-
https://github.com/adamian98/pulse/blob/40cacb97df28081e0edf8440a8c3f7c4e6205732/PULSE.py#L44
-
Hi Patrick,
I noticed that steady state events occur much earlier if a state with a large value is constant. This behavior occurs irrespective of the `optx.norm` specified, even though I would assu…
-
-
Hi all!
Will `Oryx` continue to be actively maintained? Are there maintainers who are hoping to continue working on the package?
-
I find that in the original version of the FlowNet/ FlowNet-2，the data augmentation techniques include :
> translation
> rotation
> scaling
> gaussian noise
> contrast
> multiplicative color …
-
Inplace BatchNorm seems to be developed by Mapillary here: https://github.com/mapillary/inplace_abn
This would be a very nice addition to core PyTorch (for memory savings).
cc @ezyang @gchanan @…
-
For profile and uniroot CIs with a two-element random effect term (i.e. a single correlation parameter) we should implement a parameter transformation `rho = theta/sqrt(1+theta^2)`.
For profile/uni…
-
I am trying to figure out what is the correct way to overload the transformation functors for custom types? For example, if I want to be able to transform something like `GeometryBasics.Line` then I c…
-
Hello everyone,
I'm quite new to xAI and Seldon Alibi.
Hope my question is not too naive:
if I train an explainer on a training dataset that received some transformations on data (like Scaling of a…
-
It would be useful to have (fairly straightforward) functions Affine2::new and Affine3::new (or similar names), that take an (n x (n+1)) matrix, and return an affine transform (by appending the row (0…