fa2a3a5d20
Unknown people benchmarking with lfw dataset. ( #171 )
...
* Added few classifiers to demos/classifier.py; demos/classifier_test_train.py - for test train accuracy estimation; demos/classifier_webcam.py for webcam face recognition
* Two stage classifier in webcam demo
* Renamed classifier_test_train; cleaned up demos/classifier_webcam.py
* Initial commit of working unknown evaluation. Clean up pending
* Clean up lfw-classification-unknown.py and fix flake8 warnings
2016-07-28 14:38:14 -04:00
84576d252d
Remove align_v2.
...
align_v2 manually computes the same affine transformation as align_v1
2016-07-15 15:14:58 -04:00
026288afa6
Merge pull request #155 from heman4t/master
...
Updated demo/web/vendor deps
2016-06-28 12:40:12 -04:00
efa3ab8007
Updated web/vendor deps
2016-06-28 10:47:47 +05:30
3e679b9fb9
Added align dlib v2
2016-06-07 20:26:28 +00:00
3b9b99c3b2
Bump scikit-learn requirements for #137 .
2016-05-13 18:24:17 -04:00
98c42a057c
Add LDA option to the classifier.
2016-04-03 15:36:58 -04:00
2035eeb8a5
cls->clf
2016-03-18 16:19:08 -04:00
437603e45d
Classification Demo: Fix typo and formatting.
2016-03-18 16:15:58 -04:00
3a5ce4e70a
Add GMM option to the classification demo.
2016-03-18 15:26:40 -04:00
cca19b4c6a
Classification Demo: Output where classifier is saved to.
2016-03-18 14:53:33 -04:00
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
c79cc4a73e
Classification demo: Use a linear SVM with C=1 instead of grid search.
2016-02-19 14:18:02 -05:00
cfe3a83e2f
websocket server: Use store_true for --cuda.
2016-02-05 20:08:18 -05:00
19d9d8c703
Add more details to start-servers.sh
...
Thanks @justinsteele
2016-01-20 23:18:17 -05:00
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
f96b206765
Use nn4.small2.v1 by default.
2016-01-12 15:46:57 -05:00
ff06eff893
Docker: Move Python dependencies to Ubuntu package binaries.
2016-01-11 16:12:45 -05:00
1de080d65b
Web Demo: Use outer eyes and nose.
2016-01-11 10:31:38 -05:00
434dc1ca9f
Fix flake8 warnings.
2016-01-07 18:43:25 -05:00
6246fada83
Update code to nn4.v2 for #55 .
2016-01-07 18:28:11 -05:00
4357fdccae
Update websocket-server to latest API.
2015-12-31 13:02:36 -05:00
e15d11fbd7
Finish API changes and inline Python docs for #73 .
2015-12-30 13:14:30 -05:00
1f7b50efa2
Refactor Python interface.
2015-12-29 19:57:29 -05:00
dceb6a910b
flake8 improvements.
2015-12-24 11:45:00 -05:00
e1a8ccbe37
Classifier Demo: Take multiple images on input.
2015-12-24 11:06:52 -05:00
3e5be95a3c
Web demo: Assume the HTTP and WebSocket servers are the same so the web demo works in Docker without any modifications.
2015-12-23 18:42:40 -05:00
122f70ce3b
Remove unused skimage dependency.
2015-12-22 22:14:35 -05:00
fbde622805
Demos: Remove sys.path appends and unused dlib imports.
2015-12-22 21:33:27 -05:00
ec6aa45d89
System-wide install of dlib and OpenFace.
...
Resolves #11
2015-12-22 20:58:06 -05:00
027f9dcf8e
Real-Time Web Demo: Simplify server initialization.
2015-12-19 18:17:27 -05:00
7d73946836
Web demo: server.py -> websocket-server.py
2015-12-19 17:46:57 -05:00
aec7de78dc
Explictly set txaio.use_twisted.
...
https://groups.google.com/forum/#!topic/cmu-openface/zbWEuYCf7_w
2015-12-18 10:52:36 -05:00
918d3af141
Add port option to server.
2015-12-18 10:52:36 -05:00
1b9ad376ff
Add timing information to classifier.py
...
Thanks @lucafeudi
2015-12-14 11:53:15 -05:00
b9c848c8a2
Fix pep8 warning.
2015-12-11 15:59:28 -05:00
c8a4f34095
Untested improvements to create-unknown-vectors.
2015-12-11 15:56:00 -05:00
ec7650cf73
Update server for the slightly modified alignment API.
2015-12-11 10:21:01 -05:00
12a8648959
Update demos with results from the new models.
2015-12-10 21:05:55 -05:00
d6809b119e
Update align-dlib with new alignment code for #50 .
2015-12-08 17:04:57 -05:00
a1a89ea65f
Remove skimage dependency for #50 .
2015-12-08 16:41:40 -05:00
5e6977c8cd
Classifier demo: Check the mode before checking classifierModel.
...
For #65 .
2015-12-03 13:47:37 -05:00
334461d34f
solve the memory leak problem of web-demo
2015-11-28 11:13:40 +08:00
09577c5d06
Automatically switch video feeds.
2015-11-26 15:21:18 -05:00
f1f4f63598
Web Demo: Show fiducial points and use tabs instead of scolling.
2015-11-26 13:31:27 -05:00
c48255a236
Add better error handling when the Torch model is passed as the classification model.
2015-11-24 09:57:33 -05:00
513ad57244
Web Demo: Use a non-interactive backend.
2015-11-02 11:15:02 -05:00
f195085d70
Print to the browser's console on websocket error.
2015-10-31 17:12:47 -04:00
38660b5ef2
Demo: Show that the connection is local.
2015-10-17 14:24:19 -04:00
Vijayenthiran Subramaniam