|
|
ff7e03325a
|
detection exp
|
2015-05-20 10:06:42 -07:00 |
|
|
|
516f019ba6
|
route handles input images well....ish
|
2015-05-11 13:46:49 -07:00 |
|
|
|
b0106d7bde
|
probably stuff changed
|
2015-04-13 14:09:55 -07:00 |
|
|
|
4f50e29365
|
big change to images
|
2015-04-09 15:18:54 -07:00 |
|
|
|
664c5dd2f2
|
Subdivisions for batches
|
2015-03-22 09:56:40 -07:00 |
|
|
|
dcb000b553
|
refactoring and added DARK ZONE
|
2015-03-11 22:20:15 -07:00 |
|
|
|
0f645836f1
|
Detection is back, baby\!
|
2015-02-10 19:41:03 -08:00 |
|
|
|
979d02126b
|
Generalizing conv layer so deconv is easier
|
2015-02-09 13:27:58 -08:00 |
|
|
|
2f62fe33c9
|
saving weight files as binaries, hell yeah
|
2015-02-06 18:53:53 -08:00 |
|
|
|
bfffadc755
|
Stable place to commit
|
2015-02-04 12:41:20 -08:00 |
|
|
|
809f924db2
|
CUDA so fast
|
2015-01-22 16:38:24 -08:00 |
|
|
|
6e1d5b45de
|
fast sort of working
|
2015-01-19 22:06:18 -08:00 |
|
|
|
aa5996d58e
|
Faster
|
2015-01-12 17:27:08 -08:00 |
|
|
|
79fffcce3c
|
Better imagenet distributed training
|
2014-12-11 13:15:26 -08:00 |
|
|
|
cb1f33c6ae
|
Fixed race condition in server
|
2014-12-08 11:48:57 -08:00 |
|
|
|
a99050f0c8
|
Some fixes to momentum
|
2014-12-07 20:16:21 -08:00 |
|
|
|
28e2115272
|
Distributed training
|
2014-12-07 00:41:26 -08:00 |
|
|
|
1edcf73a73
|
Detection good, split up col images
|
2014-12-03 23:20:29 -08:00 |
|
|
|
ff67f03476
|
Starting on server/client
|
2014-12-03 08:48:07 -08:00 |
|
|
|
d407bffde9
|
checkpoint
|
2014-11-18 13:51:04 -08:00 |
|
|
|
b13ad6d5fd
|
Can validate on imagenet now
|
2014-11-05 14:49:58 -08:00 |
|
|
|
2b2441313b
|
col2im maybe a little faster
|
2014-10-30 11:28:37 -07:00 |
|
|
|
af4e4f92dc
|
getting rid of sub_arrays, nvidia driver memory leak
|
2014-10-27 19:45:06 -07:00 |
|
|
|
edbccdfcaf
|
Maybe something changed?
|
2014-10-25 22:04:34 -07:00 |
|
|
|
5c9a773bb6
|
Maybe some stuff changed
|
2014-10-25 17:35:25 -07:00 |
|
|
|
14303717dc
|
Fast, needs to be faster
|
2014-10-25 11:57:26 -07:00 |
|
|
|
158bb1bee9
|
softmax on gpu
|
2014-10-21 14:49:18 -07:00 |
|
|
|
787d534560
|
Convolutional working on GPU
|
2014-10-13 00:31:10 -07:00 |
|
|
|
76ee68f96d
|
Trying some stuff w/ dropout
|
2014-08-27 19:11:46 -07:00 |
|
|
|
176d65b765
|
Nist NIN testing multi-crop
|
2014-08-11 12:52:07 -07:00 |
|
|
|
7add111509
|
maxpool fixed, good on mnist
|
2014-08-09 08:16:37 -07:00 |
|
|
|
d9f1b0b16e
|
probably how maxpool layers should be
|
2014-08-08 12:04:15 -07:00 |
|
|
|
076009ebe3
|
Fixed batch stuff in conv layer
|
2014-07-17 10:14:59 -07:00 |
|
|
|
1b94df24fd
|
Midway through lots of fixes, checkpoint
|
2014-07-17 09:05:07 -07:00 |
|
|
|
70d622ea54
|
Added batch to col2im, padding option
|
2014-07-13 22:07:51 -07:00 |
|
|
|
cd8d53df21
|
So there WAS this huge bug. Gone now
|
2014-05-09 15:14:52 -07:00 |
|
|
|
5ef74c2031
|
Slowly refactoring and pushing to GPU
|
2014-05-02 15:20:34 -07:00 |
|
|
|
00d483697a
|
Small updates
|
2014-04-30 16:17:40 -07:00 |
|
|
|
738cd4c2d7
|
Visualizations?
|
2014-04-16 17:05:29 -07:00 |
|
|
|
cc06817efa
|
Attempt at visualizing ImageNet Features
|
2014-04-11 01:00:27 -07:00 |
|
|
|
2ea63c0e99
|
Better VOC handling and resizing
|
2014-03-12 21:57:34 -07:00 |
|
|
|
228d3663f8
|
Extracting features from VOC with temp filters
|
2014-02-14 16:09:07 -08:00 |
|
|
|
118bdd6f62
|
Training on VOC
|
2014-02-14 10:26:31 -08:00 |
|
|
|
f7a17f82eb
|
Convolutional layers working w/ matrices
|
2014-01-28 16:28:42 -08:00 |
|
|
|
b2b7137b6f
|
About to do something stupid...
|
2014-01-27 23:16:56 -08:00 |
|
|
|
ad9dbfe164
|
CSE546 submission
|
2013-12-10 10:30:42 -08:00 |
|
|
|
4bdf96bd6a
|
New data format
|
2013-12-06 13:26:09 -08:00 |
|
|
|
b715671988
|
Works well on MNIST
|
2013-12-05 13:17:16 -08:00 |
|
|
|
0d6bb5d44d
|
Working?
|
2013-12-02 16:41:40 -08:00 |
|
|
|
2db9fbef2b
|
Parsing, image loading, lots of stuff
|
2013-11-13 10:50:38 -08:00 |
|
