warnings.warn('the tensorboard callback does not support '

Question

from tensorflow import keras
import tensorflow
from keras.datasets import mnist
from keras.utils import np_utils
import numpy as np
from keras.callbacks import TensorBoard
np.random.seed(10)
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_tran4D = x_train.reshape(60000, 28, 28, 1).astype('float32')
x_test4D = x_test.reshape(10000, 28, 28, 1).astype('float32')
x_train_nor = x_tran4D/255
x_test_nor = x_test4D/255
y_trainOH = np_utils.to_categorical(y_train)
y_testOH = np_utils.to_categorical(y_test)
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D
model = Sequential()
model.add(Conv2D(filters = 16,
                kernel_size=(5,5),
                padding='same',
                input_shape=(28,28,1),
                activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Conv2D(filters = 36,
                kernel_size=(5,5),
                padding='same',
                activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dropout(0.5))
model.add(Dense(10, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
Tensorboard= TensorBoard(log_dir="./model", histogram_freq=1,write_grads=True)
train_history = model.fit(x=x_train_nor, y=y_trainOH, validation_split=0.2,
                         epochs=10,
                         batch_size=300,
                         verbose=2)

当我训练手写数字识别网络时，出现了“ warnings.warn('the tensorboard callback does not support '”

Answer 1

只是一个警告， 不是错误。 后续显示正常吗？

《Python 深度学习》刷书笔记 Chapter 7 使用TensorBoard检查监控深度学习模型_LeungSr的博客-CSDN博客 文章目录使用TensorBoard可视化深度学习7-7 使用了TensorBoard的文本分类器7-8 创建一个文件7-9 使用一个TensorBoard回调函数来训练模型打开tensorboard的方法注意，新版的打开方式换了最终效果写在最后使用TensorBoard可视化深度学习TensorBoard是一个基于浏览器的可视化工具，只有当Keras使用TensorFlow后端时，这一方法才可运用于模型，其功能如下在训练过程中以可视化的方式监控指标将模型架构可视化将激活和梯度的直方图可视化. https://blog.csdn.net/leungsr/article/details/120800679