简单粗暴的tensorflow-CNN

# CNN模型定义
class CNN(tf.keras.Model):
    def __init__(self):
        super().__init__()
        self.conv1 = tf.keras.layers.Conv2D(    #卷积层定义
            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)#池化层定义
        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)               #输出最大概率
        return output

---

#典型神经网络VGG16 、 VGG19 、 ResNet 、 MobileNet
import tensorflow as tf
import tensorflow_datasets as tfds

num_epoch = 5
batch_size = 50
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(batch_size)
model = tf.keras.applications.MobileNetV2(weights=None, classes=5)
optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)
for e in range(num_epoch):
    for images, labels in dataset:
        with tf.GradientTape() as tape:
            labels_pred = model(images, training=True)
            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))
    print(labels_pred)