A computer vision model that takes in streamed games and outputs a player statistic that factors in non-descriptive events — i.e. giving the correct call at the correct time, or poaching in the lane to force a bad throw.
I expect this to be trained using a transformer and written in Python. It is inspired by Andrew Wood's analytical Ultimate dream.
This was my first voyeur into splitting my source code up into multiple files, much in the way we do for any good computer program.
I produced a pocket version of the easy-to-forget rules in Ultimate Frisbee
Here is the directory structure
[rpi@rpi treatises]$ tree frisbee
frisbee
├── 0-field.tex
├── 1-summary.tex
├── 2-definitions.tex
├── 3a-pull.tex
├── 3b-stall.tex
├── 3c-stoppages.tex
├── 3d-misc.tex
├── 4-fouls.tex
├── 4-turnovers.tex
├── 5-fouls.tex
├── 5-infractions.tex
├── 6-infractions.tex
├── 6-violations.tex
├── 7-violations.tex
├── 8-handsignals.tex
├── rules.aux
├── rules.log
├── rules.pdf
└── rules.tex