运行时出现错误

来源：6-9 图像风格转换训练流程代码实现

幕布斯4180522

2019-05-13

loss_value, content_loss_value, style_loss_value, _
= sess.run([loss, content_loss, style_loss, train_op],
feed_dict = {
content: content_val,
style: style_val,
})
在执行到这段代码时出现错误，错误信息如下：
AbortedError: Operation received an exception:Status: 5, message: could not create a view primitive descriptor, in file tensorflow/core/kernels/mkl_slice_op.cc:435
[[node gradients/concat_2_grad/Slice_1 (defined at :110) ]]
调试后发现是执行到 train_op时出现错误，代码是使用老师py3的代码
编译环境是使用anaconda中的jupyter nootbook，python3.7.1

写回答

1回答