convoluted connor a changé de compte pour @notwa@cybre.space :
80b3e936f186f59b

convoluted connor @notwa@witches.town

played guitar for [duration] minutes this morning, felt good. i'm a lot more confident in my playing lately, but i can't skimp on practice so i'll get back to that next time.

if python 2 is so good why isn't there a python 2 2

it's really just for fun and getting a feel for techniques

today I bumped up all my *mnist classifiers up a percent in accuracy through a lot of careful tweaking. I think I'm gonna look into more regularization methods and then put it aside for a while 'cause I really don't think I can outdo convolutional networks with my toy fully connected network

i forgot to mention the number being factored: 112800

just realized i should be using a batch size of like 940 instead of 400 for emnist if i wanna compare to plain mnist. also i should start using programs to find factors 'cause i totally missed 480 and 940 being factors when i did it in my head.

and yeah in retrospect i can't explain why setting bold text would make it this darker color but i guess i just got used to it

ah there we go
"\e[1m" -> "\e[36m"

huh, some color code functionality got fixed in mintty. one of my scripts was actually relying on it, but now i realize the old behavior didn't make any sense. now i'm trying to figure out how i wanna update my script.

i remember spending like 6 hours just micro-optimizing one track in nitronic rush against my own ghosts. i loved seeing all the subtle differences in each ghost and taking note of each to get the absolute best possible time.

my favorite part of nitronic rush and distance is simply just being able to crank the number of ghosts up to 20

oh yeah, here's something from my trackmogrify adventures the other night; probably the most points i'll ever get in one "trick" witches.town/media/dJ8DcvZ8p43 witches.town/media/iDdk7dJIQdz

windows Afficher plus