Brandon Amos
|
49d195355b
|
Training: Remove test code from data loader.
|
2016-02-28 13:48:22 -05:00 |
|
Brandon Amos
|
e987b15b22
|
Move old test code to attic for #99.
|
2016-02-27 17:50:11 -05:00 |
|
Brandon Amos
|
9b04bca65d
|
train.lua: Pass on comments.
|
2016-01-16 23:50:54 -05:00 |
|
Brandon Amos
|
51b01c200c
|
Train: Fix model saving logic for out-of-memory errors.
Thanks @kleinsound
|
2016-01-16 16:37:35 -05:00 |
|
Brandon Amos
|
9d1bd99579
|
Update copyright notices.
sed -i "/[Cc]opyright.*2015.*Carnegie Mellon University/s/2015/2015-2016/;" $(git grep '[Cc]opyright.*Carnegie Mellon University' | sed 's/:.*//' | uniq)
|
2016-01-13 14:52:52 -05:00 |
|
Brandon Amos
|
8bbfd4da05
|
Training: Skip battch if nTripsFound == 0.
|
2016-01-13 14:32:43 -05:00 |
|
Brandon Amos
|
d9c602c449
|
Add cuda conditionals to test.lua.
|
2016-01-12 17:43:50 -05:00 |
|
Brandon Amos
|
e5277e916c
|
sanitize: Remove unused imports.
|
2016-01-12 17:40:01 -05:00 |
|
Brandon Amos
|
dd5d0d11bd
|
Training: Remove unused 'fbnn' import.
|
2016-01-12 17:30:06 -05:00 |
|
Brandon Amos
|
6409661f5f
|
Remove unused fbnn dependency.
|
2016-01-12 14:32:54 -05:00 |
|
Brandon Amos
|
0479d0e345
|
Finish tensor size checks for #36.
|
2016-01-11 16:44:50 -05:00 |
|
Brandon Amos
|
d0b40686a2
|
Training: OpenFaceOptim: Correct Tensor type.
|
2016-01-11 16:44:32 -05:00 |
|
Brandon Amos
|
5f78673b7d
|
Move imgDim to models.
|
2016-01-11 16:38:24 -05:00 |
|
Brandon Amos
|
c5b0accd4d
|
Training: Add conditionals for cuda portions.
|
2016-01-11 16:17:36 -05:00 |
|
Brandon Amos
|
15cc5fef00
|
Training: Add CPU execution for tests.
|
2016-01-11 16:17:36 -05:00 |
|
Brandon Amos
|
ff06eff893
|
Docker: Move Python dependencies to Ubuntu package binaries.
|
2016-01-11 16:12:45 -05:00 |
|
Brandon Amos
|
6a5d95d451
|
Fix luacheck warning in sanitize.
|
2016-01-11 07:48:01 -05:00 |
|
Brandon Amos
|
8155840989
|
Training: Use e-lab's torch-toolbox sanitize.
|
2016-01-09 17:17:30 -05:00 |
|
Brandon Amos
|
697fac07c1
|
Training: Output the number of model parameters.
|
2016-01-08 11:18:44 -05:00 |
|
Brandon Amos
|
22cf225923
|
Training: By default use an epoch size of 500.
|
2016-01-08 11:00:17 -05:00 |
|
Brandon Amos
|
6246fada83
|
Update code to nn4.v2 for #55.
|
2016-01-07 18:28:11 -05:00 |
|
Brandon Amos
|
4821cb6ee2
|
Fix flake8 warnings.
|
2016-01-06 17:19:37 -05:00 |
|
Brandon Amos
|
2b8f03c908
|
Update lfw-latest.sh.
|
2016-01-06 17:02:30 -05:00 |
|
Brandon Amos
|
2769411d56
|
Add @melgor's training improvements for #55
|
2016-01-06 17:02:30 -05:00 |
|
Brandon Amos
|
4098a586ae
|
Training: Add script to run lfw evaluation on the latest model.
|
2015-12-28 16:54:35 -05:00 |
|
Brandon Amos
|
ff51b2cbde
|
Fix luacheck warnings.
|
2015-12-27 09:09:14 -05:00 |
|
Brandon Amos
|
57118ac28f
|
Fix luacheck warnings.
|
2015-12-27 08:41:49 -05:00 |
|
Brandon Amos
|
81a62c6e13
|
Fix broken links.
|
2015-12-26 17:11:44 -05:00 |
|
Brandon Amos
|
dceb6a910b
|
flake8 improvements.
|
2015-12-24 11:45:00 -05:00 |
|
Brandon Amos
|
e90694fcba
|
nn4: Add LRN and remove 5x5 convolutions for #55.
Reduces the number of parameters from 7472144 to 6959088.
|
2015-12-20 22:29:55 -05:00 |
|
Brandon Amos
|
eea992b458
|
Mention Python dependencies for training.
|
2015-12-17 11:43:00 -05:00 |
|
Brandon Amos
|
bf38abe8f9
|
Remove unused cudnn dependency.
|
2015-12-17 09:04:46 -05:00 |
|
Brandon Amos
|
df89d749d1
|
Clarify training procedure.
Summary of content from @Strateus and @melgor at
https://groups.google.com/forum/#!topic/cmu-openface/XgxfN8Xy9nA
|
2015-11-23 16:12:59 -05:00 |
|
Brandon Amos
|
0a0cae4889
|
Add non-default test code using hard negatives.
|
2015-11-20 14:10:31 -05:00 |
|
Brandon Amos
|
2e8466afb1
|
Make suggestion 1 the default option. #48.
|
2015-11-09 15:58:05 -05:00 |
|
Brandon Amos
|
aed184d860
|
Training: Suggestion 2 from @melgor in #48.
|
2015-11-08 17:08:06 -05:00 |
|
Brandon Amos
|
30f754176c
|
Training: Handle peoplePerBatch > nClasses edge case when nDonkey != -1.
|
2015-11-07 14:35:49 -05:00 |
|
Brandon Amos
|
ae348c22f9
|
Training: Fix error with tensors being unexpectedly doubles.
|
2015-11-06 17:09:47 -05:00 |
|
Brandon Amos
|
9bef1e8a60
|
Train: Detect and correct edge case when peoplePerBatch > number of classes.
Thanks @venturamartin90
|
2015-11-06 12:10:25 -05:00 |
|
Brandon Amos
|
1fb67767b7
|
Correct calls to image.load
|
2015-10-31 17:12:47 -04:00 |
|
Brandon Amos
|
948bc2d3e9
|
Training: Update for_each call to apply.
|
2015-10-26 17:41:46 -04:00 |
|
Brandon Amos
|
59002cdfe5
|
Training: Remove fbnn's Optim dependency.
|
2015-10-26 17:41:46 -04:00 |
|
Brandon Amos
|
10b5d020aa
|
Correct nn1 to nn2.
|
2015-10-15 11:13:46 -04:00 |
|
Brandon Amos
|
5ca23547fc
|
Fix some pep8 warnings.
|
2015-10-12 11:30:29 -04:00 |
|
Brandon Amos
|
69586648e6
|
Refactor: facenet->openface.
|
2015-10-10 21:28:41 -04:00 |
|
Brandon Amos
|
245a833113
|
Training: plot-loss: Show last few values.
|
2015-10-10 21:28:41 -04:00 |
|
Brandon Amos
|
f51d02fb51
|
Training: Plot: Set alpha on the test loss since it overlaps the train loss.
|
2015-10-03 22:47:27 -04:00 |
|
Brandon Amos
|
aa6ee28120
|
Training: Loss: log-scale y axis.
|
2015-10-03 17:24:17 -04:00 |
|
Brandon Amos
|
f0196220ff
|
Initial commit of loss plotting code from development repo.
|
2015-09-23 19:51:47 -04:00 |
|
Brandon Amos
|
d8790408d1
|
Initial commit of training code from development repo.
|
2015-09-23 19:49:45 -04:00 |