147 Commits

Author	SHA1	Message	Date
Joseph Redmon	b0106d7bde	probably stuff changed	2015-04-13 14:09:55 -07:00
Joseph Redmon	cf0300ea55	dropout probably ok	2015-03-27 17:32:01 -07:00
Joseph Redmon	d7d7da2653	Fixed im2col mistake >< face#palm	2015-03-26 19:13:59 -07:00
Joseph Redmon	9d418102f4	using caffe's im2col, it's so much better\!	2015-03-21 14:17:39 -07:00
Joseph Redmon	4af116e996	gonna change im2col	2015-03-21 12:25:14 -07:00
Joseph Redmon	2313a8eb54	Split commands into different files	2015-03-06 10:49:03 -08:00
Joseph Redmon	fb9e0fe336	Big changes to detection	2015-03-04 14:56:38 -08:00
Joseph Redmon	0f645836f1	Detection is back, baby\!	2015-02-10 19:41:03 -08:00
Joseph Redmon	2f62fe33c9	saving weight files as binaries, hell yeah	2015-02-06 18:53:53 -08:00
Joseph Redmon	c592fc7491	New name: Darknet	2015-01-27 13:52:37 -08:00
Joseph Redmon	153705226d	Bias updates bug fix	2015-01-27 13:31:06 -08:00
Joseph Redmon	809f924db2	CUDA so fast	2015-01-22 16:38:24 -08:00
Joseph Redmon	aa5996d58e	Faster	2015-01-12 17:27:08 -08:00
Joseph Redmon	4ab366a805	some fixes, some other experiments	2014-12-22 14:35:37 -08:00
Joseph Redmon	f88baf4a3a	99 problems	2014-12-18 15:46:45 -08:00
Joseph Redmon	28e2115272	Distributed training	2014-12-07 00:41:26 -08:00
Joseph Redmon	ff67f03476	Starting on server/client	2014-12-03 08:48:07 -08:00
Joseph Redmon	d407bffde9	checkpoint	2014-11-18 13:51:04 -08:00
Joseph Redmon	b13ad6d5fd	Can validate on imagenet now	2014-11-05 14:49:58 -08:00
Joseph Redmon	af4e4f92dc	getting rid of sub_arrays, nvidia driver memory leak	2014-10-27 19:45:06 -07:00
Joseph Redmon	14303717dc	Fast, needs to be faster	2014-10-25 11:57:26 -07:00
Joseph Redmon	158bb1bee9	softmax on gpu	2014-10-21 14:49:18 -07:00
Joseph Redmon	9b3c7136f3	Fixing up maxpool layer	2014-10-16 15:17:23 -07:00
Joseph Redmon	7756cccb79	Refactored connected to use blas	2014-10-13 22:31:48 -07:00
Joseph Redmon	787d534560	Convolutional working on GPU	2014-10-13 00:31:10 -07:00
Joseph Redmon	176d65b765	Nist NIN testing multi-crop	2014-08-11 12:52:07 -07:00
Joseph Redmon	d9f1b0b16e	probably how maxpool layers should be	2014-08-08 12:04:15 -07:00
Joseph Redmon	70d622ea54	Added batch to col2im, padding option	2014-07-13 22:07:51 -07:00
Joseph Redmon	cd8d53df21	So there WAS this huge bug. Gone now	2014-05-09 15:14:52 -07:00
Joseph Redmon	5ef74c2031	Slowly refactoring and pushing to GPU	2014-05-02 15:20:34 -07:00
Joseph Redmon	00d483697a	Small updates	2014-04-30 16:17:40 -07:00
Joseph Redmon	354b0cbdcb	GPU flag in Makefile	2014-04-19 13:10:59 -07:00
Joseph Redmon	ec16ee612f	Old feature extraction method	2014-04-17 15:05:41 -07:00
Joseph Redmon	738cd4c2d7	Visualizations?	2014-04-16 17:05:29 -07:00
Joseph Redmon	cc06817efa	Attempt at visualizing ImageNet Features	2014-04-11 01:00:27 -07:00
Joseph Redmon	2ea63c0e99	Better VOC handling and resizing	2014-03-12 21:57:34 -07:00
Joseph Redmon	118bdd6f62	Training on VOC	2014-02-14 10:26:31 -08:00
Joseph Redmon	f7a17f82eb	Convolutional layers working w/ matrices	2014-01-28 16:28:42 -08:00
Joseph Redmon	b2b7137b6f	About to do something stupid...	2014-01-27 23:16:56 -08:00
Joseph Redmon	796e464d43	Connected layers use matrices	2014-01-24 14:49:02 -08:00
Joseph Redmon	8c3694bc91	Ensemble	2013-12-07 09:38:50 -08:00
Joseph Redmon	4bdf96bd6a	New data format	2013-12-06 13:26:09 -08:00
Joseph Redmon	0d6bb5d44d	Working?	2013-12-02 16:41:40 -08:00
Joseph Redmon	2db9fbef2b	Parsing, image loading, lots of stuff	2013-11-13 10:50:38 -08:00
Joseph Redmon	d7286c2732	Loading may or may not work. But probably.	2013-11-06 16:09:41 -08:00
Joseph Redmon	9b1774bd39	Connected layers work forward and backward!	2013-11-06 10:37:37 -08:00
Joseph Redmon	41bcfac86f	First Commit!	2013-11-04 11:11:01 -08:00