Commit Graph

6154 Commits

Author SHA1 Message Date
Afshin1354 c13b255847
Update gradcheck.py (#30) 2020-10-29 17:45:34 -07:00
Omar Ben Brahim d0c3912517
fix for invalid GPU error caused by (test/test_net_speed.py::TestConvSpeed::test_mnist) when testing in CI (#31)
* install the pytorch cpu only version

* get rid of torch gpu version

* test passed seems to get rid of invalid gpu error

* added the libs to requirements.txt

* lol
2020-10-29 17:45:16 -07:00
George Hotz 1dde4ce609 oops, stay in float32 2020-10-29 08:24:12 -07:00
George Hotz 5e7e359706 fix tests 2020-10-29 08:19:07 -07:00
George Hotz 9ae3e9daf3 shape has to be a kwarg now, idk why this didn't break before 2020-10-29 08:13:05 -07:00
George Hotz 2db670ef26 enet refactor + no sigmoid warning 2020-10-29 08:08:21 -07:00
George Hotz 17fa74c15b factor out a couple nn ops 2020-10-29 08:01:12 -07:00
George Hotz f84f6c1edd write sqrt and div using pow 2020-10-29 07:57:25 -07:00
Omar Ben Brahim ec7bdb87ca
clean up CI (#28) 2020-10-29 07:43:31 -07:00
George Hotz cc17e3271a try to recognize cat. do not succeed 2020-10-27 21:41:52 -07:00
George Hotz 03d9c98f5b enet work 2020-10-27 21:23:02 -07:00
George Hotz 0ec279951f enet weight loading 2020-10-27 21:01:48 -07:00
George Hotz e84ad3e27d enet runs 2020-10-27 20:16:29 -07:00
George Hotz 9166eb58bb more enet 2020-10-27 19:37:21 -07:00
George Hotz 41828d768f sigmoid and more enet 2020-10-27 19:13:47 -07:00
George Hotz 09d1ebcdaa examples is better 2020-10-27 18:57:00 -07:00
Göktuğ Karakaşlı 4b163ee270
efficient version of adam (#20)
* counteracted bias initialization

* test new adam

* add optimizer tests

* rename helper function names to fix the test

* remove redundant import
2020-10-27 15:54:40 -07:00
George Hotz 8d75c9e4c4 we have matmul too 2020-10-27 08:57:17 -07:00
George Hotz f9788eba14 parameters, and start on efficientnet 2020-10-27 08:53:35 -07:00
George Hotz 0b68c08de0 literally just bump version for picture on pypi 2020-10-27 08:14:22 -07:00
George Hotz 6b5982b6b3 push pypi 2020-10-27 08:13:15 -07:00
George Hotz 716f86a572 sections 2020-10-27 08:10:51 -07:00
Liam 4a663d31da
less than 1000 lines (#24)
* Actions sloccount check for < 1000 lines (tests and source)

* Sudo lol

* Test sloccount in actions ci

* More tests for the expression

* apt install test to do validation in cli

* fuck test

* try something that probably won't work

* ofcourse not

* test that test fails if lines greater than 1000

* more than 1000 results in 1,000 not 1000. Delete

* remove test lines. Should pass now

* Untouch file

Untouched a file that was changed in testing
2020-10-27 08:07:15 -07:00
George Hotz dcf630dbeb
Merge pull request #22 from tsmcalister/master
adds beautiful and meaningful logo
2020-10-26 16:41:10 -07:00
= 6b44a7f729 adds beautiful and meaningful logo 2020-10-26 18:12:49 +01:00
George Hotz c5db2cf517 readme more 2020-10-26 09:21:48 -07:00
George Hotz 43591a1e71 make the example simpler 2020-10-26 09:19:20 -07:00
George Hotz 1f0514e5df pip 2020-10-26 09:15:31 -07:00
George Hotz 64bd4f7936 lol, it's not 1.0 2020-10-26 09:11:32 -07:00
George Hotz dec2f1c31a
Merge pull request #18 from goktug97/master
add setup.py and change imports to relative
2020-10-26 09:09:31 -07:00
Göktuğ Karakaşlı 81040d926d import only the module 2020-10-26 19:02:06 +03:00
Göktuğ Karakaşlı 8d80726207 two spaces 2020-10-26 18:54:55 +03:00
George Hotz 1654008c1f conv stride support 2020-10-26 08:54:43 -07:00
George Hotz 2a55d7402b clean up ops, refactor pool backward. add stride test 2020-10-26 08:47:11 -07:00
George Hotz 93dceb4bee fix kernel_size bug, name like torch, add test 2020-10-26 08:38:53 -07:00
Göktuğ Karakaşlı cc9bd45b44 add setup.py and change imports to relative 2020-10-26 18:19:50 +03:00
George Hotz d0c9be3e25
Merge pull request #17 from tsmcalister/master
makes maxpool2d parameterizable
2020-10-26 06:35:34 -07:00
Timothy Mc Alister 15e5988323 make default parameters work for functions 2020-10-26 12:43:36 +01:00
George Hotz 2d37fd686b test ops 2020-10-25 19:03:49 -07:00
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