Keras 和 TensorBoard - AttributeError: 'Sequential' 对象没有属性 '_get_distribution_strategy'

问题描述

我正在使用 keras 并尝试使用张量板绘制日志.波纹管您可以找出我收到的错误以及我正在使用的软件包版本列表.我无法理解它给了我顺序"对象没有属性_get_distribution_strategy"的错误.

I am using keras and trying to plot the logs using tensorboard. Bellow you can find out the error I am getting and also the list of packages versions I am using. I can not understand it is giving me the error of 'Sequential' object has no attribute '_get_distribution_strategy'.

包装:凯拉斯 2.3.1Keras-应用程序 1.0.8Keras-预处理 1.1.0张量板 2.1.0张量流 2.1.0张量流估计器 2.1.0

Package:Keras 2.3.1Keras-Applications 1.0.8Keras-Preprocessing 1.1.0tensorboard 2.1.0tensorflow 2.1.0tensorflow-estimator 2.1.0

模型:

model = Sequential()
    model.add(Embedding(MAX_NB_WORDS, EMBEDDING_DIM, input_shape=(X.shape[1],)))
    model.add(GlobalAveragePooling1D())
    #model.add(Dense(10, activation='sigmoid'))
    model.add(Dense(len(CATEGORIES), activation='softmax'))
    model.summary()
    #opt = 'adam'       # Here we can choose a certain optimizer for our model
    opt = 'rmsprop'
    model.compile(loss='categorical_crossentropy', optimizer=opt, metrics=['accuracy'])                  # Here we choose the loss function, input our optimizer choice, and set our metrics.

    # Create a TensorBoard instance with the path to the logs directory
    tensorboard = TensorBoard(log_dir='logs/{}'.format(time()),
                    histogram_freq = 1,
                    embeddings_freq = 1,
                    embeddings_data = X)

    history = model.fit(X, Y, epochs=epochs, batch_size=batch_size, validation_split=0.1, callbacks=[tensorboard])

错误:

C:UsersBrunoAppDataLocalProgramsPythonPython37libsite-packageskerascallbacks	ensorboard_v2.py:102: UserWarning: The TensorBoard callback does not support embeddings display when using TensorFlow 2.0. Embeddings-related arguments are ignored.
  warnings.warn('The TensorBoard callback does not support '
C:UsersBrunoAppDataLocalProgramsPythonPython37libsite-packages	ensorflow_corepythonframeworkindexed_slices.py:433: UserWarning: Converting sparse IndexedSlices to a dense Tensor of unknown shape. This may consume a large amount of memory.
  "Converting sparse IndexedSlices to a dense Tensor of unknown shape. "
Train on 1123 samples, validate on 125 samples
Traceback (most recent call last):
  File ".NN_Training.py", line 128, in <module>
    history = model.fit(X, Y, epochs=epochs, batch_size=batch_size, validation_split=0.1, callbacks=[tensorboard])    # Feed in the train
set for X and y and run the model!!!
  File "C:UsersBrunoAppDataLocalProgramsPythonPython37libsite-packageskerasengine	raining.py", line 1239, in fit
    validation_freq=validation_freq)
  File "C:UsersBrunoAppDataLocalProgramsPythonPython37libsite-packageskerasengine	raining_arrays.py", line 119, in fit_loop
    callbacks.set_model(callback_model)
  File "C:UsersBrunoAppDataLocalProgramsPythonPython37libsite-packageskerascallbackscallbacks.py", line 68, in set_model
    callback.set_model(model)
  File "C:UsersBrunoAppDataLocalProgramsPythonPython37libsite-packageskerascallbacks	ensorboard_v2.py", line 116, in set_model
    super(TensorBoard, self).set_model(model)
  File "C:UsersBrunoAppDataLocalProgramsPythonPython37libsite-packages	ensorflow_corepythonkerascallbacks.py", line 1532, in
set_model
    self.log_dir, self.model._get_distribution_strategy())  # pylint: disable=protected-access
AttributeError: 'Sequential' object has no attribute '_get_distribution_strategy'```

推荐答案

你在 keras 和 tf.keras 之间混合导入，它们不是同一个库这不受支持.

You are mixing imports between keras and tf.keras, they are not the same library and doing this is not supported.

您应该从其中一个库中进行所有导入，keras 或 tf.keras.

You should make all imports from one of the libraries, either keras or tf.keras.

这篇关于Keras 和 TensorBoard - AttributeError: 'Sequential' 对象没有属性 '_get_distribution_strategy'的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！