机器学习|从零完成深度学习手写图片分类任务


目录

  • 前言
  • 分步代码
  • 完整代码

前言 下载并安装 TensorFlow 2。将 TensorFlow 导入您的程序
注:升级 pip 以安装 TensorFlow 2 软件包。请参阅安装指南了解详细信息。
分步代码 【机器学习|从零完成深度学习手写图片分类任务】将 Tensorflow 导入您的程序:
import tensorflow as tffrom tensorflow.keras.layers import Dense, Flatten, Conv2D from tensorflow.keras import Model

加载并准备 MNIST 数据集。
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# Add a channels dimension x_train = x_train[..., tf.newaxis].astype("float32") x_test = x_test[..., tf.newaxis].astype("float32")

使用 tf.data 来将数据集切分为 batch 以及混淆数据集:
train_ds = tf.data.Dataset.from_tensor_slices( (x_train, y_train)).shuffle(10000).batch(32)test_ds = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32)

使用 Keras 模型子类化(model subclassing) API 构建 tf.keras 模型:
class MyModel(Model): def __init__(self): super(MyModel, self).__init__() self.conv1 = Conv2D(32, 3, activation='relu') self.flatten = Flatten() self.d1 = Dense(128, activation='relu') self.d2 = Dense(10)def call(self, x): x = self.conv1(x) x = self.flatten(x) x = self.d1(x) return self.d2(x)# Create an instance of the model model = MyModel()

为训练选择优化器与损失函数:
loss_object = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)optimizer = tf.keras.optimizers.Adam()

选择衡量指标来度量模型的损失值(loss)和准确率(accuracy)。这些指标在 epoch 上累积值,然后打印出整体结果。
train_loss = tf.keras.metrics.Mean(name='train_loss') train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')test_loss = tf.keras.metrics.Mean(name='test_loss') test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='test_accuracy')

使用 tf.GradientTape 来训练模型:
@tf.function def train_step(images, labels): with tf.GradientTape() as tape: # training=True is only needed if there are layers with different # behavior during training versus inference (e.g. Dropout). predictions = model(images, training=True) loss = loss_object(labels, predictions) gradients = tape.gradient(loss, model.trainable_variables) optimizer.apply_gradients(zip(gradients, model.trainable_variables))train_loss(loss) train_accuracy(labels, predictions)

测试模型:
@tf.function def step(images, labels): # training=False is only needed if there are layers with different # behavior during training versus inference (e.g. Dropout). predictions = model(images, training=False) t_loss = loss_object(labels, predictions)test_loss(t_loss) test_accuracy(labels, predictions)

EPOCHS = 5for epoch in range(EPOCHS): # Reset the metrics at the start of the next epoch train_loss.reset_states() train_accuracy.reset_states() test_loss.reset_states() test_accuracy.reset_states()for images, labels in train_ds: train_step(images, labels)for test_images, test_labels in test_ds: step(test_images, test_labels)print( f'Epoch {epoch + 1}, ' f'Loss: {train_loss.result()}, ' f'Accuracy: {train_accuracy.result() * 100}, ' f'Test Loss: {test_loss.result()}, ' f'Test Accuracy: {test_accuracy.result() * 100}' )

结果
Epoch 1, Loss: 0.13848990201950073, Accuracy: 95.81666564941406, Test Loss: 0.06706319749355316, Test Accuracy: 97.73999786376953 Epoch 2, Loss: 0.04312821477651596, Accuracy: 98.64666748046875, Test Loss: 0.052743155509233475, Test Accuracy: 98.2699966430664 Epoch 3, Loss: 0.022548513486981392, Accuracy: 99.29000091552734, Test Loss: 0.05303888022899628, Test Accuracy: 98.31999969482422 Epoch 4, Loss: 0.014073395170271397, Accuracy: 99.54499816894531, Test Loss: 0.06432698667049408, Test Accuracy: 98.3499984741211 Epoch 5, Loss: 0.009319018572568893, Accuracy: 99.67666625976562, Test Loss: 0.06866640597581863, Test Accuracy: 98.37999725341797

该图片分类器现在在此数据集上训练得到了接近 98% 的准确率(accuracy)。
完整代码
# import os # os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'import tensorflow as tf from tensorflow.keras.layers import Dense, Flatten, Conv2D from tensorflow.keras import Model 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# Add a channels dimension x_train = x_train[..., tf.newaxis].astype("float32") x_test = x_test[..., tf.newaxis].astype("float32")train_ds = tf.data.Dataset.from_tensor_slices( (x_train, y_train)).shuffle(10000).batch(32) test_ds = tf.data.Dataset.from_tensor_slices((x_test, y_test)).batch(32) class Mymodel(Model): def __init__(self): super(Mymodel, self).__init__() self.conv1 = Conv2D(32, 3, activation='relu') self.flatten = Flatten() self.d1 = Dense(128, activation='relu') self.d2 = Dense(10) def call(self, x): x = self.conv1(x) x = self.flatten(x) x = self.d1(x) return self.d2(x) model = Mymodel()loss_object = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True) optimizer = tf.keras.optimizers.Adam()train_loss = tf.keras.metrics.Mean(name='train_loss') train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='train_accuracy')test_loss = tf.keras.metrics.Mean(name='test_loss') test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy(name='test_accuracy') @tf.function def train_step(images, labels): with tf.GradientTape() as tape: # training=True is only needed if there are layers with different # behavior during training versus inference (e.g. Dropout). predictions = model(images, training=True) loss = loss_object(labels, predictions) gradients = tape.gradient(loss, model.trainable_variables) optimizer.apply_gradients(zip(gradients, model.trainable_variables))train_loss(loss) train_accuracy(labels, predictions) @tf.function def step(images, labels): # training=False is only needed if there are layers with different # behavior during training versus inference (e.g. Dropout). predictions = model(images, training=False) t_loss = loss_object(labels, predictions)test_loss(t_loss) test_accuracy(labels, predictions)EPOCHS = 5for epoch in range(EPOCHS): # Reset the metrics at the start of the next epoch train_loss.reset_states() train_accuracy.reset_states() test_loss.reset_states() test_accuracy.reset_states()for images, labels in train_ds: train_step(images, labels)for test_images, test_labels in test_ds: step(test_images, test_labels)print( f'Epoch {epoch + 1}, ' f'Loss: {train_loss.result()}, ' f'Accuracy: {train_accuracy.result() * 100}, ' f'Test Loss: {test_loss.result()}, ' f'Test Accuracy: {test_accuracy.result() * 100}' )

    推荐阅读