解决AttributeError: module 'tensorflow' has no attribute 'keras'问题
tensorflow
一个面向所有人的开源机器学习框架
项目地址:https://gitcode.com/gh_mirrors/te/tensorflow

·
在学习《深度学习应用开发Tensorflow实践》课程泰坦尼克号旅客生存预测课程,使用tensorflow高级API kares时,出现AttributeError: module ‘tensorflow’ has no attribute 'keras’问题
解决方法:将model=tf.keras.models.Sequential()替换成model=tf.contrib.keras.models.Sequential(),成功执行
原因:




一个面向所有人的开源机器学习框架
最近提交(Master分支:1 个月前 )
4f64a3d5
Instead, check for this case in `ResolveUsers` and `ResolveOperand`, by querying whether the `fused_expression_root` is part of the `HloFusionAdaptor`.
This prevents us from stepping into nested fusions.
PiperOrigin-RevId: 724311958
1 个月前
aa7e952e
Fix a bug in handling negative strides, and add a test case that exposes it.
We can have negative strides that are not just -1, e.g. with a combining
reshape.
PiperOrigin-RevId: 724293790
1 个月前
更多推荐
所有评论(0)