Satrajit Ghosh

sorry for the lateness in responding to this. i think NWB should strive for uniformity where possible, as dealing with `if`'s is not something you want any downstream developers (e.g.,...

i would leave the defaults to reflect original models but no reason one can't play with some of the architecture.

one other thing, if you followed the training settings in the guide, they are only for demonstration purposes to allow running a tutorial quickly. you should modify the default settings...

@hvgazula - the request was about retraining the brainy model not the kwyk model (you may want to edit the title). the kwyk model uses the bayesian neural network. i...

100MB doesn't make sense on fast disk systems like we have on openmind or for brain imaging data. i believe we have played with TB sized shards as well. i...

@yarikoptic - this gets tricky mostly because functional scans as often gradient-echo based and have losses that cannot be recovered. hence the fieldmap sequences often use other acquisitions to minimize...

@PeerHerholz - the code isn't in the library, but the models are in the zoo: https://github.com/neuronets/trained-models/tree/master/UCL/SynthSR (we are hoping to clean up the cli usage soon and also add more...

@tclose - thank you for all the work you have put into #662 and the thoughts here. this latter issue of wrapping functions is important to pydra, where the functions...

@BastienCagna - at present i don't believe LazyField's have any operators. This may also be a good question in the context of output field templates. perhaps @tclose or @djarecka have...

> Pydra implements space-separated options, which are common to short and long option names in modern standards. pydra actually follows nipype in this perspective and allows various formulations.