技术标签: 训练前期准备
https://github.com/codebox/image_augmentor
This is a simple data augmentation tool for image files, intended for use with machine learning data sets. The tool scans a directory containing image files, and generates new images by performing a specified set of augmentation operations on each file that it finds. This process multiplies the number of training examples that can be used when developing a neural network, and should significantly improve the resulting network's performance, particularly when the number of training examples is relatively small.
Run the utility from the command-line as follows:
python main.py <image dir> <transform1> <transform2> ...
The <image dir>
argument should be the path to a directory containing the image files to be augmented. The utility will search the directory recursively for files with any of the following extensions: jpg, jpeg, bmp, png
.
The transform
arguments determine what types of augmentation operations will be performed, using the codes listed in the table below:
Code | Description | Example Values |
---|---|---|
fliph |
Horizontal Flip | fliph |
flipv |
Vertical Flip | flipv |
noise |
Adds random noise to the image | noise_0.01 ,noise_0.5 |
rot |
Rotates the image by the specified amount | rot_90 ,rot_-45 |
trans |
Shifts the pixels of the image by the specified amounts in the x and y directions | trans_20_10 ,trans_-10_0 |
zoom |
Zooms into the specified region of the image, performing stretching/shrinking as necessary | zoom_0_0_20_20 ,zoom_-10_-20_10_10 |
blur |
Blurs the image by the specified amount | blur_1.5 |
Each transform argument results in one additional output image being generated for each input image. An argument may consist of one or more augmentation operations. Multiple operations within a single argument must be separated by commas, and the order in which the operations are performed will match the order in which they are specified within the argument.
Produce 2 output images for each input image, one of which is flipped horizontally, and one of which is flipped vertically:
python main.py ./my_images fliph flipv
Produce 1 output image for each input image, by first rotating the image by 90° and then flipping it horizontally:
python main.py ./my_images rot_90,fliph
Horizontal Flip
Mirrors the image around a vertical line running through its center
python main.py ./my_images fliph
Vertical Flip
Mirrors the image around a horizontal line running through its center
python main.py ./my_images flipv
Noise
Adds random noise to the image. The amount of noise to be added is specified by a floating-point numeric value that is included in the transform argument, the numeric value must be greater than 0.
python main.py ./my_images noise_0.01 noise_0.02 noise_0.05
Rotate
Rotates the image. The angle of rotation is specified by a integer value that is included in the transform argument
python main.py ./my_images rot_90 rot_180 rot_-90
Translate
Performs a translation on the image. The size of the translation in the x and y directions are specified by integer values that are included in the transform argument
python main.py ./my_images trans_20_20 trans_0_100
Zoom/Stretch
Zooms in (or out) to a particular area of the image. The top-left and bottom-right coordinates of the target region are specified by integer values included in the transform argument. By specifying a target region with an aspect ratio that differs from that of the source image, stretching transformations can be performed.
python main.py ./my_images zoom_150_0_300_150 zoom_0_50_300_150 zoom_200_0_300_300
Blur
Blurs the image. The amount of blurring is specified by a floating-point value included in the transform argument.
python main.py ./my_images blur_1.0 blur_2.0 blur_4.0
文章浏览阅读1.1w次,点赞7次,收藏34次。vue-grid-layout的使用、实例、遇到的问题和解决方案_vue-grid-layout
文章浏览阅读218次。然后连接一个数据源,就会在下面自动产生一个添加附件的组件。把这个控件复制粘贴到页面里,就可以单独使用来上传了。插入一个“编辑”窗体。_powerapps点击按钮上传附件
文章浏览阅读264次。(1) Abstraction (抽象)(2) Polymorphism (多态)(3) Inheritance (继承)(4) Encapsulation (封装)_"object(cnofd[\"ofdrender\"])十条"
文章浏览阅读133次。删除node_modules,重新npm install看是否成功。在 package.json 文件中的 scripts 中加入。修改你的第三方库的bug等。然后目录会多出一个目录文件。_修改 node_modules
文章浏览阅读883次。【代码】【】kali--password:su的 Authentication failure问题,&sudo passwd root输入密码时Sorry, try again._password: su: authentication failure
文章浏览阅读1w次,点赞13次,收藏97次。整理5个优秀的微信小程序开源项目。收集了微信小程序开发过程中会使用到的资料、问题以及第三方组件库。_微信小程序开源模板
文章浏览阅读128次。Centos7最简搭建NFS服务器_centos7 搭建nfs server
文章浏览阅读1.2k次,点赞2次,收藏3次。前言mybatis在持久层框架中还是比较火的,一般项目都是基于ssm。虽然mybatis可以直接在xml中通过SQL语句操作数据库,很是灵活。但正其操作都要通过SQL语句进行,就必须写大量的xml文件,很是麻烦。mybatis-plus就很好的解决了这个问题。..._mybaitis-plus ruledataobjectattributemapper' and 'com.picc.rule.management.d
文章浏览阅读325次。EECE 1080C / Programming for ECESummer 2022Laboratory 4: Global Functions PracticePlagiarism will not be tolerated:Topics covered:function creation and call statements (emphasis on global functions)Objective:To practice program development b_eece1080c
文章浏览阅读53次。被同机房早就1年前就学过的东西我现在才学,wtcl。设要求的数为\(x\)。设当前处理到第\(k\)个同余式,设\(M = LCM ^ {k - 1} _ {i - 1}\) ,前\(k - 1\)个的通解就是\(x + i * M\)。那么其实第\(k\)个来说,其实就是求一个\(y\)使得\(x + y * M ≡ a_k(mod b_k)\)转化一下就是\(y * M ...
文章浏览阅读1.3k次。首先,问题是如何出现的?晚上复查代码,发现一个activity没有调用自己的ondestroy方法我表示非常的费解,于是我检查了下代码。发现再finish代码之后接了如下代码finish();System.exit(0);//这就是罪魁祸首为什么这样写会出现问题System.exit(0);////看一下函数的原型public static void exit (int code)//Added ..._android 手动杀死app,activity不执行ondestroy
文章浏览阅读894次。Q: SylixOS 版权是什么形式, 是否分为<开发版税>和<运行时版税>.A: SylixOS 是开源并免费的操作系统, 支持 BSD/GPL 协议(GPL 版本暂未确定). 没有任何的运行时版税. 您可以用她来做任何 您喜欢做的项目. 也可以修改 SylixOS 的源代码, 不需要支付任何费用. 当然笔者希望您可以将使用 SylixOS 开发的项目 (不需要开源)或对 SylixOS 源码的修改及时告知笔者.需要指出: SylixOS 本身仅是笔者用来提升自己水平而开发的_select函数 导致堆栈溢出 sylixos