Jan

Thank you for you interest @vedantog ! You can take any example from here https://deepdow.readthedocs.io/en/latest/auto_examples/index.html and scroll all the way down and there should be a `Download Jupyter notebook ...`...

Hey there! Looking at the traceback I think this issue has to do with incorrect installation of `cvxpylayers` and more specifically it's dependency `diffcp`. I would image that if you...

> [bt](https://github.com/pmorissette/bt) is a good choice. Have you used it? I know there are some others in the Python ecosystem but there does not seem to be a clear-cut winner,...

Cool! I might give it a try! It would be nice to create minimalistic example of `deepdow` +`bt`:) Anyway, if by any chance you are interested you can also give...

Interesting! I guess one major thing that is missing in `deepdow` is that it is not dynamic - it does not tell you when to change the weights of the...

Thank you for the post. I actually never heard of this SSD concept. Really interesting. If I understood it correctly, one can characterize (sufficient + necessary condition) the SSD efficient...

Sorry for a very late response. Yeh, it seems to be because of your `numpy`. The last CI build on `master` had `numpy=1.21.0` (https://app.travis-ci.com/github/jankrepl/deepdow/jobs/523230724#L455) and everything passed. Locally, `1.21.0` works...

Amazing! Feel free to post any updates here

Hey there! I think what I meant here was that it would be nice to create a new `Benchmark` subclass (see `deepdow/benchmarks.py`) that would accept a fixed `w` of shape...

Hey there! Check out this module to get some inspiration: https://github.com/jankrepl/deepdow/blob/8fb6976a2bc77bade4d5c0e5be3974c67845f11b/deepdow/layers/transform.py#L62 And here is the documentation: https://deepdow.readthedocs.io/en/latest/source/layers.html#rnn I hope that helps:)