在适合网络涉及tf.map_fn()时TFLearn陷入困境

时间:2017-10-26 12:27:43

标签: python python-3.x tensorflow deep-learning tflearn

我的代码是

     ...
     network = fully_connected(network, 512, activation='relu')
     print(network)
     #network = tf.map_fn(lambda x:tf.abs(x), network)
    network=...

tf.abs op就是一个例子,我已经尝试过其他函数,包括一个什么都不做但只返回输入的函数,但这些都没有帮助)

通过评论第三行,该程序将永远停留在这里:

Preprocessing... Calculating std over all dataset (this may take long)...
STD: 0.30816 (To avoid repetitive computation, add it to argument 'std' of `add_featurewise_stdnorm`)
INFO:tensorflow:Summary name Accuracy/ (raw) is illegal; using Accuracy/__raw_ instead.
---------------------------------
Training samples: 55000
Validation samples: 10000

我现在不知道该怎么办。

0 个答案:

没有答案