Séb Arnold

In hindsight, this is a bad idea. Instead the web app should be made efficient enough to handle large collections of results.

Basic functionality implemented. Mathematically not equivalent, will need to fix that.

Ideally, if a snapshot is extended you would be able to retrieve the history of hyperparameters that were used at each snapshot.

Hi Daler, Thanks for opening the issue, I agree that the guide is light on explanations. I'll try to flesh it out as soon as I have a bit of...

I am not sure if this is really a good idea in the end. It feels like once results are saved, they should never be modified since they are the...

Visualizing Results and Optimizing Hyperparameters drafts are online. Managing Experiments probably needs #11 and #10 to be implemented before the full tutorial can be put online.

Hey @brando90, thanks for this PR again. I think it needs similar small changes as for #303.

Thanks for reporting this, @shkim960520. The current hyper-parameters should match the tensorflow code release, but I had to tune them a little get 65.5%. If I recall correctly, it was...

It seems like changing `model = l2l.vision.models.MiniImagenetCNN(ways)` for ` model = l2l.vision.models.MiniImagenetCNN(ways, hidden_size=32)` on l. 86 fixes the issue as it matches the original code. Could you confirm this also...

Hello @mi92, Thanks for reporting this discrepancy! Have you tried fixing by using the same final learning rate? If it works better, would you like to submit a PR for...