Python Tensorflow._api.v2.train 没有属性“AdamOptimizer”
声明：本页面是StackOverFlow热门问题的中英对照翻译，遵循CC BY-SA 4.0协议，如果您需要使用它，必须同样遵循CC BY-SA许可，注明原文地址和作者信息，同时你必须将它归于原作者（不是我）：StackOverFlow
原文地址: http://stackoverflow.com/questions/55318273/
Warning: these are provided under cc-by-sa 4.0 license. You are free to use/share it, But you must attribute it to the original authors (not me):
StackOverFlow
Tensorflow._api.v2.train has no attribute 'AdamOptimizer'
提问by MatlabNewb
When using
使用时
model.compile(optimizer = tf.train.AdamOptimizer(),
loss = 'sparse_categorical_crossentropy',
metrics=['accuracy'])
in my Jupyter Notebook the following Error pops up:
在我的 Jupyter Notebook 中，弹出以下错误：
module 'tensorflow._api.v2.train' has no attribute 'AdamOptimizer'
模块“tensorflow._api.v2.train”没有属性“AdamOptimizer”
Tensorflow Version: 2.0.0-alpha0
Tensorflow 版本：2.0.0-alpha0
Do you think the only possibility is to downgrade the TF version?
你认为唯一的可能就是降级TF版本吗？
回答by Meixu Song
tf.train.AdamOptimizer() => tf.optimizers.Adam()
From https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/optimizers
来自https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/optimizers
回答by William G
I haven't tried 2.0 yet, but from what I've seen on the dev submit videos, you can use
我还没有尝试过 2.0，但从我在开发提交视频中看到的，你可以使用
model.compile(optimizer = 'adam',
loss = 'sparse_categorical_crossentropy',
metrics=['accuracy'])
回答by Rriskit
tf.optimizers.Adam()
Is the way to go. No reason to downgrade.
There are lots of changes in tf 2.0 compared to 1.14.
Note that the parameter-names of Adam have changed, too. e.g. beta1 is now beta_1, check the documentation in Meixu Songs link.
是要走的路。没有理由降级。
与 1.14 相比，tf 2.0 有很多变化。
请注意，Adam 的参数名称也已更改。例如 beta1 现在是 beta_1，请查看 Meixu Songs 链接中的文档。
回答by ShaneCalder
model.compile(optimizer = tf.keras.optimizers.Adam(),
loss = 'sparse_categorical_crossentropy',
metrics=['accuracy'])
回答by MrRex
I had the same error. I removed
我有同样的错误。我删除了
tf.train.AdamOptimizer()
And I wrote
我写了
tf.optimizers.Adam()
Instead.
反而。
回答by Adi
It's a minor change in upgraded version.
这是升级版的一个小改动。
Please use:
请用：
model.compile(optimizer=tf.optimizers.Adam(), loss="sparse_categorical_crossentropy")
Thanks!
谢谢！
