Frédéric Branchaud-Charron
Frédéric Branchaud-Charron
Hello, I'm not familiar with fastAI unfortunatly. But let me know if that works for you: 1. ActiveLearningDataset works on a pytorch Dataset. 2. ActiveLearningLoop requires a function that returns...
Anything I can assist with? Happy to schedule a call as needed too.
Sounds good, what I was thinking was the following: * Add torchmetrics as a dependency (poetry add torchmetrics) * Make sure that baal.modelwrapper.ModelWrapper._update_metrics and _reset_metrics works with PL metrics and...
I just wrote the following Baal metrics that leverage torchmetrics. We have very similar APIs so I think its a good idea to scrap Baal metrics in favor of torchmetrics....
Hello, I would have time to work on it this week if you are not already started.
> I like this. thanks a lot @Dref360. I was only wondering don't you think it is more descriptive to have "active_step" as the key for metrics and have "datasize"...
I think this is ready for review. I added the dataset size in the response of `get_metrics`.
@rafapi just added an example in our documentation.
Quick video showcasing the feature. https://www.loom.com/share/4b7d0eeee187463cac12ecd57828c5fe
Do we know what is missing? BALD is in numpy, I do not know how to have a patch_module for TF, but we could do without for now.