TensorFlow v2.0入门教程——06卷积神经网络(CNN)

CNN

class CNN(tf.keras.Model):
    def __init__(self):
        super().__init__()
        # valid:表示不够卷积核大小的块,则丢弃;same表示不够卷积核大小的块就补0,所以输出和输入形状相同
        self.conv1 = tf.keras.layers.Conv2D(
            filters=32,             # 卷积层神经元（卷积核）数目
            kernel_size=[5, 5],     # 感受野大小
            padding='same',         # padding策略（vaild 或 same）
            activation=tf.nn.relu   # 激活函数
        )
        self.pool1 = tf.keras.layers.MaxPool2D(pool_size=[2, 2], strides=2)
        self.conv2 = tf.keras.layers.Conv2D(
            filters=64,
            kernel_size=[5, 5],
            padding='same',
            activation=tf.nn.relu
        )
        self.pool2 = tf.keras.layers.MaxPool2D(pool_size=[2, 2], strides=2)
        self.flatten = tf.keras.layers.Reshape(target_shape=(7 * 7 * 64,))
        self.dense1 = tf.keras.layers.Dense(units=1024, activation=tf.nn.relu)
        self.dense2 = tf.keras.layers.Dense(units=10)

    def call(self, inputs):
        x = self.conv1(inputs)                  # [batch_size, 28, 28, 32]
        x = self.pool1(x)                       # [batch_size, 14, 14, 32]
        x = self.conv2(x)                       # [batch_size, 14, 14, 64]
        x = self.pool2(x)                       # [batch_size, 7, 7, 64]
        x = self.flatten(x)                     # [batch_size, 7 * 7 * 64]
        x = self.dense1(x)                      # [batch_size, 1024]
        x = self.dense2(x)                      # [batch_size, 10]
        output = tf.nn.softmax(x)
        return output

# 调整超参数
num_epochs = 5
batch_size = 50
learning_rate = 0.001
model = CNN()
data_loader = MNISTLoader()
optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)
num_batches = int(data_loader.num_train_data // batch_size * num_epochs)
# 梯度下降
for batch_index in range(num_batches):
    X, y = data_loader.get_batch(batch_size)
    with tf.GradientTape() as tape:
        y_pred = model(X)
        loss = tf.keras.losses.sparse_categorical_crossentropy(y_true=y, y_pred=y_pred)
        loss = tf.reduce_mean(loss)
        print("batch %d: loss %f" % (batch_index, loss.numpy()))
    grads = tape.gradient(loss, model.variables)
    optimizer.apply_gradients(grads_and_vars=zip(grads, model.variables))

测试准确率

sparse_categorical_accuracy = tf.keras.metrics.SparseCategoricalAccuracy()
num_batches = int(data_loader.num_test_data // batch_size)
for batch_index in range(num_batches):
    start_index, end_index = batch_index * batch_size, (batch_index + 1) * batch_size
    y_pred = model.predict(data_loader.test_data[start_index: end_index])
    sparse_categorical_accuracy.update_state(y_true=data_loader.test_label[start_index: end_index], y_pred=y_pred)
print("test accuracy: %f" % sparse_categorical_accuracy.result())

test accuracy: 0.992200

MobileNetV2

以下展示一个例子，使用 MobileNetV2 网络在 tf_flowers 五分类数据集上进行训练（为了代码的简短高效，在该示例中我们使用了 TensorFlow Datasets 和 tf.data 载入和预处理数据）。通过将 weights 设置为 None ，我们随机初始化变量而不使用预训练权值。同时将 classes 设置为 5，对应于 5 分类的数据集。

import tensorflow as tf
import tensorflow_datasets as tfds

learning_rate = 0.001

dataset = tfds.load("tf_flowers", split=tfds.Split.TRAIN, as_supervised=True)
dataset = dataset.map(lambda img, label: (tf.image.resize(img, [224, 224]) / 255.0, label)).shuffle(1024).batch(32)
model = tf.keras.applications.MobileNetV2(weights=None, classes=5)
optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)
for images, labels in dataset:
    with tf.GradientTape() as tape:
        labels_pred = model(images)
        loss = tf.keras.losses.sparse_categorical_crossentropy(y_true=labels, y_pred=labels_pred)
        loss = tf.reduce_mean(loss)
        print("loss %f" % loss.numpy())
    grads = tape.gradient(loss, model.trainable_variables)
    optimizer.apply_gradients(grads_and_vars=zip(grads, model.trainable_variables))