从tensorflow的1.5版起,tensorflow也开始启用动态机制Eager Execution了,它支持大部分tensorflow运作和gpu加速
Eager Execution是一个很灵活的机器学习平台,可以提供给(An intuitive interface,Easier debugging,Natural control flow)
下面几行代码可以很容易的帮我们入门使用Eager Execution,使用Eager Execution可以很及时的返回运算结果:
>>> import tensorflow as tf
>>> import tensorflow.contrib.eager as tfe
>>> tfe.enable_eager_execution()
>>> x = [[2.]]
>>> m = tf.matmul(x, x)
>>> print(m)
tf.Tensor([[ 4.]], shape=(1, 1), dtype=float32)
而以往不使用Eager Execution的结果便是:
>>> x = [[2.]]
>>> m = tf.matmul(x, x)
>>> print(m)
Tensor("MatMul:0", shape=(1, 1), dtype=float32)
需要在一个session里运行:
>>> import tensorflow as tf
>>> x = [[2.]]
>>> m = tf.matmul(x, x)
>>> print(m)
Tensor("MatMul:0", shape=(1, 1), dtype=float32)
>>> sess=tf.Session()
>>> print(sess.run(m))
[[ 4.]]
>>> import tensorflow as tf
>>> x = [[2.]]
>>> m = tf.matmul(x, x)
>>> print(m)
Tensor("MatMul:0", shape=(1, 1), dtype=float32)
>>> sess=tf.Session()
>>> print(sess.run(m))
[[ 4.]]
简单的 Eager Execution初步尝试