-
In FAQ, you mention that hyperparameters can be tuned using all the data:
"How do I select the hyperparameters of the first stage models?
Alternatively, you can pick the best first stage models …
-
Hello,
I'm hoping to confirm that the hyperparameters specified in your paper are correct. Specifically, for miniimagenet, 100k meta steps were taken during training? I ask because it seems some of…
-
Though you haven't yet done an extensive hyperparameter search, might you give us one or two examples of hyperparameter settings you have used?
-
Hi!
When I try to use the original hyperparameters in the paper (ngf=ndf=128), the generator won't catch up with the discriminator and its error will get stuck forever. Is the Adam algorithm missin…
-
The paper only contains some of the discriminator hyperparameters
![image](https://user-images.githubusercontent.com/40682795/95158945-693a8680-07cf-11eb-99b1-75e50270ba3b.png)
However, there ar…
-
Hi @ficstamas ,
many thanks for open sourcing this very interesting implementation!
I would like to train own models with this implementation (as additional models to my ByT5 project on [histori…
-
Hello, I'm very interested in your work and plan to reproduce the experiments. Could you please provide the detailed hyperparameters on different datasets? Thanks.
-
Hi,
Interesting work here!
Can you please provide the details on the following hyperparameters used for each of the following datasets,
INaturalist18 : weight decay, learning rate used.
ImagenetL…
-
Hi Shion,
I have tried training your model several times on many different learning rates and epochs, yet we are not getting results for MLP classification that are nearly as good as yours. DO. you…
-
Hello, thanks for sharing your excellent work!
I have some specific questions about the selection of hyperparameters in experiments and hope you can answer them:
1. In the GDN.py class OutLayer …