import tensorflow as tf import numpy as np import matplotlib.pyplot as plt # 导入Fashin mnist 数据集(大小28*28) fashion_mnist = tf.keras.datasets.fashion_mnist (train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data() # 对应图像打上相应的标签 class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat', 'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot'] # 打印数据信息 # print(train_images.shape) # print(len(train_labels)) # print(train_labels) # print(test_images.shape) # print(len(test_labels)) # print(test_labels) # 显示图像示例 # plt.figure() # plt.imshow(train_images[0]) # plt.colorbar() # plt.grid() # plt.show() # 预处理数据,是数据在0~1范围之间 train_images = train_images / 255.0 test_images = test_images / 255.0 # 验证是否准备好数据 # plt.figure(figsize=(10,10)) # for i in range(25): # plt.subplot(5,5,i+1) # plt.xticks([]) # plt.yticks([]) # plt.grid(False) # plt.imshow(train_images[i], cmap=plt.cm.binary) # plt.xlabel(class_names[train_labels[i]]) # plt.show() # 构建模型 model = tf.keras.Sequential([ tf.keras.layers.Flatten(input_shape=(28, 28)), # 将图像格式从 28*28 转换成一维数组 ==>格式化数据 tf.keras.layers.Dense(128, activation='relu'), # 128节点,处理数据 tf.keras.layers.Dense(10) # 返回长度为10的logits数组,每个节点都表示一个分数,表明当前图像10个类别之一 ]) # 编译模型 model.compile(optimizer='adam', loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=['accuracy']) # 训练模型 model.fit(train_images, train_labels, epochs=10) # 评估准确性 test_loss, test_acc = model.evaluate(test_images, test_labels, verbose=2) print('\nTest accuracy:', test_acc) # # 可视化预测 # 添加一个softmax,将logits转换为更容易解释的概率 probability_model = tf.keras.Sequential([model, tf.keras.layers.Softmax()]) predictions = probability_model.predict(test_images) print(predictions[12]) print(test_labels[np.argmax(predictions[0])]) # 绘图查看完整的10个类别预测集 def plot_image(i, predictions_array, true_label, img, class_names=class_names): true_label, img = true_label[i], img[i] plt.grid(False) plt.xticks([]) plt.yticks([]) plt.imshow(img, cmap=plt.cm.binary) predicted_label = test_labels[np.argmax(predictions_array)] if predicted_label.all() == true_label.all(): color = 'blue' else: color = 'red' class_names = np.array(class_names) plt.xlabel("{} {:2.0f}% ({})".format(class_names[predicted_label], 100 * np.max(predictions_array), class_names[true_label]), color=color) def plot_value_array(i, predictions_array, true_label): true_label = true_label[i] plt.grid(False) plt.xticks(range(10)) plt.yticks([]) thisplot = plt.bar(range(10), predictions_array, color="#777777") plt.ylim([0, 1]) predictions_label = np.argmax(predictions_array) thisplot[predictions_label].set_color('red') thisplot[true_label].set_color('blue') # i = 0 # plt.figure(figsize=(6, 3)) # plt.subplot(1, 2, 1) # plot_image(i, predictions[i], test_labels, test_images) # plt.subplot(1, 2, 2) # plot_value_array(i, predictions[i], test_labels) # plt.show() i = 12 plt.figure(figsize=(6, 3)) plt.subplot(1, 2, 1) plot_image(i, predictions[i], test_labels, test_images) plt.subplot(1, 2, 2) plot_value_array(i, predictions[i], test_labels) plt.show() num_rows = 5 num_cols = 3 num_images = num_cols*num_rows plt.figure(figsize=(2*2*num_cols, 2*num_rows)) for i in range(num_images): plt.subplot(num_rows, 2*num_cols, 2*i+1) plot_image(i, predictions[i], test_labels, test_images) plt.subplot(num_rows, 2*num_cols, 2*i+2) plot_value_array(i, predictions[i], test_labels) plt.tight_layout() plt.show()
# 记录自己学习tensorflow过程,大佬们不喜勿喷
# 每天学习一点点,路在脚下! 加油!