模块“tensorflow._api.v2.train"没有属性“GradientDescentOptimizer" [英] module 'tensorflow._api.v2.train' has no attribute 'GradientDescentOptimizer'

问题描述

我用的是Python 3.7.3，安装了tensorflow 2.0.0-alpha0，但是有一些问题.比如模块tensorflow._api.v2.train"没有属性GradientDescentOptimizer"这是我所有的代码

I used Python 3.7.3 and installed tensorflow 2.0.0-alpha0,But there are some problems。such as module 'tensorflow._api.v2.train' has no attribute 'GradientDescentOptimizer' Here's all my code

import  tensorflow as tf
import  numpy as np

x_data=np.random.rand(1,10).astype(np.float32)
y_data=x_data*0.1+0.3


Weights = tf.Variable(tf.random.uniform([1], -1.0, 1.0))
biases = tf.Variable(tf.zeros([1]))
y=Weights*x_data+biases

loss=tf.reduce_mean(tf.square(y-y_data))

optimizer=tf.train.GradientDescentOptimizer(0.5)
train=optimizer.minimize(loss)

init = tf.global_variables_initializer()  

sess = tf.Session()
sess.run(init)          

for step in range(201):
    sess.run(train)
    if step % 20 == 0:
        print(step, sess.run(Weights), sess.run(biases))

推荐答案

在 TensorFlow 2.0 中，Keras 成为默认的高级 API，优化器功能从 tf.keras.optimizers 迁移到单独的 API称为 tf.optimizers.它们继承自 Keras 类优化器.tf.train 中的相关函数未包含在 TF 2.0 中.所以要访问GradientDescentOptimizer，调用tf.optimizers.SGD

In TensorFlow 2.0, Keras became the default high-level API, and optimizer functions migrated from tf.keras.optimizers into separate API called tf.optimizers. They inherit from Keras class Optimizer. Relevant functions from tf.train aren't included into TF 2.0. So to access GradientDescentOptimizer, call tf.optimizers.SGD

这篇关于模块“tensorflow._api.v2.train"没有属性“GradientDescentOptimizer"的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！