我正在尝试在tenserflow上运行一个简单的神经网络代码。但是，出现以下错误，我不知道问题出在哪里。我用谷歌搜索，找不到解决方案。
我在macOS Mojave 10.14.5上使用tenserflow versiob 1.4.0
任何帮助将不胜感激。
干杯， 阿亚拉
import tensorflow as tf
import numpy as np
# A neural network example
from tensorflow.python.keras.datasets import mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data(path='mnist.npz')
print(x_train.shape)
print(y_train.shape)
print(x_test.shape)
print(y_test.shape)
# extract the training data in batches of samples
def get_batch(x_data, y_data, batch_size):
idxs=np.random.randint(0, len(y_data), batch_size)
return x_data[:, :, idxs], y_data[idxs]
# python optimisation variables
learning_rate=0.5
epochs=10
batch_size=100
# declare the training data placeholders
x=tf.placeholder(tf.float32, [None, 28, 28])
# reshape input x - for 28 x 28 pixels = 784
x_rs=tf.reshape(x, [-1, 784])
# scale the input data (maximum is 255.0, minimum is 0.0)
x_sc=tf.div(x_rs, 255.0)
# now declare the output data placeholder - 10 digits
y=tf.placeholder(tf.int64, [None, 1])
# convert the y data to one hot values
y_one_hot=tf.reshape(tf.one_hot(y, 10), [-1, 10])
# now declare the weights connecting the input to the hidden layer
W1=tf.Variable(tf.random_normal([784, 300], stddev=0.03), name='W1')
b1=tf.Variable(tf.random_normal([300]), name='b1')
# and the weights connecting the hidden layer to the output layer
W2=tf.Variable(tf.random_normal([300, 10], stddev=0.03), name='W2')
b2=tf.Variable(tf.random_normal([10]), name='b2')
# calculate the output of the hidden layer
hidden_out = tf.add(tf.matmul(x_sc, W1), b1)
hidden_out = tf.nn.relu(hidden_out)
# now calculate the hidden layer output - no activation applied
logits = tf.add(tf.matmul(hidden_out, W2), b2)
# now let's define the cost function which we are going to train the model on
cross_entropy=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=y_one_hot,
logits=logits))
# add an optimiser
optimizer=tf.train.GradientDescentOptimizer(learning_rate=learning_rate).minimize(cross_entropy)
# finally setup the initialisation operator
init_op = tf.global_variables_initializer()
# define an accuracy assessment operation
correct_prediction = tf.equal(tf.argmax(y_one_hot, 1), tf.argmax(logits, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
# start the session
with tf.Session() as sess:
# initialise the variables
sess.run(init_op)
total_batch = int(len(y_train) / batch_size)
for epoch in range(epochs):
avg_cost = 0
for i in range(total_batch):
batch_x, batch_y = get_batch(x_train, y_train, batch_size=batch_size)
_, c = sess.run([optimizer, cross_entropy], feed_dict={x: batch_x, y:
batch_y.reshape(-1, 1)})
avg_cost += c / total_batch
acc = sess.run(accuracy, feed_dict={x: x_test, y: y_test.reshape(-1, 1)})
print("Epoch: {}, cost={:.3f}, test set accuracy={:.3f}%".format(epoch + 1,
avg_cost, acc*100))
print("\nTraining complete!")
这是我得到的错误
-------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-20-ea13f6382360> in <module>
44
45 # now let's define the cost function which we are going to train the model on
---> 46 cross_entropy=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(labels=y_one_hot,
47 logits=logits))
48 # add an optimiser
AttributeError: module 'tensorflow.python.ops.nn' has no attribute 'softmax_cross_entropy_with_logits_v2'
通过Google搜索错误。