ZHANG Xinyun

question about "--episodes-per-batch"

2

Hi, Thanks for your excellent work. Due to the limitation of my GPUs, I couldn't set --episodes-per-batch" to 8 as you did in your paper, instead I set it to...

result for protonet

1

Hi, In https://openreview.net/forum?id=SJl5Np4tPr, I noticed that you've also done some experiments with Prototypical Network. However, I tried to run this experiment (only training on miniImagenet with pre-defined parameters) using your...

pseudo seen and pseudo unseen domains

3

Hi, I found in your code that every epoch you split the ps and pu domains by random.sample(base_set, k=2), so you only use one domain as the ps domain and...

您好，我看season1的extract_feature的代码里面好像没有用到online的数据啊。。。

Dense Regression Branch

6

Could you please explain a little bit where the Dense Regression Branch is in your model? I think I only find the bounding box, cls, and landmark branch but not...

About the finetune accuracy

5

Hi, thanks for your interesting work. I met a problem when I tried to finetune the model. I loaded the released pretrained model BERT_base model, and finetuned it on GLUE...