一小时学会TensorFlow2之Fashion Mnist-巨人网络通讯

一小时学会TensorFlow2之Fashion Mnist

描述

Fashion Mnist 是一个类似于 Mnist 的图像数据集. 涵盖 10 种类别的 7 万 (6 万训练集 + 1 万测试集) 个不同商品的图片.

Tensorboard

Tensorboard 是 tensorflow 的一个可视化工具.

创建 summary

我们可以通过tf.summary.create_file_writer(file_path)来创建一个新的 summary 实例.

例子:

# 将当前时间作为子文件名
current_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")

# 监听的文件的路径
log_dir = 'logs/' + current_time

# 创建writer
summary_writer = tf.summary.create_file_writer(log_dir)

存入数据

通过tf.summary.scalar我们可以向 summary 对象存入数据.

格式:

tf.summary.scalar(
    name, data, step=None, description=None
)

例子:

with summary_writer.as_default():
    tf.summary.scalar("train-loss", float(Cross_Entropy), step=step)

metrics

metrics.Mean()

metrics.Mean()可以帮助我们计算平均数.

格式:

tf.keras.metrics.Mean(
    name='mean', dtype=None
)

例子:

# 准确率表
loss_meter = tf.keras.metrics.Mean()

metrics.Accuracy()

格式:

tf.keras.metrics.Accuracy(
    name='accuracy', dtype=None
)

例子:

# 损失表
acc_meter = tf.keras.metrics.Accuracy()

变量更新重置

我们可以通过update_state来实现变量更新, 通过rest_state来实现变量重置.

例如:

# 跟新损失
loss_meter.update_state(Cross_Entropy)

# 重置
loss_meter.reset_state()

案例

pre_process 函数

def pre_process(x, y):
    """
    数据预处理
    :param x: 特征值
    :param y: 目标值
    :return: 返回处理好的x, y
    """
    # 转换x
    x = tf.cast(x, tf.float32) / 255
    x = tf.reshape(x, [-1, 784])

    # 转换y
    y = tf.cast(y, dtype=tf.int32)
    y = tf.one_hot(y, depth=10)

    return x, y

get_data 函数

def get_data():
    """
    获取数据
    :return: 返回分批完的训练集和测试集
    """

    # 获取数据
    (X_train, y_train), (X_test, y_test) = tf.keras.datasets.fashion_mnist.load_data()

    # 分割训练集
    train_db = tf.data.Dataset.from_tensor_slices((X_train, y_train)).shuffle(60000, seed=0)
    train_db = train_db.batch(batch_size).map(pre_process)

    # 分割测试集
    test_db = tf.data.Dataset.from_tensor_slices((X_test, y_test)).shuffle(10000, seed=0)
    test_db = test_db.batch(batch_size).map(pre_process)

    # 返回
    return train_db, test_db

train 函数

def train(epoch, train_db):
    """
    训练数据
    :param train_db: 分批的数据集
    :return: 无返回值
    """
    for step, (x, y) in enumerate(train_db):
        with tf.GradientTape() as tape:

            # 获取模型输出结果
            logits = model(x)

            # 计算交叉熵
            Cross_Entropy = tf.losses.categorical_crossentropy(y, logits, from_logits=True)
            Cross_Entropy = tf.reduce_sum(Cross_Entropy)

            # 跟新损失
            loss_meter.update_state(Cross_Entropy)

        # 计算梯度
        grads = tape.gradient(Cross_Entropy, model.trainable_variables)

        # 跟新参数
        optimizer.apply_gradients(zip(grads, model.trainable_variables))

        # 每100批调试输出一下误差
        if step % 100 == 0:
            print("step:", step, "Cross_Entropy:", loss_meter.result().numpy())

            # 重置
            loss_meter.reset_state()

            # 可视化
            with summary_writer.as_default():
                tf.summary.scalar("train-loss", float(Cross_Entropy), step= epoch * 235 + step)

test 函数

def test(epoch, test_db):
    """
    测试模型
    :param epoch: 轮数
    :param test_db: 分批的测试集
    :return: 无返回值
    """

    # 重置
    acc_meter.reset_state()

    for x, y in test_db:
        # 获取模型输出结果
        logits = model(x)

        # 预测结果
        pred = tf.argmax(logits, axis=1)

        # 从one_hot编码变回来
        y = tf.argmax(y, axis=1)

        # 计算准确率
        acc_meter.update_state(y, pred)

    # 调试输出
    print("epoch:", epoch + 1, "Accuracy:", acc_meter.result().numpy() * 100, "%", )

    # 可视化
    with summary_writer.as_default():
        tf.summary.scalar("val-acc", acc_meter.result().numpy(), step=epoch * 235)

main 函数

def main():
    """
    主函数
    :return: 无返回值
    """

    # 获取数据
    train_db, test_db = get_data()

    # 轮期
    for epoch in range(iteration_num):
        train(epoch, train_db)
        test(epoch, test_db)

完整代码

import datetime
import tensorflow as tf

# 定义超参数
batch_size = 256  # 一次训练的样本数目
learning_rate = 0.001  # 学习率
iteration_num = 20  # 迭代次数

# 优化器
optimizer = tf.keras.optimizers.Adam(learning_rate=learning_rate)

# 准确率表
loss_meter = tf.keras.metrics.Mean()

# 损失表
acc_meter = tf.keras.metrics.Accuracy()

# 可视化
current_time = datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
log_dir = 'logs/' + current_time
summary_writer = tf.summary.create_file_writer(log_dir)  # 创建writer

# 模型
model = tf.keras.Sequential([
    tf.keras.layers.Dense(256, activation=tf.nn.relu),
    tf.keras.layers.Dense(128, activation=tf.nn.relu),
    tf.keras.layers.Dense(64, activation=tf.nn.relu),
    tf.keras.layers.Dense(32, activation=tf.nn.relu),
    tf.keras.layers.Dense(10)
])

# 调试输出summary
model.build(input_shape=[None, 28 * 28])
print(model.summary())


def pre_process(x, y):
    """
    数据预处理
    :param x: 特征值
    :param y: 目标值
    :return: 返回处理好的x, y
    """
    # 转换x
    x = tf.cast(x, tf.float32) / 255
    x = tf.reshape(x, [-1, 784])

    # 转换y
    y = tf.cast(y, dtype=tf.int32)
    y = tf.one_hot(y, depth=10)

    return x, y


def get_data():
    """
    获取数据
    :return: 返回分批完的训练集和测试集
    """

    # 获取数据
    (X_train, y_train), (X_test, y_test) = tf.keras.datasets.fashion_mnist.load_data()

    # 分割训练集
    train_db = tf.data.Dataset.from_tensor_slices((X_train, y_train)).shuffle(60000, seed=0)
    train_db = train_db.batch(batch_size).map(pre_process)

    # 分割测试集
    test_db = tf.data.Dataset.from_tensor_slices((X_test, y_test)).shuffle(10000, seed=0)
    test_db = test_db.batch(batch_size).map(pre_process)

    # 返回
    return train_db, test_db


def train(epoch, train_db):
    """
    训练数据
    :param train_db: 分批的数据集
    :return: 无返回值
    """
    for step, (x, y) in enumerate(train_db):
        with tf.GradientTape() as tape:

            # 获取模型输出结果
            logits = model(x)

            # 计算交叉熵
            Cross_Entropy = tf.losses.categorical_crossentropy(y, logits, from_logits=True)
            Cross_Entropy = tf.reduce_sum(Cross_Entropy)

            # 跟新损失
            loss_meter.update_state(Cross_Entropy)

        # 计算梯度
        grads = tape.gradient(Cross_Entropy, model.trainable_variables)

        # 跟新参数
        optimizer.apply_gradients(zip(grads, model.trainable_variables))

        # 每100批调试输出一下误差
        if step % 100 == 0:
            print("step:", step, "Cross_Entropy:", loss_meter.result().numpy())

            # 重置
            loss_meter.reset_state()

            # 可视化
            with summary_writer.as_default():
                tf.summary.scalar("train-loss", float(Cross_Entropy), step=epoch * 235 + step)


def test(epoch, test_db):
    """
    测试模型
    :param epoch: 轮数
    :param test_db: 分批的测试集
    :return: 无返回值
    """

    # 重置
    acc_meter.reset_state()

    for x, y in test_db:
        # 获取模型输出结果
        logits = model(x)

        # 预测结果
        pred = tf.argmax(logits, axis=1)

        # 从one_hot编码变回来
        y = tf.argmax(y, axis=1)

        # 计算准确率
        acc_meter.update_state(y, pred)

    # 调试输出
    print("epoch:", epoch + 1, "Accuracy:", acc_meter.result().numpy() * 100, "%", )

    # 可视化
    with summary_writer.as_default():
        tf.summary.scalar("val-acc", acc_meter.result().numpy(), step=epoch * 235)


def main():
    """
    主函数
    :return: 无返回值
    """

    # 获取数据
    train_db, test_db = get_data()

    # 轮期
    for epoch in range(iteration_num):
        train(epoch, train_db)
        test(epoch, test_db)


if __name__ == "__main__":
    main()

输出结果:

Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense (Dense) (None, 256) 200960
_________________________________________________________________
dense_1 (Dense) (None, 128) 32896
_________________________________________________________________
dense_2 (Dense) (None, 64) 8256
_________________________________________________________________
dense_3 (Dense) (None, 32) 2080
_________________________________________________________________
dense_4 (Dense) (None, 10) 330
=================================================================
Total params: 244,522
Trainable params: 244,522
Non-trainable params: 0
_________________________________________________________________
None
2021-06-14 18:01:27.399812: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:176] None of the MLIR Optimization Passes are enabled (registered 2)
step: 0 Cross_Entropy: 591.5974
step: 100 Cross_Entropy: 196.49309
step: 200 Cross_Entropy: 125.2562
epoch: 1 Accuracy: 84.72999930381775 %
step: 0 Cross_Entropy: 107.64579
step: 100 Cross_Entropy: 105.854385
step: 200 Cross_Entropy: 99.545975
epoch: 2 Accuracy: 85.83999872207642 %
step: 0 Cross_Entropy: 95.42945
step: 100 Cross_Entropy: 91.366234
step: 200 Cross_Entropy: 90.84072
epoch: 3 Accuracy: 86.69999837875366 %
step: 0 Cross_Entropy: 82.03317
step: 100 Cross_Entropy: 83.20552
step: 200 Cross_Entropy: 81.57012
epoch: 4 Accuracy: 86.11000180244446 %
step: 0 Cross_Entropy: 82.94046
step: 100 Cross_Entropy: 77.56677
step: 200 Cross_Entropy: 76.996346
epoch: 5 Accuracy: 87.27999925613403 %
step: 0 Cross_Entropy: 75.59219
step: 100 Cross_Entropy: 71.70899
step: 200 Cross_Entropy: 74.15144
epoch: 6 Accuracy: 87.29000091552734 %
step: 0 Cross_Entropy: 76.65844
step: 100 Cross_Entropy: 70.09151
step: 200 Cross_Entropy: 70.84446
epoch: 7 Accuracy: 88.27999830245972 %
step: 0 Cross_Entropy: 67.50707
step: 100 Cross_Entropy: 64.85907
step: 200 Cross_Entropy: 68.63099
epoch: 8 Accuracy: 88.41999769210815 %
step: 0 Cross_Entropy: 65.50318
step: 100 Cross_Entropy: 62.2706
step: 200 Cross_Entropy: 63.80803
epoch: 9 Accuracy: 86.21000051498413 %
step: 0 Cross_Entropy: 66.95486
step: 100 Cross_Entropy: 61.84385
step: 200 Cross_Entropy: 62.18851
epoch: 10 Accuracy: 88.45999836921692 %
step: 0 Cross_Entropy: 59.779297
step: 100 Cross_Entropy: 58.602314
step: 200 Cross_Entropy: 59.837025
epoch: 11 Accuracy: 88.66000175476074 %
step: 0 Cross_Entropy: 58.10068
step: 100 Cross_Entropy: 55.097878
step: 200 Cross_Entropy: 59.906315
epoch: 12 Accuracy: 88.70999813079834 %
step: 0 Cross_Entropy: 57.584858
step: 100 Cross_Entropy: 54.95376
step: 200 Cross_Entropy: 55.797752
epoch: 13 Accuracy: 88.44000101089478 %
step: 0 Cross_Entropy: 53.54782
step: 100 Cross_Entropy: 53.62939
step: 200 Cross_Entropy: 54.632828
epoch: 14 Accuracy: 87.02999949455261 %
step: 0 Cross_Entropy: 54.387398
step: 100 Cross_Entropy: 52.323734
step: 200 Cross_Entropy: 53.968185
epoch: 15 Accuracy: 88.98000121116638 %
step: 0 Cross_Entropy: 50.468914
step: 100 Cross_Entropy: 50.79311
step: 200 Cross_Entropy: 51.296227
epoch: 16 Accuracy: 88.67999911308289 %
step: 0 Cross_Entropy: 48.753258
step: 100 Cross_Entropy: 46.809692
step: 200 Cross_Entropy: 48.08208
epoch: 17 Accuracy: 89.10999894142151 %
step: 0 Cross_Entropy: 46.830627
step: 100 Cross_Entropy: 47.208813
step: 200 Cross_Entropy: 48.671318
epoch: 18 Accuracy: 88.77999782562256 %
step: 0 Cross_Entropy: 46.15514
step: 100 Cross_Entropy: 45.026627
step: 200 Cross_Entropy: 45.371685
epoch: 19 Accuracy: 88.7399971485138 %
step: 0 Cross_Entropy: 47.696465
step: 100 Cross_Entropy: 41.52749
step: 200 Cross_Entropy: 46.71362
epoch: 20 Accuracy: 89.56000208854675 %