十. Tensorboard

import tensorflow as tf
import datetime
import os


# Press the green button in the gutter to run the script.
if __name__ == '__main__':
    (train_image, train_labels), (test_image, test_labels) = tf.keras.datasets.mnist.load_data()
    train_image = tf.expand_dims(train_image, -1)
    test_image = tf.expand_dims(test_image, -1)
    train_image = tf.cast(train_image / 255, tf.float32)
    test_image = tf.cast(test_image / 255, tf.float32)
    train_labels = tf.cast(train_labels, tf.int64)
    test_labels = tf.cast(test_labels, tf.int64)
    dataset = tf.data.Dataset.from_tensor_slices((train_image, train_labels))
    test_dataset = tf.data.Dataset.from_tensor_slices((test_image, test_labels))
    dataset = dataset.repeat().shuffle(60000).batch(128)
    test_dataset = test_dataset.repeat(1).batch(128)
    model = tf.keras.Sequential([
        tf.keras.layers.Conv2D(16, [3, 3], activation='relu', input_shape=(None, None, 1)),
        tf.keras.layers.Conv2D(32, [3, 3], activation='relu'),
        tf.keras.layers.GlobalMaxPooling2D(),
        tf.keras.layers.Dense(10, activation='softmax')
    ])
    model.compile(optimizer='adam',
                  loss='sparse_categorical_crossentropy',
                  metrics=['accuracy'])

    log_dir = os.path.join("logs",datetime.datetime.now().strftime("%Y%m%d-H%M%S"))
    #路径拼接
    tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=log_dir,histogram_freq=1)
    '''
    log_dir：保存TensorBoard要解析的日志文件的目录路径。
    histogram_freq：默认为0。计算模型各层的激活值和权重直方图的频率(以epoch计)。如果设置为0，将不会计算直方图。若想直方图可视化，必须指定验证数据(或分割验证集)。
    '''

    model.fit(dataset,
              epochs=5,
              steps_per_epoch=60000 // 128,
              validation_data=test_dataset,
              validation_steps=10000 // 128,
              callbacks=[tensorboard_callback])

控制台启动tensorboard

PS F:pandaspythonProject> tensorboard --logdir logs
2021-10-20 16:28:17.925351: I tensorflow/stream_executor/platform/default/dso_loader.cc:49] Successfully opened dynamic library cudart64_110.dll
Serving TensorBoard on localhost; to expose to the network, use a proxy or pass --bind_all
TensorBoard 2.7.0 at http://localhost:6006/ (Press CTRL+C to quit)

自定义变量tensorboard

    file_writer = tf.summary.create_file_writer(log_dir+'metrics')#文件编写器
    file_writer.set_as_default()#设置成默认

    #自定义变量
    def lr_sch(epoch):
        learning_rate = 0.2
        if epoch>5:
            learning_rate=0.02
        if epoch>10:
            learning_rate=0.01
        if epoch>20:
            learning_rate=0.005
        tf.summary.scalar('learning rate',data=learning_rate,step=epoch)#记录标量值变化
        return learning_rate
    lr_callback = tf.keras.callbacks.LearningRateScheduler(lr_sch)

    model.fit(dataset,
              epochs=25,
              steps_per_epoch=60000 // 128,
              validation_data=test_dataset,
              validation_steps=10000 // 128,
              callbacks=[tensorboard_callback,lr_callback])

自定义训练的Tensorboard

    optimizer = tf.keras.optimizers.Adam()
    loss_func = tf.keras.losses.SparseCategoricalCrossentropy()
    def loss(model, x, y):
        y_ = model(x)
        return loss_func(y, y_)

    train_loss = tf.keras.metrics.Mean('train_loss')
    train_accuracy = tf.keras.metrics.SparseCategoricalAccuracy('train_accuracy')

    test_loss = tf.keras.metrics.Mean('test_loss')
    test_accuracy = tf.keras.metrics.SparseCategoricalAccuracy('test_accuracy')


    def train_step(model, images, labels):
        with tf.GradientTape() as t:
            pred = model(images)
            loss_step = loss_func(labels, pred)
        grads = t.gradient(loss_step, model.trainable_variables)
        optimizer.apply_gradients(zip(grads, model.trainable_variables))
        train_loss(loss_step)
        train_accuracy(labels, pred)
    def test_step(model, images, labels):
        pred = model(images)
        loss_step = loss_func(labels, pred)
        test_loss(loss_step)
        test_accuracy(labels, pred)

    current_time = datetime.datetime.now().strftime("%Ym%d-%H%M%S")
    train_log_dir = 'logs/gradient_tape/' + current_time + '/train'
    test_log_dir = 'logs/gradient_tape/' + current_time + '/test'
    train_summary_writer = tf.summary.create_file_writer(train_log_dir)
    test_summary_writer = tf.summary.create_file_writer(test_log_dir)

    def train():
        for epoch in range(10):
            for (batch,(images,labels)) in enumerate(dataset):
                train_step(model,images,labels)
            print('.',end=' ')
            with train_summary_writer.as_default():
                tf.summary.scalar('loss',train_loss.result(),step=epoch)
                tf.summary.scalar('accuracy', train_accuracy.result(),step=epoch)
            for (batch,(images,labels)) in enumerate(test_dataset):
                test_step(model,images,labels)
            print('*',end=' ')
            with test_summary_writer.as_default():
                tf.summary.scalar('loss', test_loss.result(), step=epoch)
                tf.summary.scalar('accuracy', test_accuracy.result(), step=epoch)
            template = 'Epoch {}, Loss: {}, Accuracy: {}, Test Loss: {}, Test Accuracy: {}'
            print(template.format((
                epoch+1,
                train_loss.result(),
                train_accuracy.result()*100,
                train_loss.result(),
                train_accuracy.result()*100
            )))
            train_loss.reset_states()
            train_accuracy.reset_states()
            test_loss.reset_states()
            test_accuracy.reset_states()
train()