网站策划书免费,青海西宁今天刚刚紧急通知,idea制作网站,网站建设分为哪三部分课程来源#xff1a;人工智能实践:Tensorflow笔记2 文章目录前言1、文件一览2、将load_data()函数替换掉2、调用generateds函数4、效果总结前言 本讲目标:自制数据集#xff0c;解决本领域应用 将我们手中的图片和标签信息制作为可以直接导入的npy文件。 1、文件一览 首先看…课程来源人工智能实践:Tensorflow笔记2 文章目录前言1、文件一览2、将load_data()函数替换掉2、调用generateds函数4、效果总结前言 本讲目标:自制数据集解决本领域应用 将我们手中的图片和标签信息制作为可以直接导入的npy文件。 1、文件一览 首先看看我们的文件长什么样 路径D:\python code\AI\class4\MNIST_FC\mnist_image_label\mnist_test_jpg_10000 图片文件(黑底白字的灰度图大小28x28,每个像素点都是0~255之间的整数) 标签文件(图片名和对应的标签中间用空格隔开) 2、将load_data()函数替换掉 之前我们导入数据集的方式是(以mnist数据集为例) fashion tf.keras.datasets.mnist (x_train, y_train),(x_test, y_test) mnist.load_data()导入后变量的数据类型和形状 x_train.shape(60000,28,28) 3维数组60000个28行28列的图片灰度值y_train.shape(60000,) 60000张图片对应的标签是1维数组x_test.shape(10000,28,28) 3维数组10000个28行28列的图片灰度值y_test.shape(10000,) 10000张图片对应的标签是1维数组 我们需要自己写个函数generateds(图片路径标签文件) 观察数据集 我们需要做的把图片灰度值数据拼接到图片列表把标签数据拼接到标签列表。 函数代码如下 def generateds(path, txt):f open(txt, r) #只读形式读取文本数据contents f.readlines() # 按行读取读取所有行f.close() #关闭文件x, y_ [], [] #建立空列表for content in contents: #逐行读出value content.split() # 以空格分开存入数组 图片名为value0 标签为value1img_path path value[0] #图片路径图片名-拼接出索引路径img Image.open(img_path) #读入图片img np.array(img.convert(L))img img / 255. #归一化数据x.append(img) #将归一化的数据贴到列表xy_.append(value[1]) #标签贴到列表y_print(loading : content) #打印状态提示x np.array(x)y_ np.array(y_)y_ y_.astype(np.int64)return x, y_2、调用generateds函数 使用函数代码 添加了 训练集图片路径 训练集标签文件 训练集输入特征存储文件 训练集标签存储文件 测试集图片路径 测试集标签文件 测试集输入特征存储文件 测试集标签存储文件 train_path D:/python code/AI/class4/FASHION_FC/fashion_image_label/fashion_train_jpg_60000/ train_txt D:/python code/AI/class4/FASHION_FC/fashion_image_label/fashion_train_jpg_60000.txt x_train_savepath D:/python code/AI/class4/FASHION_FC/fashion_image_label/fashion_x_train.npy y_train_savepath D:/python code/AI/class4/FASHION_FC/fashion_image_label/fahion_y_train.npytest_path D:/python code/AI/class4/FASHION_FC/fashion_image_label/fashion_test_jpg_10000/ test_txt D:/python code/AI/class4/FASHION_FC/fashion_image_label/fashion_test_jpg_10000.txt x_test_savepath D:/python code/AI/class4/FASHION_FC/fashion_image_label/fashion_x_test.npy y_test_savepath D:/python code/AI/class4/FASHION_FC/fashion_image_label/fashion_y_test.npy #观察测试集训练集文件是否存在如果存在直接读取如果不存在调用generate datasets函数 if os.path.exists(x_train_savepath) and os.path.exists(y_train_savepath) and os.path.exists(x_test_savepath) and os.path.exists(y_test_savepath):print(-------------Load Datasets-----------------)x_train_save np.load(x_train_savepath)y_train np.load(y_train_savepath)x_test_save np.load(x_test_savepath)y_test np.load(y_test_savepath)x_train np.reshape(x_train_save, (len(x_train_save), 28, 28))x_test np.reshape(x_test_save, (len(x_test_save), 28, 28)) else:print(-------------Generate Datasets-----------------)x_train, y_train generateds(train_path, train_txt)x_test, y_test generateds(test_path, test_txt)print(-------------Save Datasets-----------------)x_train_save np.reshape(x_train, (len(x_train), -1))x_test_save np.reshape(x_test, (len(x_test), -1))np.save(x_train_savepath, x_train_save)np.save(y_train_savepath, y_train)np.save(x_test_savepath, x_test_save)np.save(y_test_savepath, y_test)model tf.keras.models.Sequential([tf.keras.layers.Flatten(),tf.keras.layers.Dense(128, activationrelu),tf.keras.layers.Dense(10, activationsoftmax) ])model.compile(optimizeradam,losstf.keras.losses.SparseCategoricalCrossentropy(from_logitsFalse),metrics[sparse_categorical_accuracy])model.fit(x_train, y_train, batch_size32, epochs5, validation_data(x_test, y_test), validation_freq1) model.summary()4、效果 制作完数据集之后开始用神经网络训练 可以发现原本的文件夹中出现了你所需要的npy文件。 完整代码 import tensorflow as tf from PIL import Image import numpy as np import ostrain_path D:/python code/AI/class4/FASHION_FC/fashion_image_label/fashion_train_jpg_60000/ train_txt D:/python code/AI/class4/FASHION_FC/fashion_image_label/fashion_train_jpg_60000.txt x_train_savepath D:/python code/AI/class4/FASHION_FC/fashion_image_label/fashion_x_train.npy y_train_savepath D:/python code/AI/class4/FASHION_FC/fashion_image_label/fahion_y_train.npytest_path D:/python code/AI/class4/FASHION_FC/fashion_image_label/fashion_test_jpg_10000/ test_txt D:/python code/AI/class4/FASHION_FC/fashion_image_label/fashion_test_jpg_10000.txt x_test_savepath D:/python code/AI/class4/FASHION_FC/fashion_image_label/fashion_x_test.npy y_test_savepath D:/python code/AI/class4/FASHION_FC/fashion_image_label/fashion_y_test.npydef generateds(path, txt):f open(txt, r)contents f.readlines() # 按行读取f.close()x, y_ [], []for content in contents:value content.split() # 以空格分开存入数组img_path path value[0]img Image.open(img_path)img np.array(img.convert(L))img img / 255.x.append(img)y_.append(value[1])print(loading : content)x np.array(x)y_ np.array(y_)y_ y_.astype(np.int64)return x, y_if os.path.exists(x_train_savepath) and os.path.exists(y_train_savepath) and os.path.exists(x_test_savepath) and os.path.exists(y_test_savepath):print(-------------Load Datasets-----------------)x_train_save np.load(x_train_savepath)y_train np.load(y_train_savepath)x_test_save np.load(x_test_savepath)y_test np.load(y_test_savepath)x_train np.reshape(x_train_save, (len(x_train_save), 28, 28))x_test np.reshape(x_test_save, (len(x_test_save), 28, 28)) else:print(-------------Generate Datasets-----------------)x_train, y_train generateds(train_path, train_txt)x_test, y_test generateds(test_path, test_txt)print(-------------Save Datasets-----------------)x_train_save np.reshape(x_train, (len(x_train), -1))x_test_save np.reshape(x_test, (len(x_test), -1))np.save(x_train_savepath, x_train_save)np.save(y_train_savepath, y_train)np.save(x_test_savepath, x_test_save)np.save(y_test_savepath, y_test)model tf.keras.models.Sequential([tf.keras.layers.Flatten(),tf.keras.layers.Dense(128, activationrelu),tf.keras.layers.Dense(10, activationsoftmax) ])model.compile(optimizeradam,losstf.keras.losses.SparseCategoricalCrossentropy(from_logitsFalse),metrics[sparse_categorical_accuracy])model.fit(x_train, y_train, batch_size32, epochs5, validation_data(x_test, y_test), validation_freq1) model.summary() 总结 课程链接:MOOC人工智能实践TensorFlow笔记2