aleju/imgaug: Image augmentation for machine learning experiments.

原作者: [db:作者] 来自: 网络收藏邀请

开源软件名称（OpenSource Name）：

aleju/imgaug

开源软件地址(OpenSource Url)：

https://github.com/aleju/imgaug

开源编程语言(OpenSource Language)：

Python 100.0%

开源软件介绍(OpenSource Introduction)：

imgaug

This python library helps you with augmenting images for your machine learning projects. It converts a set of input images into a new, much larger set of slightly altered images.

	Image	Heatmaps	Seg. Maps	Keypoints	Bounding Boxes, Polygons
Original Input
Gauss. Noise + Contrast + Sharpen
Affine
Crop + Pad
Fliplr + Perspective

More (strong) example augmentations of one input image:

Features
Installation
Documentation
Recent Changes
Example Images
Code Examples
Citation

Features

Many augmentation techniques

E.g. affine transformations, perspective transformations, contrast changes, gaussian noise, dropout of regions, hue/saturation changes, cropping/padding, blurring, ...
Optimized for high performance
Easy to apply augmentations only to some images
Easy to apply augmentations in random order

Support for
- Images (full support for uint8, for other dtypes see documentation)
- Heatmaps (float32), Segmentation Maps (int), Masks (bool)
  - May be smaller/larger than their corresponding images. No extra lines of code needed for e.g. crop.
- Keypoints/Landmarks (int/float coordinates)
- Bounding Boxes (int/float coordinates)
- Polygons (int/float coordinates)
- Line Strings (int/float coordinates)
Automatic alignment of sampled random values
- Example: Rotate image and segmentation map on it by the same value sampled from uniform(-10°, 45°). (0 extra lines of code.)
Probability distributions as parameters
- Example: Rotate images by values sampled from uniform(-10°, 45°).
- Example: Rotate images by values sampled from ABS(N(0, 20.0))*(1+B(1.0, 1.0))", where ABS(.) is the absolute function, N(.) the gaussian distribution and B(.) the beta distribution.
Many helper functions
- Example: Draw heatmaps, segmentation maps, keypoints, bounding boxes, ...
- Example: Scale segmentation maps, average/max pool of images/maps, pad images to aspect ratios (e.g. to square them)
- Example: Convert keypoints to distance maps, extract pixels within bounding boxes from images, clip polygon to the image plane, ...
Support for augmentation on multiple CPU cores

Installation

The library supports python 2.7 and 3.4+.

Installation: Anaconda

To install the library in anaconda, perform the following commands:

conda config --add channels conda-forge
conda install imgaug

You can deinstall the library again via conda remove imgaug.

Installation: pip

Then install imgaug either via pypi (can lag behind the github version):

pip install imgaug

or install the latest version directly from github:

pip install git+https://github.com/aleju/imgaug.git

For more details, see the install guide

To deinstall the library, just execute pip uninstall imgaug.

Documentation

Example jupyter notebooks:

Load and Augment an Image
Multicore Augmentation
Augment and work with: Keypoints/Landmarks, Bounding Boxes, Polygons, Line Strings, Heatmaps, Segmentation Maps

More notebooks: imgaug-doc/notebooks.

Example ReadTheDocs pages:

More RTD documentation: imgaug.readthedocs.io.

All documentation related files of this project are hosted in the repository imgaug-doc.

Recent Changes

0.4.0: Added new augmenters, changed backend to batchwise augmentation, support for numpy 1.18 and python 3.8.
0.3.0: Reworked segmentation map augmentation, adapted to numpy 1.17+ random number sampling API, several new augmenters.
0.2.9: Added polygon augmentation, added line string augmentation, simplified augmentation interface.
0.2.8: Improved performance, dtype support and multicore augmentation.

See changelogs/ for more details.

Example Images

The images below show examples for most augmentation techniques.

Values written in the form (a, b) denote a uniform distribution, i.e. the value is randomly picked from the interval [a, b]. Line strings are supported by (almost) all augmenters, but are not explicitly visualized here.

meta

_Identity

_{ChannelShuffle}

arithmetic

_Add

_{Add
(per_channel=True)}

_{AdditiveGaussianNoise}

_{AdditiveGaussianNoise
(per_channel=True)}

_Multiply

_Cutout

_Dropout

_{CoarseDropout
(p=0.2)}

_{CoarseDropout
(p=0.2, per_channel=True)}

_Dropout2d

_{SaltAndPepper}

_{CoarseSaltAndPepper
(p=0.2)}

_Invert

_Solarize

_{JpegCompression}

artistic

_Cartoon

blend

_{BlendAlpha
with EdgeDetect(1.0)}

_{BlendAlphaSimplexNoise
with EdgeDetect(1.0)}

_{BlendAlphaFrequencyNoise
with EdgeDetect(1.0)}

_{BlendAlphaSomeColors
with RemoveSaturation(1.0)}

_{BlendAlphaRegularGrid
with Multiply((0.0, 0.5))}

BlendAlphaSimplexNoise with EdgeDetect1.0

BlendAlphaFrequencyNoise with EdgeDetect1.0

BlendAlphaSomeColors with RemoveSaturation1.0

BlendAlphaRegularGrid with Multiply0.0, 0.5

blur

_GaussianBlur

_AverageBlur

_MedianBlur

_{BilateralBlur
(sigma_color=250,
sigma_space=250)}

_{MotionBlur
(angle=0)}

BilateralBlur sigma_color=250, sigma_space=250

_{MotionBlur
(k=5)}

_{MeanShiftBlur}

collections

_RandAugment

color

_{MultiplyAndAddToBrightness}

_{MultiplyHueAndSaturation}

_MultiplyHue

_{MultiplySaturation}

_{AddToHueAndSaturation}

_Grayscale

_{RemoveSaturation}

_{ChangeColorTemperature}

_{KMeansColorQuantization
(to_colorspace=RGB)}

_{UniformColorQuantization
(to_colorspace=RGB)}

KMeansColorQuantization to_colorspace=RGB

UniformColorQuantization to_colorspace=RGB

contrast

_{GammaContrast}

_{GammaContrast
(per_channel=True)}

_{SigmoidContrast
(cutoff=0.5)}

_{SigmoidContrast
(gain=10)}

_LogContrast

_{LinearContrast}

_{AllChannels-
HistogramEqualization}

_{HistogramEqualization}

_{AllChannelsCLAHE}

_CLAHE

请发表评论

全部评论

专题导读

More+

10-27 六六分期app的软件客服如何联系？(六六分期

11-06 可心卡盟:win10系统火狐flash插件崩溃怎么

11-06 亲亲特价:怎么删除回收站图标

11-06 济南大学虚拟社区:鲁大师节能降温的具体办

11-06 xlueops.exe:无线网络安装向导

11-06 女斗合众国:win7系统cf与主机连接不稳定怎

11-06 0xc000022-[cf烟雾头]cf怎么调烟雾头

11-06 qizideyouhuo:应用程序无法正常启动0xc0000

11-06 ipz-185:win7系统vcf文件怎么打开

11-06 傻哥蹦迪:win10系统s4怎么打开usb调试

11-06 八神浩树gtaste:回收站清空了怎么恢复

11-06 妖尾之黑色守护:win10系统电脑没有1440x900

11-06 校园至尊魔王小说:win7系统浏览网页时字体

11-06 女斗合众国:win10系统访问共享文件夹提示请

11-06 tokyo hot n0654:恢复win7系统默认字体一招

11-06 雨酷仙境:设置win7系统转移临时文件夹腾出

11-06 阿穆纳伊之杖:win7系统开始菜单在右边还原

11-06 tunespotting:win10系统火狐flash插件总是

11-06 甘尔葛分析师：计谋网站seo关键词暴涨有什

11-06 蔡贵霖: 计谋网站seo关键词暴涨有什么秘密

11-06 博益网首页:ao3网页版进入不了解决方法

11-06 漏斗子专栏: 网站数据分析小白易懂精华篇

11-06 见证双虹怎么做:win7系统开启telnet命令的

11-06 颾狐蝶蜋:系统资源不足无法完成请求的服务

11-06 国光中学校歌:提交网站到alexa查询详细步骤

11-06 西安有情天:静态网页和动态网页的区别

11-06 红木雅尚斋:外部链接构造对网站的好处

11-06 前官礼遇：防止域名劫持–增强域安全性的10

11-06 密传二转答案: 中文分词算法有哪些

11-06 金泉家园邮编:百度快照劫持的表现及应对方

learnml/machine-learning-specialization发布时间：2022-08-18

jermwatt/machine_learning_refined: Notes, examples, and Python demos for the 2nd ...发布时间：2022-08-18

剪的笔顺,诠释剪的笔画,认识剪的部首

六六分期app的软件客服如何联系？(六六分期

2023-10-27

florent37/ViewAnimator: A fluent Android

2022-08-15

florent37/Shrine-MaterialDesign2: implem

2022-08-17

CVE-2020-36276

2022-09-23

SimpleSoftwareIO/simple-sms: Send and re

2022-08-13

阅读排行榜

1 六六分期app的软件客服如何联系？(六六分期

六六分期app的软件客服如何联系？不知道吗？加qq群【895510560】即可！标题：六六分期

阅读：19135|2023-10-27

2 可心卡盟:win10系统火狐flash插件崩溃怎么

今天小编告诉大家如何处理win10系统火狐flash插件总是崩溃的问题，可能很多用户都不知

阅读：9973|2022-11-06

3 亲亲特价:怎么删除回收站图标

今天小编告诉大家如何对win10系统删除桌面回收站图标进行设置，可能很多用户都不知道

阅读：8317|2022-11-06

4 济南大学虚拟社区:鲁大师节能降温的具体办

今天小编告诉大家如何对win10系统电脑设置节能降温的设置方法，想必大家都遇到过需要

阅读：8686|2022-11-06

5 xlueops.exe:无线网络安装向导

我们在使用xp系统的过程中,经常需要对xp系统无线网络安装向导设置进行设置，可能很多

阅读：8627|2022-11-06

6 女斗合众国:win7系统cf与主机连接不稳定怎

今天小编告诉大家如何处理win7系统玩cf老是与主机连接不稳定的问题，可能很多用户都不

阅读：9643|2022-11-06

7 0xc000022-[cf烟雾头]cf怎么调烟雾头

电脑对日常生活的重要性小编就不多说了，可是一旦碰到win7系统设置cf烟雾头的问题，很

阅读：8611|2022-11-06

8 qizideyouhuo:应用程序无法正常启动0xc0000

我们在日常使用电脑的时候，有的小伙伴们可能在打开应用的时候会遇见提示应用程序无法

阅读：7991|2022-11-06

9 ipz-185:win7系统vcf文件怎么打开

今天小编告诉大家如何对win7系统打开vcf文件进行设置，可能很多用户都不知道怎么对win

阅读：8642|2022-11-06

10 傻哥蹦迪:win10系统s4怎么打开usb调试

今天小编告诉大家如何对win10系统s4开启USB调试模式进行设置，可能很多用户都不知道怎

阅读：7527|2022-11-06

扫描微信二维码

查看手机版网站

随时了解更新最新资讯

139-2527-9053

在线客服（服务时间 9:00～18:00）

在线QQ客服

地址：深圳市南山区西丽大学城创智工业园

电邮：jeky_zhao#qq.com

移动电话：139-2527-9053

上一篇：

下一篇：

dustinvtran/ml-videos: A collection of v

Ali-Azmoud/flutter_xlider: A material de

更的笔顺,体会更的笔画,理会更的部首

fluttercandies/extended_image_library: p

小程序之数据缓冲的封装