bba911c802
Replace satitize by clearState()
2016-03-16 18:20:11 +01:00
e7c574829d
Merge pull request #108 from melgor/cudnn_convert
...
Replace nn_to_cudnn by cudnn.convert #106
2016-03-16 11:54:20 -04:00
cada02629c
TSNE: Update colorscheme.
2016-03-16 11:42:52 -04:00
8830e48b57
batch-represent: Handle edge case when a batch contains 1 image.
2016-03-16 11:17:15 -04:00
7d21caf004
Merge branch 'cudnn_convert' of https://github.com/melgor/openface into cudnn_convert
...
Conflicts:
training/model.lua
training/train.lua
2016-03-16 16:15:05 +01:00
f63acb637e
Replace nn_to_cudnn by cudnn.convert #106
2016-03-16 15:38:06 +01:00
6fd4ac8604
Training: Sample from all of a person's images.
...
This fixes a bug in the training code that caused
only the first (same) `nSamplesPerClass` images in each
class to be sampled every time rather than sampling
from all of the person's images.
2016-03-15 16:27:09 -04:00
2c3164c50d
openface_server error message: Add bash login shell note for #105 .
2016-03-12 15:12:09 -05:00
811fce8613
lfw-classification: Fix typo.
2016-03-11 18:32:22 -05:00
e455a1c82e
Update classification results with OpenBLAS.
2016-03-11 18:32:22 -05:00
71885041e7
Python library: Import everything in the root openface module.
2016-03-11 16:58:28 -05:00
d6b9d16156
Docs: Reference prune-dataset after align-dlib.
2016-03-11 16:50:35 -05:00
6ab7a6bb4e
lfw-classification: Update LFW path.
2016-03-11 15:33:35 -05:00
e2d7513ff5
Replace nn_to_cudnn by cudnn.convert #106
2016-03-11 11:09:23 +01:00
b8de89375a
Dockerfile: Update default CMD to use a Bash login shell.
2016-03-10 18:52:31 -05:00
6001f91a15
Docs: Improve web demo Docker command.
2016-03-10 18:21:30 -05:00
338516a153
docs: Add OpenBLAS execution times.
2016-03-10 14:13:10 -05:00
3a66bc2345
Docs: Add GenBeta link.
2016-03-09 23:48:41 -05:00
d4ee384d5e
demos/vis-outputs: Add aligned example images, fix image.load usage, and output where the images are being saved to
...
Thanks @pppoe! https://github.com/cmusatyalab/openface/pull/107
2016-03-09 22:26:12 -05:00
18575f7199
Web demo: bower: Update metadata.
2016-03-09 18:56:56 -05:00
8fb4a9d528
Update badges in README.
2016-03-08 20:55:39 -05:00
71b6bbf765
Fix flake warning.
2016-03-08 20:39:03 -05:00
665cb4c9d7
Training plot-loss.py: Improve triplet loss plot bounds.
2016-03-08 18:36:58 -05:00
04d23481fb
Fix typo.
2016-03-06 21:15:10 -05:00
4616f61ff8
DNN Training: Halve default epochSize.
2016-03-06 20:03:54 -05:00
f17a36c2fd
plot-loss: Import sys.
2016-03-06 19:56:12 -05:00
dd82f1825d
Update docs on training a DNN.
2016-03-06 19:54:40 -05:00
f112398178
DNN Training: Plot LFW accuracies for #100 .
2016-03-06 19:46:33 -05:00
bbff0a01dd
Fix tests for training the DNN.
2016-03-06 19:45:37 -05:00
1786f20fb2
Update description of pyannote-video
...
\cc @hbredin
2016-03-06 19:01:40 -05:00
f5766412d2
NN Training: Add LFW validation for #100 .
2016-03-04 18:30:39 -05:00
e4c4aef3e4
Training: Zero pad experiment work directory numbers.
2016-03-04 18:09:55 -05:00
8db6a8ad05
Docs: Remove broken link.
2016-03-03 09:05:41 -05:00
1b4057da55
VGG Download: Use all images, timeout URL requests.
2016-03-02 10:40:43 -05:00
f9b8a28f8c
VGG Dataset Script: Fix formatting.
2016-03-01 12:25:36 -05:00
958a49b4a6
VGG Dataset Script: Fix flake formatting warnings.
2016-02-29 08:44:59 -05:00
74d0850b63
VGG Dataset Script: Remove unused import.
2016-02-29 08:41:11 -05:00
e6c73b18aa
Add git exception for download-lfw-subset.
2016-02-29 08:39:04 -05:00
6fc8e9d8e5
VGG Dataset Script: Add header and except to gitignore.
2016-02-29 08:37:42 -05:00
99d9955bda
Add VGG dataset download and align script.
2016-02-29 08:34:01 -05:00
0b20785778
align-dlib: Remove outdated argument.
2016-02-29 08:29:35 -05:00
540b7d03c6
Fix luacheck warning.
2016-02-28 15:08:50 -05:00
49d195355b
Training: Remove test code from data loader.
2016-02-28 13:48:22 -05:00
ccaf423904
Remove -testEpochSize from the training unit test.
2016-02-27 18:00:20 -05:00
e987b15b22
Move old test code to attic for #99 .
2016-02-27 17:50:11 -05:00
b2054fed5e
detect-outliers: Add --delete option.
2016-02-27 16:41:04 -05:00
d845e6cd16
align-dlib: Add verbose option.
2016-02-27 15:11:05 -05:00
1bb08b2e83
Website: Link to related projects and articles.
...
Let me know if you all want to tweak these.
+ @mkiser's algorithmia post
+ @richards-tech's NiFi integrations
+ @aybassiouny's C++ version
+ @hbredin's pyannote-video (want a one-sentence description or link somewhere else?)
2016-02-26 18:00:01 -05:00
69837ba70b
Bump version to 0.2.1
2016-02-25 12:41:24 -05:00
aeb14897c5
Update acknowledgements.
2016-02-24 23:59:29 -05:00
melgor