当前位置:网站首页>图像数据预处理
图像数据预处理
2022-07-07 23:11:00 【booze-J】
1.下载数据集
首先我们需要先到网上下载猫狗数据集:
猫狗分类数据集下载地址:https://pan.baidu.com/s/1i4SKqWH
密码:d8mt
2.数据集划分
刚开始下载的数据train和test都是猫和狗混合的图片,需要修改一下重新划分一下train和test中的猫和狗分别划分出来。文件结构如下:
|_image
|_train
|_dog
|_cat
|_test
|_dog
|_cat
由于训练时长的问题,这里只用到了2000张图片进行训练,1000图片进行验证。可以自行决定训练和测试数据集的大小。
3.数据预处理代码
代码运行平台为jupyter-notebook,文章中的代码块,也是按照jupyter-notebook中的划分顺序进行书写的,运行文章代码,直接分单元粘入到jupyter-notebook即可。
from keras.preprocessing.image import ImageDataGenerator,array_to_img,img_to_array,load_img
- rotation_range是一个0~180的度数,用来指定随机选择图片的角度
- width_shift和height_shift用来指定水平和竖直方向随机移动的程度,这是两个0~1之间的比
- rescale值将在执行其他处理前乘到整个图像上,我们的图像在RGB通道都是0~255的整数,这样的操作可能使图像的值过高或过低,所以我们将这个值定为0~1之间的数
- shear_range是用来进行剪切变换的程度,参考剪切变换
- zoom_range用来进行随机的放大
- horizontal_flip随机的对图片进行水平翻转,这个参数适用于水平翻转不影响图片语义的时候
- fill_mode用来指定当需要进行像素填充,比如旋转、水平和竖直位移时,如何填充新出现的像素
datagen = ImageDataGenerator(
rotation_range=40, # 随机旋转角度
width_shift_range=0.2, # 随机水平平移
height_shift_range=0.2, # 随机竖直平移
rescale=1./255, # 数值归一化
shear_range=0.2, # 随机裁剪
zoom_range=0.2, # 随机放大
horizontal_flip=True, # 水平翻转
fill_mode="nearest" # 填充方式
)
这里我们以一张图片先来演示数据处理的效果:
# 载入图片
img = load_img("./image/train/cat/cat.1.jpg")
# 将图片转化为array数据格式
x = img_to_array(img)
# (280, 300, 3) = (H,W,channels)
print(x.shape)
# 给图片增加一个维度 加这个维度主要是因为训练的时候需要一个四维的图片
x = x.reshape((1,)+x.shape)
# (1, 280, 300, 3) = (batch_size,H,W,channels)
print(x.shape)
i = 0
# 生成21张图片
# flow随机生成图片 save_prefix为新生成名字的前缀
for batch in datagen.flow(x,batch_size=1,save_to_dir='temp',save_prefix="cat",save_format="jpeg"):
# 执行20次
i += 1
if i>20:
break
测试的图片:
代码运行结果:
可以看到这个数据增强的效果还是不错的哈!
边栏推荐
- Reptile practice (VIII): reptile expression pack
- C # generics and performance comparison
- 1293_ Implementation analysis of xtask resumeall() interface in FreeRTOS
- After going to ByteDance, I learned that there are so many test engineers with an annual salary of 40W?
- Hotel
- How to insert highlighted code blocks in WPS and word
- STL -- common function replication of string class
- 新库上线 | CnOpenData中国星级酒店数据
- Deep dive kotlin collaboration (the end of 23): sharedflow and stateflow
- 【测试面试题】页面很卡的原因分析及解决方案
猜你喜欢
[Yugong series] go teaching course 006 in July 2022 - automatic derivation of types and input and output
What if the testing process is not perfect and the development is not active?
Huawei switch s5735s-l24t4s-qa2 cannot be remotely accessed by telnet
Deep dive kotlin synergy (XXII): flow treatment
Kubernetes Static Pod (静态Pod)
第一讲:链表中环的入口结点
Class head up rate detection based on face recognition
How to learn a new technology (programming language)
AI遮天传 ML-初识决策树
备库一直有延迟,查看mrp为wait_for_log,重启mrp后为apply_log但过一会又wait_for_log
随机推荐
ReentrantLock 公平锁源码 第0篇
[necessary for R & D personnel] how to make your own dataset and display it.
Summary of weidongshan phase II course content
LeetCode刷题
Application practice | the efficiency of the data warehouse system has been comprehensively improved! Data warehouse construction based on Apache Doris in Tongcheng digital Department
Thinkphp内核工单系统源码商业开源版 多用户+多客服+短信+邮件通知
Basic mode of service mesh
[Yugong series] go teaching course 006 in July 2022 - automatic derivation of types and input and output
RPA cloud computer, let RPA out of the box with unlimited computing power?
Reentrantlock fair lock source code Chapter 0
The standby database has been delayed. Check that the MRP is wait_ for_ Log, apply after restarting MRP_ Log but wait again later_ for_ log
New library online | cnopendata China Star Hotel data
Hotel
Analysis of 8 classic C language pointer written test questions
韦东山第二期课程内容概要
玩转Sonar
【愚公系列】2022年7月 Go教学课程 006-自动推导类型和输入输出
股票开户免费办理佣金最低的券商,手机上开户安全吗
How can CSDN indent the first line of a paragraph by 2 characters?
Kubernetes Static Pod (静态Pod)