Tagger
Tagger copied to clipboard
XMUNLP
Deep Semantic Role Labeling with Self-Attention
我想查看train时features里面是包含的是什么文件 试着print(features）的时候报错了 可能是我的train.txt不行 所以我试图了解feature到底包含了哪两种信息 如果能给出具体的答案的话，对我有非常大的帮助！
I'm using the provided command to generate outputs, the one in the section under "decoding." I have a few questions: 1) It continuously prints things like: ``` 2018-05-14 16:51:35.363220: I...
Hi, Thanks for your great work ! I am wondering how to set the TRAIN_PATH as mentioned in the training command. I tried to set it to the path that...
请问 您在loss中加入 with tf.variable_scope("losses_avg"): loss_moving_avg = tf.get_variable("training_loss", initializer=100.0, trainable=False) lm = loss_moving_avg.assign(loss_moving_avg * 0.9 + loss * 0.1) tf.summary.scalar("loss_avg/total_loss", lm) with tf.control_dependencies([lm]): loss = tf.identity(loss) 为什么要加入一个losses_avg
When i trained the model with these parameters, the result is fine. Normally, F1 Score is up to 0.81 or even better. ``` glove.6B.100d.txt feature_size=100 hidden_size=200 filter_size=800 ``` But when...
我大致看了下代码，似乎每一行起始是一个数字，是什么含义？ 我试了 """ 4 john wants to go """ 报数组引用越界的错 改成 """ 1 john wants to go """ 就好了。 麻烦详细的介绍下decoding时的数据格式
