Fashion MNIST分类

Fashion MNIST数据集当初称之为深度学习的Hello World。代替了之前的手写体辨认了。

起因应该是深度学习的倒退，手写体辨认变得太简略了。

官网例子

官网代码

尝试应用卷积神经网络来辨认

官网卷积神经网络参考

获取Fashion MNIST数据

import tensorflow as tffrom tensorflow import keras# Helper librariesimport numpy as npimport matplotlib.pyplot as pltprint(tf.__version__)fashion_mnist = tf.keras.datasets.fashion_mnist(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']train_images, test_images = train_images / 255.0, test_images / 255.0print(train_images.shape)

定义卷积神经网络模型

model = tf.keras.models.Sequential()model.add(tf.keras.layers.Conv2D(32, (3, 3), activation='relu', input_shape=(28, 28,1)))model.add(tf.keras.layers.MaxPooling2D((2, 2)))model.add(tf.keras.layers.Conv2D(64, (3, 3), activation='relu'))model.add(tf.keras.layers.MaxPooling2D((2, 2)))model.add(tf.keras.layers.Conv2D(64, (3, 3), activation='relu'))model.add(tf.keras.layers.Flatten())model.add(tf.keras.layers.Dense(64, activation='relu'))model.add(tf.keras.layers.Dense(10,activation='softmax'))# model = tf.keras.models.Sequential([#     tf.keras.layers.Conv2D(32,kernel_size=(3,3),activation='relu', input_shape=(28, 28,1)),#     tf.keras.layers.MaxPooling2D(),#     tf.keras.layers.Conv2D(64,kernel_size=(5,5),activation='relu'),#     tf.keras.layers.MaxPooling2D(),#     tf.keras.layers.Flatten(),#     tf.keras.layers.Dense(64,activation='relu'),#     tf.keras.layers.Dense(10,activation='softmax')]# )model.summary()

训练模型

model.compile(optimizer='adam',              loss=tf.keras.losses.sparse_categorical_crossentropy,              metrics=['accuracy'])history = model.fit(train_images.reshape(-1,28,28,1), train_labels, epochs=10,                     validation_data=(test_images.reshape(-1,28,28,1), test_labels),batch_size=1000)

训练后果

能够看到同样的10次迭代训练，应用卷积神经网络训练的后果

val_loss: 0.3499 - val_accuracy: 0.8765

比官网的应用一般神经网络训练的数据要精确一些
loss: 0.3726 - accuracy: 0.8635

Train on 60000 samples, validate on 10000 samplesEpoch 1/1060000/60000 [==============================] - 105s 2ms/sample - loss: 1.1311 - accuracy: 0.6256 - val_loss: 0.6830 - val_accuracy: 0.7482Epoch 2/1060000/60000 [==============================] - 105s 2ms/sample - loss: 0.5803 - accuracy: 0.7813 - val_loss: 0.5385 - val_accuracy: 0.8018Epoch 3/1060000/60000 [==============================] - 105s 2ms/sample - loss: 0.4933 - accuracy: 0.8199 - val_loss: 0.4858 - val_accuracy: 0.8226Epoch 4/1060000/60000 [==============================] - 106s 2ms/sample - loss: 0.4413 - accuracy: 0.8405 - val_loss: 0.4407 - val_accuracy: 0.8419Epoch 5/1060000/60000 [==============================] - 106s 2ms/sample - loss: 0.4057 - accuracy: 0.8553 - val_loss: 0.4226 - val_accuracy: 0.8514Epoch 6/1060000/60000 [==============================] - 105s 2ms/sample - loss: 0.3795 - accuracy: 0.8643 - val_loss: 0.3933 - val_accuracy: 0.8591Epoch 7/1060000/60000 [==============================] - 108s 2ms/sample - loss: 0.3583 - accuracy: 0.8727 - val_loss: 0.3835 - val_accuracy: 0.8633Epoch 8/1060000/60000 [==============================] - 106s 2ms/sample - loss: 0.3437 - accuracy: 0.8780 - val_loss: 0.3694 - val_accuracy: 0.8641Epoch 9/1060000/60000 [==============================] - 106s 2ms/sample - loss: 0.3322 - accuracy: 0.8810 - val_loss: 0.3570 - val_accuracy: 0.8701Epoch 10/1060000/60000 [==============================] - 116s 2ms/sample - loss: 0.3258 - accuracy: 0.8831 - val_loss: 0.3499 - val_accuracy: 0.8765

做下简略预测

的确是一件上衣哈

print(model.predict(test_images[10].reshape(-1,28,28,1)))print(test_labels[10])plt.figure()plt.imshow(test_images[10])plt.colorbar()plt.grid(False)plt.show()class_names[4]