Oliver Cobb

Particularly important given we require models defined using subclassing API to have the annoying `get_config()` and `from_config()` methods defined.

Do we think users are ever going to have equal reference and test batch sizes in practice? I'd guess almost always the reference set is going to be much larger....

> Thanks for your comments @ojcobb, I've had a first go at addressing them. > > One interesting thing to note is that in order to save some compute, in...

Nice work! Indeed the previous coupling to `GaussianRBF` got a bit nasty in places and is nice to have got rid of all that and extended with some new possibilities!...

Hi @Joshwlks and @vinyasHarish95, I think there's some confusion here arising from a slight misinterpretation of `SpotTheDiff`'s output. It should not be interpreted as a unique description of the difference...

I will take a closer look at the code next week but the overall approach you've described sounds sensible to me. I agree that there's no need for a method...

Beyond what we've discussed around the preemptive renaming of `reset` to `reset_state` it all looks good to me! Good work on the additional docstrings too!

Hi @dtinth, would you mind confirming whether this still works with the latest version of Excalidraw? I'm struggling to get it working (also on Surface Pro 7 and Edge). Thank...

Hi @vinyasHarish95, Thanks for pointing out this potential source of confusion. The sentence "_it is important that the learned detectors are trained on training data which is held-out from the...