Daniel Nouri
Daniel Nouri
> I observe that there is no chatting a while ago. Does the project still have support? It's still used by some people. Although Theano, the most important library used...
I updated the 'greeting' in the way that @caleytown suggested. I think it's what people expect.
@caleytown If you've initialized your network before, e.g. you've trained it with `fit` already before your loop, then make sure that you initialize the network again (and thus pass the...
Excellent. Thanks! On Thu, 18 Nov 2021 at 09:33, James A. Fellows Yates < ***@***.***> wrote: > I just want post here that I recently added nolearn to conda-forge >...
So you're thinking these two could be refactored? Maybe we could see such a refactored version to be able to judge which one is better? The one major difference that...
It seems pretty damn useful for classification fits. :-)
A `on_batch_finished` handler has been added since. But it won't cover your use case where you do early stopping between epochs. However, I think that @dirtysalt's `MinibatchIterator` works well enough...
You're probably seeing the [effect of this change](https://github.com/dnouri/nolearn/pull/228). Can you try setting `config.reoptimize_unpickled_function` to True?
That thread is a little confusing, with multiple issues. Can you paste the traceback that you're getting?
@BenjaminBossan Do you mind describing the difference between this and the implementation that was removed in #228?