试运行了《TensorFlow: 实战Google深度学习框架》一书中第三章全连接网络训练代码,windows系统使用python 3.8, tensorflow2.3.0, numpy
源代码如下:
import tensorflow as tf
from numpy.random import RandomState
batch_size = 8
w1 = tf.Variable(tf.random_normal([2,3], stddev = 1, seed = 1))
w2 = tf.Variable(tf.random_normal([3,1], stddev = 1, seed = 1))
x = tf.placeholder(tf.float32, shape = (None,2), name = 'x-input')
y_ = tf.placeholder(tf.float32, shape = (None,1), name = 'y-input') #真值
a = tf.matmul(x,w1)
y = tf.matmul(a, w2) #预测值
cross_entropy = -tf.reduce_mean(y_ * tf.log(tf.clip_by_value(y,1e-10, 1.0)))
train_step = tf.train.AdamOptimizer(0.001).minimize(cross_entropy)
rdm = RandomState(1)
dataset_size = 128
X = rdm.rand(dataset_size,2)
Y = [[int(x1+x2 < 1)] for (x1,x2) in X]
init_op = tf.initialize_all_variables()
with tf.Session() as sess:
sess.run(init_op)
print(sess.run(w1))
print(sess.run(w2))
STEPS = 5000
for i in range(STEPS):
start = (i * batch_size) % dataset_size
end = min(start+batch_size, dataset_size)
sess.run(train_step, feed_dict = {x: X[start:end], y_: Y[start:end]})
if i % 1000 == 0:
total_cross_entropy = sess.run(cross_entropy, feed_dict = {x: X, y_: Y})
print("After %d training step(s), cross entropy on all data is %g"%(i, total_cross_entropy))
print(sess.run(w1))
print(sess.run(w2))
创建__init__.py文档,运行后报错module 'tensorflow' has no attribute 'random_normal',将random_normal改为random.normal后解决
报错module 'tensorflow' has no attribute 'placeholder',后将'import tensorflow as tf' 改为
import tensorflow.compat.v1 as tf
tf.disable_v2_behavior()
运行成功!