zoukankan      html  css  js  c++  java
  • Tensorflow2.0笔记24——数据增强,增大数据量

    Tensorflow2.0笔记

    本博客为Tensorflow2.0学习笔记,感谢北京大学微电子学院曹建老师

    2.2 数据增强,增大数据量

    1.数据增强(增大数据量)

    image_gen_train=tf.keras.preprocessing.image.ImageDataGenerator( 增强方法)
    image_gen_train.fit(x_train) 
    

    常用增强方法:

    缩放系数:rescale=所有数据将乘以提供的值

    随机旋转:rotation_range=随机旋转角度数范围宽度偏移:width_shift_range=随机宽度偏移量

    高度偏移:height_shift_range=随机高度偏移量水平翻转:horizontal_flip=是否水平随机翻转

    随机缩放:zoom_range=随机缩放的范围 [1-n,1+n]

    例:

    image_gen_train = ImageDataGenerator( 
    rescale=1./255, # 原 像 素 值 0~255 归 至 0~1 
    rotation_range=45, #随机 45 度旋转 
    width_shift_range=.15,  #随机宽度偏移 [-0.15,0.15) 
    height_shift_range=.15,  #随机高度偏移 [-0.15,0.15) 
    horizontal_flip=True, #随机水平翻转 
    zoom_range=0.5 # 随 机 缩 放 到 [1-50%,1+50%]
    

    代码 mnist_train_ex2.py:

    import tensorflow as tf
    from tensorflow.keras.preprocessing.image import ImageDataGenerator
    
    mnist = tf.keras.datasets.mnist
    (x_train, y_train), (x_test, y_test) = mnist.load_data()
    x_train, x_test = x_train / 255.0, x_test / 255.0
    x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)  # 给数据增加一个维度,从(60000, 28, 28)reshape为(60000, 28, 28, 1)
    
    image_gen_train = ImageDataGenerator(
        rescale=1. / 1.,  # 如为图像,分母为255时,可归至0~1
        rotation_range=45,  # 随机45度旋转
        width_shift_range=.15,  # 宽度偏移
        height_shift_range=.15,  # 高度偏移
        horizontal_flip=False,  # 水平翻转
        zoom_range=0.5  # 将图像随机缩放阈量50%
    )
    image_gen_train.fit(x_train)
    
    model = tf.keras.models.Sequential([
        tf.keras.layers.Flatten(),
        tf.keras.layers.Dense(128, activation='relu'),
        tf.keras.layers.Dense(10, activation='softmax')
    ])
    
    model.compile(optimizer='adam',
                  loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=False),
                  metrics=['sparse_categorical_accuracy'])
    
    model.fit(image_gen_train.flow(x_train, y_train, batch_size=32), epochs=5, validation_data=(x_test, y_test),
              validation_freq=1)
    model.summary()
    

    ​ 注:1、model.fit(x_train,y_train,batch_size=32,……)变为 model.fit(image_gen_train.flow(x_train,y_train,batch_size=32), ……); 2、数据增强函数的输入要求是 4 维,通过 reshape 调整;3、如果报错:缺少scipy 库,pip install scipy 即可。

    2.数据增强可视化

    # 显示原始图像和增强后的图像
    import tensorflow as tf
    from matplotlib import pyplot as plt
    from tensorflow.keras.preprocessing.image import ImageDataGenerator
    import numpy as np
    
    mnist = tf.keras.datasets.mnist
    (x_train, y_train), (x_test, y_test) = mnist.load_data()
    x_train = x_train.reshape(x_train.shape[0], 28, 28, 1)
    
    image_gen_train = ImageDataGenerator(
        rescale=1. / 255,
        rotation_range=45,
        width_shift_range=.15,
        height_shift_range=.15,
        horizontal_flip=False,
        zoom_range=0.5
    )
    image_gen_train.fit(x_train)
    print("xtrain",x_train.shape)
    x_train_subset1 = np.squeeze(x_train[:12])
    print("xtrain_subset1",x_train_subset1.shape)
    print("xtrain",x_train.shape)
    x_train_subset2 = x_train[:12]  # 一次显示12张图片
    print("xtrain_subset2",x_train_subset2.shape)
    
    fig = plt.figure(figsize=(20, 2))
    plt.set_cmap('gray')
    # 显示原始图片
    for i in range(0, len(x_train_subset1)):
        ax = fig.add_subplot(1, 12, i + 1)
        ax.imshow(x_train_subset1[i])
    fig.suptitle('Subset of Original Training Images', fontsize=20)
    plt.show()
    
    # 显示增强后的图片
    fig = plt.figure(figsize=(20, 2))
    for x_batch in image_gen_train.flow(x_train_subset2, batch_size=12, shuffle=False):
        for i in range(0, 12):
            ax = fig.add_subplot(1, 12, i + 1)
            ax.imshow(np.squeeze(x_batch[i]))
        fig.suptitle('Augmented Images', fontsize=20)
        plt.show()
        break;
    

    image-20210623202709193

    image-20210623202730330

  • 相关阅读:
    C# 分布式自增ID算法snowflake(雪花算法)
    C# DateTime日期格式化
    HTTP响应状态码参考
    VS2019已还原ReSharper的功能
    2019前端UI框架排行榜
    2019年ASP.NET Core学习路线
    jumpserver堡垒机安装
    Linux shell 时间操作(取昨天 前天)
    nfs共享文件搭建
    zabbix agent配置详解(windows)
  • 原文地址:https://www.cnblogs.com/wind-and-sky/p/14924465.html
Copyright © 2011-2022 走看看