卷积神经网络CNN （Tensorflow 2.1）

很玄学，没有修改参数，在test上的准确率从98%多变为99.1%了

参考链接：《简单粗暴Tensorflow》，狂吹

import tensorflow as tf
import numpy as np

class MNISTLoader():
    def __init__(self):
        mnist = tf.keras.datasets.mnist
        (self.train_data, self.train_label), (self.test_data, self.test_label) = mnist.load_data()
        # MNIST中的图像默认为uint8（0-255的数字）。以下代码将其归一化到0-1之间的浮点数，并在最后增加一维作为颜色通道
        self.train_data = np.expand_dims(self.train_data.astype(np.float32) / 255.0, axis=-1)      # [60000, 28, 28, 1]
        self.test_data = np.expand_dims(self.test_data.astype(np.float32) / 255.0, axis=-1)        # [10000, 28, 28, 1]
        self.train_label = self.train_label.astype(np.int32)    # [60000]
        self.test_label = self.test_label.astype(np.int32)      # [10000]
        self.num_train_data, self.num_test_data = self.train_data.shape[0], self.test_data.shape[0]

    def get_batch(self, batch_size):
        # 从数据集中随机取出batch_size个元素并返回
        index = np.random.randint(0, np.shape(self.train_data)[0], batch_size)
        return self.train_data[index, :], self.train_label[index]


# tf.keras.layers.Conv2D(
#     filters, kernel_size, strides=(1, 1), padding='valid', data_format=None,
#     dilation_rate=(1, 1), activation=None, use_bias=True,
#     kernel_initializer='glorot_uniform', bias_initializer='zeros',
#     kernel_regularizer=None, bias_regularizer=None, activity_regularizer=None,
#     kernel_constraint=None, bias_constraint=None, **kwargs
# )
# filters: Integer, the dimensionality of the output space (i.e. the number of output filters in the convolution).
# kernel_size：感受野 An integer or tuple/list of 2 integers, specifying the height and width of the 2D convolution window.
# strides：横纵步幅
# padding：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

class CNN(tf.keras.Model):
    def __init__(self):
        super().__init__()
        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.pool = 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.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.pool(x)                        # [batch_size, 14, 14, 32]
        x = self.conv2(x)                       # [batch_size, 14, 14, 64]
        x = self.pool(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

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)
for batch_index in range(num_batches):
    X, y = data_loader.get_batch(batch_size) #从数据集中随机选一部分数据
    with tf.GradientTape() as tape:
        y_pred = model(X) #得到预测值
        loss = tf.keras.losses.sparse_categorical_crossentropy(y_true=y, y_pred=y_pred)#计算loss
        loss = tf.reduce_mean(loss)
        print("batch %d: loss %f" % (batch_index, loss.numpy()))
    grads = tape.gradient(loss, model.variables) #calc grads
    optimizer.apply_gradients(grads_and_vars=zip(grads, model.variables)) #update grads

#tf.keras.metrics.SparseCategoricalAccuracy是一个评估器
#不太懂为什么分批检查预测值
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
    #model.predict 输入测试数据,输出预测结果
    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())