型跟容易泛化,所以坚持使用Bounding Boxes(对象检测)的方式 |
use linknet | unet> linknet > fpn |
Correct Dice Metric | (看完了)讨论误差函数机制 |
Instance Segmentation->Request for list of past competition | 参考资料 |
Information: Bad image list Corrupt and Mislabeled Images Information: Bad image list |
一些损坏的数据 |
Question about the black area in the image | 有很好的可视化 |
ResNet34 implementation of Unet works but ResNet 50 and 101 fails? | (看完了)改变模型如果爆内存就减少batch_size |
Flowers are easy to pick ? | 介绍了一些树算法 |
Single model performance | 最佳单模 |
A best description of Generating mask from encoded pixel | 涉及encoded pixel |
Adding TTA to the model before optimisation could help Augmentations Strategies for this Competition. TTA? |
使用时间强化 |
Augmentations thred Augmentations released version 0.4.0 |
图像增强的讨论 |
Questions about the origin of the data | 讨论快照功能 |
More Tricks to Train w/ Bigger Batches (pytorch) Some tricks to train faster (pytorch) A trick to use bigger batches for training: gradient accumulation |
讨论训练技巧 |
Simple Descriptions of Cloud Types / Labeling Process | 讨论肉眼区分类别 |
Fast data loading [Experiments] | 快速读取数据 |
Deeper, Stronger, Better? |
发现resnet18有效
|
Beware of Pandas value_counts method for validation split | 指出几个代码的pandas使用有误 |
Efficient Net B4-B7 | 评论区提到修补小batch_size的办法是使用 gradient accumulation |
Improving code quality with utility scripts Utility scripts for Keras users Using High-level frameworks is not learner friendly |
代码推销 |
Object Detection vs Instance Segmentation | 很多概念 |
Hybrid convolutional and bidirectional LSTM or RNN | 使用RNN网络 |
EfficientNets are now available in pytorch segmentation model repo. | 没看懂这个是干嘛的,房之后再看 |
New method to tackle severe label noise | 处理label噪音的一篇论文 |
FPN or Unet: Which one is better? | 提到了FPN以及Unet |
Some thoughts on this competition | kernel grandmaster的一些想法 |
what is the label to be taken for overlapping masks? for example, in the image 0011165.jpg, Fish and Flower masks overlap each other for some region. | mask重合 |
Must read material | 一些资料 |
Ideas for merging ensemble's predictions How to effectively ensemble models with Keras |
讨论模型融合 |
Instance Segmentation->How to predict classes | 讨论UNET的输出怎么改成多分类 |
What does it mean to use a pretrained resnet encoder with UNET? | 讨论UNET使用预训练的resnet编码器是什么意思? |
Regular image segmentation approach | 提到进行语义分割任务的都有两个数据集 |
Discussing post processing | 讨论后处理 |
Weakly supervised segmentation | 弱监督分割 |
Must-see Kernels and topics - Understanding Clouds from Satellite Images | 对于资料的自行总结 |
RLE Decode in C++ | 提到了RLE技术 |
Hints from a late joiner's persepctive | 提到了后处理 |
Impact of using classier for removing the masks | 考虑去掉mask编码 |
A Late Joiner's Understanding and Notes | 需要细看 |
LPT: See what's going on with that commit ? | 介绍了一个有用的训练的可视化工具 |
Knock Knock can send you email notification (or slack notification) | 一个工具用来提醒你训练结束的时候发信息到你邮件通知你 |
一些统计数据来自[1]:
Useful Stats::
no. of empty mask = 7055
no. of non-empty mask = 7737
no. of non-empty mask for Fish
= 1864
no. of non-empty mask for Flower
= 1509
no. of non-empty mask for Gravel
= 1982
no. of non-empty mask for Sugar
= 2382
Reference:
[1]Public TestSet Distribution via LB probing
[2]https://www.kaggle.com/c/understanding_cloud_organization/data
Understanding Clouds from Satellite Images比赛的discussion调研与colab数据集下载配置相关推荐
- Understanding Clouds from Satellite Images的kernel调研+肉眼识别每种云朵示例
pupil1视角,凡是看过的全部进行upvote作为标记 kernel 注释 框架 输出模型格式 EDA: Find Me In The Clouds 非常赞的可视化(博文下方列出其主要内容) ...
- Understanding Clouds from Satellite Images语义分割比赛中train_test_split与stratify配合使用
用法来自: https://www.kaggle.com/mobassir/keras-efficientnetb2-for-classifying-cloud 数据集中每张图片可能包含1种云朵到4种 ...
- Severstal: Steel Defect Detection比赛的discussion调研
特征匹配 https://zhuanlan.zhihu.com/p/52140541 https://www.kaggle.com/c/severstal-steel-defect-detection ...
- ICDAR 2019比赛及数据集下载-任务-ICDAR2019任意形状文本的鲁棒阅读挑战
ICDAR 2019比赛及数据集下载 https://rrc.cvc.uab.es/?ch=14&com=tasks 任务-ICDAR2019任意形状文本的鲁棒阅读挑战 我们提议的比赛包括三个 ...
- NFL discussion调研
discussion 备注 Classification or Regression on XGB,LightGBM? Best Algorithm for this type of problem. ...
- Python基于深度学习多标签分类模型实现云状识别
其实这个比赛早在19年的时候就结束,比赛名为<Understanding Clouds from Satellite Images>,原来的任务其实不仅要识别出来类型还要能够分割出来具体的 ...
- NLPer福利-中文语言理解基准测【CLUEbenchmark】
NLPer福利-中文语言理解基准测[CLUEbenchmark] 公众号:ChallengeHub 官方链接:https://www.cluebenchmarks.com Github链接:https ...
- 本科生晋升GM记录 Kaggle比赛进阶技巧分享
图灵TOPIA 来源:知乎 作者:@GaryLIU 图灵联邦编辑部 前言 本文作者@GaryLIU 从入坑kaggle到拿到GM仅用了一年多的时间,他表示自己的学习之路可以分成三个阶段,以下是他的经验 ...
- Titanic 泰坦尼克号预测-Tensorflow 方法-【Kaggle 比赛】
本文介绍Kaggle入门比赛Titanic泰坦尼克号幸存预测的解题思路,使用的是神经网络和Tensorflow框架.提交代码附在本文的最后部分. 基本思路为: 导入数据集 对数据预处理 训练 预测并输 ...
最新文章
- windows系统下Python环境的搭建
- (原創) 如何將CMOS所擷取的影像傳到PC端? (SOC) (DE2) (TRDB-DC2)
- express 使用 redirect 对 ajax 无效 页面不跳转
- Laravel增加自定义助手函数
- Swift 绘图板功能完善以及终极优化
- 中国净水装置行业市场供需与战略研究报告
- 【软件测试】白盒测试的条件覆盖标准强于判定覆盖(错)
- 细说ASP.NET Cache及其高级用法
- python生成折线图怎么对特定点做颜色_python库matplotlib绘制折线图,散点图以及设置样式...
- java 博饼 算法_java博饼游戏( 完善中。。。。。。。。。。。)
- [GIS原理] 9.1 数字高程模型DEM-特征 | 分类 | 构建 | 数据结构 | 空间内插 | DEM的未来
- 1024*1024像素的图片,文件大小多少?
- LeedCode 24:两两交换链表中的节点
- 计算机处理器ghz,电脑CPU的GHZ代表什么?比如1.7GHZ、2.2GHZ??
- 东莞女德班被责令停办 学员被遣散并退回学费
- 《CLR via C#》读书笔记---06 类型和成员基础
- css 五彩斑斓的黑,b站老陈打码。
- 两台win 7系统电脑 一台双网卡 共享上网
- 【你好,windows】windows7 x64x86旗舰纯净终结版(usb3.0_nvme)2020.1.19
- 7-2 平面向量加法
热门文章
- Elasticsearch 安装配置 外网访问 及 后台启动
- JS获取页面元素并修改
- Socket程序中的Error#10054错误
- CVE-2019-2725复现(从环境搭建到getshell)
- Python3.7模块之re
- java私有instance_java – Instance Initializer与私有成员
- jekenis父子结构项目打包_自动打包机的型号怎么选择?自动打包机型号选择须知...
- Angular - angular2升级到angular8
- 软件测试反例,基于模型检测多反例对软件进行调试
- 微前端之qiankun