# 引入Tensorboard
from keras.callbacks import TensorBoard

tbCallBack = TensorBoard(log_dir='./logs',  # log 目錄
                 histogram_freq=0,  # 按照何等頻率（epoch）來計算直方圖，0為不計算
#                  batch_size=32,     # 用多大量的數據計算直方圖
                 write_graph=True,  # 是否存儲網絡結構圖
                 write_grads=True, # 是否可視化梯度直方圖
                 write_images=True,# 是否可視化參數
                 embeddings_freq=0, 
                 embeddings_layer_names=None, 
                 embeddings_metadata=None)

model.fit(...inputs and parameters..., callbacks=[tbCallBack])

通過引入tensorboard加入了回調函數的功能。 它將在訓練期間運行并輸出可用于張量板的文件。如果您想要在訓練的過程中可視化，請在terminal終端輸入

tensorboard --logdir ./logs 

然后在瀏覽器中訪問http://localhost:6006

image.png

完整代碼如下：
由keras/examples/mnist_mlp.py示例代碼修改

from __future__ import print_function

import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.optimizers import RMSprop

# 引入Tensorboard
from keras.callbacks import TensorBoard

batch_size = 128
num_classes = 10
epochs = 20

# the data, split between train and test sets
(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
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')

# convert class vectors to binary class matrices
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Dense(512, activation='relu', input_shape=(784,)))
model.add(Dropout(0.2))
model.add(Dense(512, activation='relu'))
model.add(Dropout(0.2))
model.add(Dense(num_classes, activation='softmax'))

model.summary()

model.compile(loss='categorical_crossentropy',
              optimizer=RMSprop(),
              metrics=['accuracy'])

tbCallBack = TensorBoard(log_dir='./logs',  # log 目錄
                 histogram_freq=0,  # 按照何等頻率（epoch）來計算直方圖，0為不計算
#                  batch_size=32,     # 用多大量的數據計算直方圖
                 write_graph=True,  # 是否存儲網絡結構圖
                 write_grads=True, # 是否可視化梯度直方圖
                 write_images=True,# 是否可視化參數
                 embeddings_freq=0, 
                 embeddings_layer_names=None, 
                 embeddings_metadata=None)

history = model.fit(x_train, y_train,
                    batch_size=batch_size,
                    epochs=epochs,
                    verbose=1,
                    validation_data=(x_test, y_test),
                    callbacks=[tbCallBack])
score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])