TensorFlow——交互式使用會話：InteractiveSession類

目的是在交互式環境下（如jupyter），手動設定當前會話為默認會話，從而省去每次都要顯示地說明sess的繁瑣，如：Tensor.ecal(session=sess)或sess.Operation.run()

只需要寫成Tensor.ecal()或Operation.run()

>>> import tensorflow as tf
>>> sess = tf.InteractiveSession()
can't determine number of CPU cores: assuming 4
I tensorflow/core/common_runtime/local_device.cc:25] Local device intra op parallelism threads: 4
can't determine number of CPU cores: assuming 4
I tensorflow/core/common_runtime/local_session.cc:45] Local session inter op parallelism threads: 4
>>> x = tf.Variable([1.0, 2.0])
>>> a = tf.constant([3.0, 3.0])
>>> x.initializer.run()    # initializer初始化了變量x 初始化了的x可以直接用run()而不需要用sess.run()來運行
>>> sub = tf.sub(x, a)    # tf里的矩陣減法函數是sub(),其實寫成x-a沒錯
>>> print(sub.eval())    # 在這里，sub.eval()相當於sess.run(sub)，因為操作sub與張量sub同名了
[-2. -1.]
>>> sess.close()