Elliot Hallmark
Elliot Hallmark
Has there been any research on how this strategy interacts with a learning rate schedule? Especially for something extreme like the one-cycle policy (super convergence). It seems like the history...
Sorry if I missed this (and I didn't find a mailing list). Looping through entities is very convenient, but I'd like to specify queries for performance. Trying to make a...
detect if screen has resized and ask windows to resize themselves. Currently, windows size themselves to fit initial terminal size but don't update their size ever again.
Make an example of a menu that changes it's own options. (what callback would that be?). Sub menus and paginations.
Don't cut mid word and use indentation to make it clear a line has wrapped.
I'm sure the update/refresh calls are sub optimal. If performance ever mattered, this should be looked at.
The outer parallelization of calling variants with the pileup model using GNU parallel is inefficient for targeted amplicon BAM files where large portions of contigs have no supporting reads. In...
Our use case is variant calling on the output of a targeted amplicon assay on many samples in parallel. The way that `clair3_c_impl.sh` parallelizes the pileup calling step in this...
It would be great to have any training code at all for Kosmos 2.5 and to be able to have a chance to fine tune it. It's an amazing model...