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 |
|
Brandon Amos
|
bead828442
|
Add torch-TripletEmbedding submodule.
|
2015-09-18 16:57:25 -04:00 |