官方文档:
input1 = tf.placeholder(tf.types.float32)
input2 = tf.placeholder(tf.types.float32)
output = tf.mul(input1, input2)
with tf.Session() as sess:
print sess.run([output], feed_dict={input1:[7.], input2:[2.]})
# 输出:
# [array([ 14.], dtype=float32)]
运行之后发现错误:AttributeError: 'module' object has no attribute 'types'
用的是TensorFlow1.7.0,参考了一下:placeholder函数
改成
input1 = tf.placeholder(tf.float32)
input2 = tf.placeholder(tf.float32)
就可以了