An_idi0t

may I ask a question about the algorithm ?

4

hello ,big gun, I'm new in this area, after reading your paper MAML,I am confused why you update theta in the inner loop to get theta' , and then in...

Hello, I found you code calculate the masking using tf.not_equal(input_ids, 0), but in my vocab.txt, 0 refers to a character rather than , how to send manually constructed masking embedding...

一个处理20NG 数据集的问题

1

你好，我注意到data/corpus/20ng.txt 有19026行数据，不过data/20ng.txt只有18846行，我想确认下，您的处理方式是corpus里面的前面18846行数据和它一一对应，剩下的丢弃是吗？

Hi, Xing it's an interesting work, but I wanna , dose the text information only influence the construction of prototype? If so, when there comes visually similar query samples, e.g....

关于classifier normalize？

6

你好，看了您的paper受益匪浅。 这边有个问题想问一下，paper中提到，借鉴propensity score的思想，对logit进行normalize。不知道这个是什么原理呢?如果不加normalize对de-confound的影响大吗？

Hello brother, it's really a good job. But what confused me is that in training step 2, when we need to train a weight generator, you keep on training the...