AttributeError：“顺序”对象没有属性“_get_distribution_strategy”

Question

我正在通过 linkedin 关注通过 Keras 构建模型的在线课程。

这是我的代码。 （这声称有效）

 import pandas as pd
import keras
from keras.models import Sequential
from keras.layers import *

training_data_df = pd.read_csv("sales_data_training_scaled.csv")

X = training_data_df.drop('total_earnings', axis=1).values
Y = training_data_df[['total_earnings']].values

# Define the model
model = Sequential()
model.add(Dense(50, input_dim=9, activation='relu', name='layer_1'))
model.add(Dense(100, activation='relu', name='layer_2'))
model.add(Dense(50, activation='relu', name='layer_3'))
model.add(Dense(1, activation='linear', name='output_layer'))
model.compile(loss='mean_squared_error', optimizer='adam')

# Create a TensorBoard logger
logger = keras.callbacks.TensorBoard(
    log_dir='logs',
    write_graph=True,
    histogram_freq=5
)

# Train the model
model.fit(
    X,
    Y,
    epochs=50,
    shuffle=True,
    verbose=2,
    callbacks=[logger]
)

# Load the separate test data set
test_data_df = pd.read_csv("sales_data_test_scaled.csv")

X_test = test_data_df.drop('total_earnings', axis=1).values
Y_test = test_data_df[['total_earnings']].values

test_error_rate = model.evaluate(X_test, Y_test, verbose=0)
print("The mean squared error (MSE) for the test data set is: {}".format(test_error_rate))

执行以下代码时出现以下错误。

 Using TensorFlow backend.
2020-01-16 13:58:14.024374: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2020-01-16 13:58:14.037202: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fc47b436390 initialized for platform Host (this does not guarantee that XLA will be used). Devices:
2020-01-16 13:58:14.037211: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version
Traceback (most recent call last):
  File "/Users/himsaragallage/Documents/Building_Deep_Learning_apps/06/model_logging final.py", line 35, in <module>
    callbacks=[logger]
  File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/keras/engine/training.py", line 1239, in fit
    validation_freq=validation_freq)
  File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/keras/engine/training_arrays.py", line 119, in fit_loop
    callbacks.set_model(callback_model)
  File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/keras/callbacks/callbacks.py", line 68, in set_model
    callback.set_model(model)
  File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/keras/callbacks/tensorboard_v2.py", line 116, in set_model
    super(TensorBoard, self).set_model(model)
  File "/Library/Frameworks/Python.framework/Versions/3.7/lib/python3.7/site-packages/tensorflow_core/python/keras/callbacks.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'

Process finished with exit code 1

当我尝试调试时

我发现这个错误是因为我正在尝试使用 tensorboard logger 引起的。更精确地。当我添加 callbacks=[logger] 时。如果没有这行代码，程序运行时不会出现任何错误。但是不会使用Tensorboard。

请给我一个可以消除错误的方法，我可以成功运行上面提到的 python 脚本。

原文由 Himsara Gallege 发布，翻译遵循 CC BY-SA 4.0 许可协议

Answer 1

希望您指的是这个 LinkedIn Keras 课程。

即使我在使用 Tensorflow Version 2.1 时也遇到了同样的错误。但是，在降级 Tensorflow Version 并稍微修改代码后，我可以调用 Tensorboard 。

工作代码如下所示：

 import pandas as pd
import keras
import tensorflow as tf
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import *

training_data_df = pd.read_csv("sales_data_training_scaled.csv")

X = training_data_df.drop('total_earnings', axis=1).values
Y = training_data_df[['total_earnings']].values

# Define the model
model = Sequential()
model.add(Dense(50, input_dim=9, activation='relu', name='layer_1'))
model.add(Dense(100, activation='relu', name='layer_2'))
model.add(Dense(50, activation='relu', name='layer_3'))
model.add(Dense(1, activation='linear', name='output_layer'))
model.compile(loss='mean_squared_error', optimizer='adam')

# Create a TensorBoard logger
logger = tf.keras.callbacks.TensorBoard(
    log_dir='logs',
    write_graph=True,
    histogram_freq=5
)

# Train the model
model.fit(
    X,
    Y,
    epochs=50,
    shuffle=True,
    verbose=2,
    callbacks=[logger]
)

# Load the separate test data set
test_data_df = pd.read_csv("sales_data_test_scaled.csv")

X_test = test_data_df.drop('total_earnings', axis=1).values
Y_test = test_data_df[['total_earnings']].values

test_error_rate = model.evaluate(X_test, Y_test, verbose=0)
print("The mean squared error (MSE) for the test data set is: {}".format(test_error_rate))

原文由 Tensorflow Support 发布，翻译遵循 CC BY-SA 4.0 许可协议

Answer 2

您可能会发现 这篇 文章很有用。

所以不是从keras导入（即）

 from keras.models import Sequential

从张量流导入：

 from tensorflow.keras.models import Sequential

这当然也适用于大多数其他进口商品。

这只是一个幸运的猜测，因为我无法运行您的代码，但希望对您有所帮助！

原文由 Pörripeikko 发布，翻译遵循 CC BY-SA 4.0 许可协议