tensorflow内部原理可参考tensorflow原理
import tensorflow as tf # Simple hello world using TensorFlow # Create a Constant op # The op is added as a node to the default graph. # # The value returned by the constructor represents the output # of the Constant op. hello = tf.constant('Hello, TensorFlow!') # Start tf session sess = tf.Session() # Run the op print(sess.run(hello))
sess.close()
tf.constant(
value, #可以是常数或list
dtype=None,
shape=None, #若定义了该属性,list维度不足,则以最后list的最后一个元素补全
name='Const',
verify_shape=False
)#创建一个常数张量
sess = tf.Session() #Session为所有操作和张量提供了资源,不使用时必须释放sess.close()
run(
fetches, #can be single graph element, list, tuple, namedtuple, dict etc
feed_dict=None,
options=None,
run_metadata=None
) #执行所有计算和张量赋值