上篇文章简单介绍了一些常见的运算的例子,但是tensorflow强大在于对于tensor的运算,这里以维度为2的tensor(矩阵)为例,介绍一下常见的运算相关的方法。
例1: 加法
代码片段
a = tf.constant([[1,2],[3,4]])
b = tf.constant([[5,6],[7,8]])
add = a + b
with tf.Session() as sess:
print("a = " + str(sess.run(a)))
print("b = " + str(sess.run(b)))
print("a + b = " + str(sess.run(add)))
简要说明:
使用表达式或者tf.add进行矩阵加法
例2: 减法
代码片段
a = tf.constant([[1,2],[3,4]])
b = tf.constant([[5,6],[7,8]])
sub = tf.subtract(b,a)
with tf.Session() as sess:
print("a = " + str(sess.run(a)))
print("b = " + str(sess.run(b)))
print("tf.subtract(b,a) = " + str(sess.run(sub)))
简要说明:
使用表达式或者tf.subtract进行矩阵减法
例3: 乘法:tf.matmul
代码片段
a = tf.constant([[1,2],[3,4]])
b = tf.constant([[5,6],[7,8]])
mul = tf.matmul(a,b)
with tf.Session() as sess:
print("a = " + s