python：显示和保存.h5文件中的图片（HDF5文件）——吴恩达深度学习笔记

        因想查看吴恩达老师的深度学习课程里面h5数据文件存储的图片，所以来搜索了h5文件的操作。随后发现看到一位博主有同样的想法，于是把他保存单张图片的代码改成了批量保存的，并且写了非本课程也适用的版本。

        原博客底下有人说不能运行，是因为缺少了矩阵处理的代码。现在不需要原课程代码也可以读取h5文件了。底下有另两个代码块，同课程学习者可以把最下面的代码块直接粘到原代码底下

运行就可以保存h5文件的图片——记得更改数据文件的地址，如果你不是这课程的学生的话

这段代码是参考了一些博主所写的。以下是完整代码

需要自行改动地址和h5文件内部对应的键名

import numpy as np
import matplotlib.pyplot as plt
import h5py
import os
#import PIL
# 读取数据集
def load_dataset():
    #改动下三行中的地址和键名
    destination_dataset = h5py.File('文件夹/名字.h5', "r")
    destination_set_x_orig = np.array(destination_dataset["你h5文件对应的键名destination_set_x"][:])  # your destination set features
    destination_set_y_orig = np.array(destination_dataset["你h5文件对应的键名destination_set_y"][:])  # your destination set labels
    destination_set_y_orig = destination_set_y_orig.reshape((1, destination_set_y_orig.shape[0]))
    return destination_set_x_orig, destination_set_y_orig

destination_set_x_orig , destination_set_y = load_dataset()

destination_set_x_flatten  = destination_set_x_orig.reshape(destination_set_x_orig.shape[0],-1).T

destination_set_x = destination_set_x_flatten / 255

def createFolder(path):
    folder = os.path.exists(path)

    if not folder:  # 判断是否存在文件夹,如果不存在则创建文件夹

        os.makedirs(path)

file = './destination_images'

createFolder(file)
#  range范围取决于你h5文件存储的图像数量
for count in range(0,100):
    index = count
    plt.imsave("destination_images/"+ str((index+1)) +".jpg", destination_set_x[:, index].reshape((destination_set_x_orig.shape[1], destination_set_x_orig.shape[1], 3)))
    plt.imshow(destination_set_x[:, index].reshape((destination_set_x_orig.shape[1], destination_set_x_orig.shape[1], 3)))
    plt.show()

这下面是完整的代码块，可以单独运行，不需要课程原代码

import numpy as np
import matplotlib.pyplot as plt
import h5py
import os
#import PIL
# 读取数据集
def load_dataset():
    train_dataset = h5py.File('datasets/train_catvnoncat.h5', "r")
    train_set_x_orig = np.array(train_dataset["train_set_x"][:])  # your train set features
    train_set_y_orig = np.array(train_dataset["train_set_y"][:])  # your train set labels
    test_dataset = h5py.File('datasets/test_catvnoncat.h5', "r")
    test_set_x_orig = np.array(test_dataset["test_set_x"][:])  # your test set features
    test_set_y_orig = np.array(test_dataset["test_set_y"][:])  # your test set labels
    classes = np.array(test_dataset["list_classes"][:])  # the list of classes
    train_set_y_orig = train_set_y_orig.reshape((1, train_set_y_orig.shape[0]))
    test_set_y_orig = test_set_y_orig.reshape((1, test_set_y_orig.shape[0]))
    return train_set_x_orig, train_set_y_orig, test_set_x_orig, test_set_y_orig, classes

train_set_x_orig , train_set_y , test_set_x_orig , test_set_y , classes = load_dataset()

train_set_x_flatten  = train_set_x_orig.reshape(train_set_x_orig.shape[0],-1).T
test_set_x_flatten = test_set_x_orig.reshape(test_set_x_orig.shape[0], -1).T

train_set_x = train_set_x_flatten / 255
test_set_x = test_set_x_flatten / 255

def createFolder(path):
    folder = os.path.exists(path)

    if not folder:  # 判断是否存在文件夹,如果不存在则创建文件夹

        os.makedirs(path)

file1 = './train_images'
file2 = './test_images'
createFolder(file1)
createFolder(file2)
#  range范围取决于你h5文件存储的图像数量
for count1 in range(0,209):
    index = count1
    plt.imsave("train_images/"+ str((index+1)) +".jpg", train_set_x[:, index].reshape((train_set_x_orig.shape[1], train_set_x_orig.shape[1], 3)))
    plt.imshow(train_set_x[:, index].reshape((train_set_x_orig.shape[1], train_set_x_orig.shape[1], 3)))
    plt.show()
for count2 in range(0,50):
    index = count2
    plt.imsave("test_images/"+ str((index+1)) +".jpg", test_set_x[:, index].reshape((test_set_x_orig.shape[1], test_set_x_orig.shape[1], 3)))
    plt.imshow(test_set_x[:, index].reshape((test_set_x_orig.shape[1], test_set_x_orig.shape[1], 3)))
    plt.show()

上面的代码包含了读取h5文件的一系列定义，吴恩达老师的课程代码里面有，所以就不必重新定义了。不想弹出一堆照片的话，可以把显示的部分注释掉了，

对于把有完整代码文件的朋友，把这段粘到后面就行了。

range范围取决于你h5文件存储的图像数量

def createFolder(path):
    folder = os.path.exists(path)

    if not folder:  # 判断是否存在文件夹,如果不存在则创建文件夹

        os.makedirs(path)

file1 = './train_images'
file2 = './test_images'
createFolder(file1)
createFolder(file2)
#  range范围取决于你h5文件存储的图像数量
for count1 in range(0,209):
    index = count1
    plt.imsave("train_images/"+ str((index+1)) +".jpg", train_set_x[:, index].reshape((train_set_x_orig.shape[1], train_set_x_orig.shape[1], 3)))
    plt.imshow(train_set_x[:, index].reshape((train_set_x_orig.shape[1], train_set_x_orig.shape[1], 3)))
    plt.show()
for count2 in range(0,50):
    index = count2
    plt.imsave("test_images/"+ str((index+1)) +".jpg", test_set_x[:, index].reshape((test_set_x_orig.shape[1], test_set_x_orig.shape[1], 3)))
    plt.imshow(test_set_x[:, index].reshape((test_set_x_orig.shape[1], test_set_x_orig.shape[1], 3)))
    plt.show()

想要读取别的h5文件的话记得改动地址。

同课程学习者也可以另外建一个代码文件，学着老师引用读取数据库函数的方式读取，这样就不需要那一块定义load的函数了。因为那一块就是课程里面的lr_utils文件里的。