-
Traceback (most recent call last):
File "C:/Users/Dingd/Documents/GitHub/MAML-Pytorch-master/omniglot_train.py", line 95, in
main(args)
File "C:/Users/Dingd/Documents/GitHub/MAML-Pytorch-m…
-
https://github.com/dragen1860/MAML-Pytorch/blob/98a00d41724c133bd29619a2fb2cc46dd128a368/MiniImagenet.py#L81
should be changed to `OrderedDict`.
Result can't be reproduced because the use of dicti…
-
您好，前陣子剛研究了您修改前的那個版本，想請問修改前後主要差別是多了evaluate用於驗證MAML效果勝過自動化生成的參數嗎?
另外，內容提到的maml.h5跟前一個版本產生出來的maml.h5是相同的嗎，還是是用不同dataset train出來的結果?
-
Instead of messing with MAML file tags, is there a WYSIWYG tool to edit MAML files?
-
作者您好！
因为近期在follow您的工作。关于您的实验设置有以下两点疑惑：
1.论文提到，实验是采用3天的作为目标数据，剩余数据作为验证数据。我在代码里看到的是这样：
这样的话是用的后20%的数据作为测…
-
**Interesting Papers:**
Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves
Metz et al. (2020)
M2SGD: Learning to Learn I…
-
The newer 0.14.1 version of platyPS does something that the 0.14.0 version does not:
If you use the Session parameter with New-MarkdownHelp (which I'm forced to do with Exchange, since all Exchange…
-
Hello,
Thanks for this great library.
I have a question. I want to use RL2 and specifically the RL2TRPO algorithm with discrete action-space. However, it seems that the current implementation do…
-
In line 126 of few_shot/maml.py:
`meta_batch_loss.backward()`
however, the graph for meta_batch_loss does not use model parameters. Each loss used to get meta_batch_loss was obtained using fast_…
-
Hi Fangzhou,
Thank you for your excellent work. The codebase is well-organized and easy to follow.
When I tried to train `mini-imagenet` using either 2 - 8 GPUs by the following command,
```…