keras tensorboard：在同一个图中绘制训练和验证标量

Question

所以我在 keras 中使用 tensorboard。在 tensorflow 中，可以使用两种不同的摘要编写器来训练和验证标量，以便 tensorboard 可以将它们绘制在同一个图中。类似于

中的 figure

TensorBoard - Plot training and validation losses on the same graph?

有没有办法在 keras 中做到这一点？

谢谢。

Answer 1

要使用单独的编写器处理验证日志，您可以编写一个自定义回调，将原始 TensorBoard 方法包装起来。

import os
import tensorflow as tf
from keras.callbacks import TensorBoard

class TrainValTensorBoard(TensorBoard):
    def __init__(self, log_dir='./logs', **kwargs):
        # Make the original `TensorBoard` log to a subdirectory 'training'
        training_log_dir = os.path.join(log_dir, 'training')
        super(TrainValTensorBoard, self).__init__(training_log_dir, **kwargs)

        # Log the validation metrics to a separate subdirectory
        self.val_log_dir = os.path.join(log_dir, 'validation')

    def set_model(self, model):
        # Setup writer for validation metrics
        self.val_writer = tf.summary.FileWriter(self.val_log_dir)
        super(TrainValTensorBoard, self).set_model(model)

    def on_epoch_end(self, epoch, logs=None):
        # Pop the validation logs and handle them separately with
        # `self.val_writer`. Also rename the keys so that they can
        # be plotted on the same figure with the training metrics
        logs = logs or {}
        val_logs = {k.replace('val_', ''): v for k, v in logs.items() if k.startswith('val_')}
        for name, value in val_logs.items():
            summary = tf.Summary()
            summary_value = summary.value.add()
            summary_value.simple_value = value.item()
            summary_value.tag = name
            self.val_writer.add_summary(summary, epoch)
        self.val_writer.flush()

        # Pass the remaining logs to `TensorBoard.on_epoch_end`
        logs = {k: v for k, v in logs.items() if not k.startswith('val_')}
        super(TrainValTensorBoard, self).on_epoch_end(epoch, logs)

    def on_train_end(self, logs=None):
        super(TrainValTensorBoard, self).on_train_end(logs)
        self.val_writer.close()

• 在__init__ 中，为训练和验证日志设置了两个子目录
• 在set_model 中，为验证日志创建了一个写入器self.val_writer
• 在on_epoch_end 中，验证日志与训练日志分开，并写入self.val_writer 文件

以 MNIST 数据集为例：

from keras.models import Sequential
from keras.layers import Dense
from keras.datasets import mnist

(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(60000, 784)
x_test = x_test.reshape(10000, 784)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255

model = Sequential()
model.add(Dense(64, activation='relu', input_shape=(784,)))
model.add(Dense(10, activation='softmax'))
model.compile(loss='sparse_categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

model.fit(x_train, y_train, epochs=10,
          validation_data=(x_test, y_test),
          callbacks=[TrainValTensorBoard(write_graph=False)])

然后您可以在 TensorBoard 中对同一图形上的两条曲线进行可视化。

---

编辑：我稍微修改了这个类，以便它可以用于急切执行。

最大的变化是我在下面的代码中使用了tf.keras。似乎独立 Keras 中的 TensorBoard 回调尚不支持 Eager 模式。

import os
import tensorflow as tf
from tensorflow.keras.callbacks import TensorBoard
from tensorflow.python.eager import context

class TrainValTensorBoard(TensorBoard):
    def __init__(self, log_dir='./logs', **kwargs):
        self.val_log_dir = os.path.join(log_dir, 'validation')
        training_log_dir = os.path.join(log_dir, 'training')
        super(TrainValTensorBoard, self).__init__(training_log_dir, **kwargs)

    def set_model(self, model):
        if context.executing_eagerly():
            self.val_writer = tf.contrib.summary.create_file_writer(self.val_log_dir)
        else:
            self.val_writer = tf.summary.FileWriter(self.val_log_dir)
        super(TrainValTensorBoard, self).set_model(model)

    def _write_custom_summaries(self, step, logs=None):
        logs = logs or {}
        val_logs = {k.replace('val_', ''): v for k, v in logs.items() if 'val_' in k}
        if context.executing_eagerly():
            with self.val_writer.as_default(), tf.contrib.summary.always_record_summaries():
                for name, value in val_logs.items():
                    tf.contrib.summary.scalar(name, value.item(), step=step)
        else:
            for name, value in val_logs.items():
                summary = tf.Summary()
                summary_value = summary.value.add()
                summary_value.simple_value = value.item()
                summary_value.tag = name
                self.val_writer.add_summary(summary, step)
        self.val_writer.flush()

        logs = {k: v for k, v in logs.items() if not 'val_' in k}
        super(TrainValTensorBoard, self)._write_custom_summaries(step, logs)

    def on_train_end(self, logs=None):
        super(TrainValTensorBoard, self).on_train_end(logs)
        self.val_writer.close()

思路是一样的--

• 查看TensorBoard回调的源码
• 查看设置 writer 的作用
• 在这个自定义回调中做同样的事情

同样，您可以使用 MNIST 数据对其进行测试，

from tensorflow.keras.datasets import mnist
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense
from tensorflow.train import AdamOptimizer

tf.enable_eager_execution()

(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train = x_train.reshape(60000, 784)
x_test = x_test.reshape(10000, 784)
x_train = x_train.astype('float32')
x_test = x_test.astype('float32')
x_train /= 255
x_test /= 255
y_train = y_train.astype(int)
y_test = y_test.astype(int)

model = Sequential()
model.add(Dense(64, activation='relu', input_shape=(784,)))
model.add(Dense(10, activation='softmax'))
model.compile(loss='sparse_categorical_crossentropy', optimizer=AdamOptimizer(), metrics=['accuracy'])

model.fit(x_train, y_train, epochs=10,
          validation_data=(x_test, y_test),
          callbacks=[TrainValTensorBoard(write_graph=False)])

Answer 2

如果您使用的是 TensorFlow 2.0，则现在默认使用 Keras TensorBoard 回调来获取此信息。 （将 TensorFlow 与 Keras 结合使用时，请确保您使用的是 tensorflow.keras。）

请参阅本教程：

https://www.tensorflow.org/tensorboard/r2/scalars_and_keras