11648 Commits

Author SHA1 Message Date
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
George Hotz
65f3a9d499 Merge pull request #11 from 0xNaN/master
tiny gradcheck
2020-10-22 10:22:42 -07:00
Adrian Garcia Badaracco
5ed2bbfa0a remove newline 2020-10-21 18:43:11 -05:00
Adrian Garcia Badaracco
81fe70a3c0 make single line 2020-10-21 18:42:40 -05:00
Adrian Garcia Badaracco
fa99c2c723 actually add files 2020-10-21 18:38:48 -05:00
Adrian Garcia Badaracco
466a67f4dd Add requirements.txt 2020-10-21 18:37:47 -05:00
0xNaN
4bdb524da7 moving mask_like to utils 2020-10-22 01:30:59 +02:00
0xNaN
ac4ef3a588 removing docs since interface is now the same of pytorch, LOC < 50 ;) 2020-10-22 01:28:52 +02:00
0xNaN
f6cad1d7d8 s/model/func/ 2020-10-22 01:28:52 +02:00
0xNaN
d95adbddb4 gradcheck now returns only a bool, refactoring of test_gradcheck 2020-10-22 01:28:52 +02:00
0xNaN
adbfc67456 test jacobian and numerical_jacobian against torch.autograd.functional.jacobian 2020-10-22 01:28:52 +02:00
0xNaN
7458089b3b fix shape of Jacobian to (n_out, n_in) 2020-10-22 01:28:52 +02:00
0xNaN
1561d3b9c0 extracting jacobian and test_jacobian 2020-10-22 01:28:52 +02:00
0xNaN
93bc3c22a0 tiny gradcheck 2020-10-22 01:28:52 +02:00
George Hotz
e8feaa53d6 Merge pull request #12 from adriangb/pytest-again
TST: Pytest round 2
2020-10-21 16:19:43 -07:00
Adrian Garcia Badaracco
9a8be135a7 incorporate changes 2020-10-21 13:21:44 -05:00
Adrian Garcia Badaracco
58b4f191a4 Merge remote-tracking branch 'upstream/master' into pytest-again 2020-10-21 13:19:58 -05:00
George Hotz
5a1ff084d8 Merge pull request #13 from geohot/numba
use numba to double conv speed
2020-10-21 09:51:42 -07:00