115 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
George Hotz	2eebbd32c6	ops test speed	2020-10-25 19:01:02 -07:00
George Hotz	b27bcbe4b4	avgpool and test refactor	2020-10-25 18:40:01 -07:00
George Hotz	4c42676cb6	400 -> 200	2020-10-25 17:19:59 -07:00
George Hotz	567707a5f6	rename max_pool2d to match torch, remove more fast conv crap	2020-10-25 17:16:47 -07:00
George Hotz	5d1373c71b	if you want fast convs, revert this	2020-10-25 17:10:34 -07:00
George Hotz	ea41f5e1c1	seems more generic	2020-10-25 16:40:37 -07:00
George Hotz	2333c4dea7	no tqdm in actions	2020-10-25 16:40:08 -07:00
George Hotz	ad48061927	better sort in torch profiler	2020-10-25 16:07:49 -07:00
George Hotz	82f8e10813	no hacks in that test	2020-10-25 15:52:05 -07:00
George Hotz	4baa4c041f	it's crazy how much faster pytorch is than numpy	2020-10-25 15:42:33 -07:00
George Hotz	5ddbd7f04b	2 to 3x slower than torch	2020-10-25 15:27:33 -07:00
George Hotz	f8311f5ecd	print fp/bp mnist	2020-10-25 15:08:18 -07:00
George Hotz	d38367b561	cleaner relu	2020-10-25 14:35:04 -07:00
George Hotz	5c179d18ad	add profiling for mnist net	2020-10-25 14:20:55 -07:00
George Hotz	8fcada8071	faster and better convnet	2020-10-25 13:48:44 -07:00
George Hotz	1255903519	hmm, no reason it should have been wrong, numpy weirdness	2020-10-25 13:14:12 -07:00
George Hotz	96f9cdb8a0	woah, fastconv is wrong	2020-10-25 12:56:42 -07:00
George Hotz	bb98cdfef7	improve conv testing	2020-10-25 12:46:04 -07:00
George Hotz	ef24aac09e	finally, fast convs	2020-10-25 12:39:44 -07:00
George Hotz	0f02084805	conv isn't fast yet	2020-10-25 12:13:58 -07:00
George Hotz	12641d5bd7	umm, okay slow col2im	2020-10-25 12:01:59 -07:00
George Hotz	67506eb6ba	fast im2col	2020-10-25 11:49:35 -07:00
George Hotz	c9968756d1	allow the line profiler to work	2020-10-25 11:13:40 -07:00
George Hotz	5062c2c8ff	profile conv better	2020-10-25 11:11:00 -07:00
George Hotz	c74764bac3	oops, set to None	2020-10-25 08:28:18 -07:00
George Hotz	935f5ddaaa	always keep batch size out front	2020-10-25 08:14:07 -07:00
George Hotz	b91fd3afad	maxpool	2020-10-25 07:43:34 -07:00
George Hotz	3cef527e80	Merge pull request #14 from adriangb/reqs-txt ... requirements.txt	2020-10-24 07:06:08 -07:00
Adrian Garcia Badaracco	02ecdc86c3	remove install from workflow	2020-10-24 09:03:22 -05:00
Adrian Garcia Badaracco	2a64bd5980	everyone's a dev	2020-10-24 09:01:15 -05:00
George Hotz	5216a1d9f3	refactor into tensor and ops	2020-10-23 10:34:21 -07:00
George Hotz	9b9e47f369	added conv profile test	2020-10-23 09:46:10 -07:00
George Hotz	5756115e57	anyone else let down by the fast conv?	2020-10-23 09:09:29 -07:00
George Hotz	bcb60e0b7c	wow, you have to name them test	2020-10-23 06:33:18 -07:00
George Hotz	f16c5577f0	useless parens	2020-10-23 06:29:57 -07:00
George Hotz	0f358a9cfb	remove the eps from the sqrt	2020-10-23 06:28:32 -07:00
George Hotz	2259c9faa1	low lr improves rmsprop	2020-10-23 06:22:32 -07:00
George Hotz	d56a0af6cb	t isn't used	2020-10-23 06:17:40 -07:00
George Hotz	49ae15a450	i like that comma	2020-10-23 06:12:04 -07:00
George Hotz	eda29fa0e0	clean up test	2020-10-23 06:11:38 -07:00
George Hotz	373b4e341b	Merge pull request #15 from f0ti/master ... added RMSprop optim	2020-10-23 06:08:20 -07:00
f0ti	0b87aaca1e	update rsmprop	2020-10-23 14:46:45 +02:00
f0ti	c5f726ec2e	all three	2020-10-23 11:53:01 +02:00
f0ti	6a38ccb6b0	update rmsprop and readme	2020-10-23 11:49:43 +02:00
George Hotz	21ebb0b769	if you wait 24 seconds, that gets 98%	2020-10-22 21:49:14 -07:00
George Hotz	816f648161	chans doesn't need to be in self	2020-10-22 21:19:35 -07:00
George Hotz	77251cc6c3	7x7 conv = more accuracy	2020-10-22 21:10:27 -07:00
George Hotz	64b128b712	shorter and faster conv	2020-10-22 20:54:11 -07:00
George Hotz	1d612f17ce	remove float64 check	2020-10-22 20:27:21 -07:00
f0ti	7e1eddb0c5	added RMSprop optim	2020-10-23 02:50:02 +02:00