笔者在运行 import tensorflow as tf时出现下面的错误，但在运行import tensorflow时没有出错。

>>> import tensorflow as tfRuntimeError: module compiled against API version 0xc but this version of numpy is 0xaImportError: numpy.core.multiarray failed to importImportError: numpy.core.umath failed to importImportError: numpy.core.umath failed to import2018-12-09 01:22:17.925262: F tensorflow/python/lib/core/bfloat16.cc:675] Check failed: PyBfloat16_Type.tp_base != nullptr

后运行keras初级教程上的以下代码也报错：

# univariate lstm examplefrom numpy import arrayfrom keras.models import Sequentialfrom keras.layers import LSTMfrom keras.layers import Dense# define datasetX = array([[10, 20, 30], [20, 30, 40], [30, 40, 50], [40, 50, 60]])y = array([40, 50, 60, 70])# reshape from [samples, timesteps] into [samples, timesteps, features]X = X.reshape((X.shape[0], X.shape[1], 1))# define modelmodel = Sequential()model.add(LSTM(50, activation='relu', input_shape=(3, 1)))model.add(Dense(1))model.compile(optimizer='adam', loss='mse')# fit modelmodel.fit(X, y, epochs=1000, verbose=0)# demonstrate predictionx_input = array([50, 60, 70])x_input = x_input.reshape((1, 3, 1))yhat = model.predict(x_input, verbose=0)print(yhat)

经查阅资料后，安装以下网站的pip install tf-nightly

https://pypi.org/project/tf-nightly/

安装完成后运行上面所有代码就OK了，特此分享！

到此这篇关于解决import tensorflow as tf 出错的原因的文章就介绍到这了,更多相关import tensorflow as tf 内容请搜索以前的文章或继续浏览下面的相关文章希望大家以后多多支持！