xljhtq

Adv Loss is not supported by the paper???

4

Hi, I want to know where the adv loss is different from the domain loss?? In another word, the adv loss in the paper "Adversarial Multi-task Learning for Text Classification"...

Hi, I have runned your code, but I find that Interleaved Training is not used in adversarial training in your code. So I want to know whether it is needed...

您好博主： 如题，batch_norm_layer这个函数似乎源码中并没有用上。这个正常是放在哪块的呢？直接放在输入方直接做batch_norm的吗？

您好，请问一下： ### 最终得到attention_score表示的是交叉特征重要性，但是interaction_score表示的是什么呢？因为最终这两个score是相乘的，interaction_score还有可能是负数。 ### 比如下面截图的paper中，user-tag 和user-item中的interaction_score都是负的，那么最终是看attention_score大小来决定哪个交叉特征重要还是看attention_score*interaction_score谁大谁重要呢？ 

how to shuffle batches with the iterator?

1

Hi, I have read the code completely and I appreciate your code style. So I want to know how to complete shuffling mini-batches in the code Because there exists no...

problem about tf.layers.batch_normalization

4

Hi, in the DPCNN code, I find that the function "tf.layers.batch_normalization" is used when training the model. But the parameter "training" is not set True! e.g conv3 = tf.layers.batch_normalization(conv3, training=True)...

The use of GPU is not efficient ????

1

When I trained the model with GPU and the training data is very bigger, I found low utilization rate of GPU, namely about 11% and the utilization rate of CPU...

Big Data Problem

1

When I load the file with many data, I have met with a problem. The free memory will be smaller and smaller because of the exitence of sorting algorithm in...

2.4.6这种老版本下，停用词表如何自定义？

2

博主，您好： 在以前版本下，elasticsearch中似乎没有加载停用词的地方，这个应该在哪里进行自定义呢？