Tadas Baltrusaitis
6c979c0bd3
Optimize NU-RLMS
2017-09-14 12:07:48 +01:00
Tadas Baltrusaitis
f5b364c54b
- Choosing better CE-CLM models for C++ (more general and work well in a broader setting)
...
- Reducing the memory load of the model in C++ by half
2017-09-13 19:39:11 +01:00
Tadas Baltrusaitis
7e3a8570ca
Copy constructor fix for face detection validator.
2017-09-03 08:47:56 +01:00
Tadas Baltrusaitis
c96aa6391b
Dealing with unusual image formats (16 bit and 4 channel).
2017-09-02 09:01:24 +01:00
Tadas Baltrusaitis
f8e51bca28
Simplification and speedup of landmark validation.
2017-09-01 14:58:17 +01:00
Tadas Baltrusaitis
e0b8e775e7
Face detection speedup through faster convolution.
2017-09-01 11:19:45 +01:00
Tadas Baltrusaitis
65172b8305
Some more speedup.
2017-08-30 20:01:25 +01:00
Tadas Baltrusaitis
b71b2f1cfc
Another performance improvement by rearranging GEMM order.
2017-08-30 15:20:56 +01:00
Tadas Baltrusaitis
e1bf2c5a39
Another slight performance increase.
2017-08-29 21:43:27 +01:00
Tadas Baltrusaitis
f62516789c
Simplifying conversion to grayscale
2017-08-26 17:01:54 +01:00
Tadas Baltrusaitis
e8e93c3f96
Incorporating MTCNN face detection with CE-CLM.
...
Merge remote-tracking branch 'origin/feature/mtcnn_face_det' into feature/CE-CLM
# Conflicts:
# exe/FaceLandmarkImg/FaceLandmarkImg.cpp
# exe/FaceLandmarkVid/FaceLandmarkVid.cpp
# exe/FaceLandmarkVidMulti/FaceLandmarkVidMulti.cpp
# exe/FeatureExtraction/FeatureExtraction.cpp
# lib/local/LandmarkDetector/LandmarkDetector.vcxproj
# lib/local/LandmarkDetector/LandmarkDetector.vcxproj.filters
# lib/local/LandmarkDetector/src/LandmarkDetectorFunc.cpp
# lib/local/LandmarkDetector/src/LandmarkDetectorParameters.cpp
# lib/local/LandmarkDetector/src/LandmarkDetectorUtils.cpp
2017-08-26 13:23:16 +01:00
Tadas Baltrusaitis
452d1b8008
Integrating MTCNN in all of the demos.
2017-08-18 20:57:19 +01:00
Tadas Baltrusaitis
a251415fea
Starting to incorporate MTCNN
2017-08-18 10:03:01 +01:00
Tadas Baltrusaitis
441777c9ed
Code cleanup and rearrangement.
2017-08-17 12:35:11 +01:00
Tadas Baltrusaitis
8d01ea5911
Different implementation of convolution, through matrix multiplication which is quite a bit faster.
2017-08-17 11:40:57 +01:00
Tadas Baltrusaitis
2bd085cb47
Exploring CNN optimization
2017-08-16 17:14:00 +01:00
Tadas Baltrusaitis
d062ab690d
Final bit of simplification and fixing an issue with RNet and ONet.
2017-08-15 21:53:25 +01:00
Tadas Baltrusaitis
abcc91364e
Towards MTCNN, implementing PNet
2017-08-10 15:30:35 -04:00
Tadas Baltrusaitis
13e42a70cf
Some more work on MTCNN.
2017-08-09 16:16:31 -04:00
Tadas Baltrusaitis
7fe7bb4904
Towards MTCNN c++ implementation.
2017-08-09 15:04:14 -04:00
Tadas Baltrusaitis
8dea625717
Adding more preparation for MTCNN in C++
2017-08-09 12:01:53 -04:00
Tadas Baltrusaitis
8b5f8b9a36
Starting to work on MTCNN C++ implementation.
2017-08-09 11:00:38 -04:00
Tadas Baltrusaitis
f19fab7ff7
Bringing CE-CLM up to speed with master.
2017-08-03 11:14:49 -04:00
Tadas Baltrusaitis
5959176921
Some big changes:
...
- face validator is a retrained CNN now
- starting retiring CLM-Z from OpenFace
2017-08-01 17:11:02 -04:00
Tadas Baltrusaitis
8eb086545c
Simplified validator model.
2017-07-31 15:55:29 -04:00
Tadas Baltrusaitis
7513cf7964
Speeding up fancy face validation.
2017-07-29 21:11:16 -04:00
Tadas Baltrusaitis
8cc98be724
First try at a new landmark validator.
2017-07-29 18:19:41 -04:00
Tadas Baltrusaitis
af77a045d9
Playing around with a new landmark detection validation method.
2017-07-28 15:06:04 -04:00
Tadas Baltrusaitis
283bf810db
Sparse models in C++, gain in speed
2017-07-20 12:12:13 -04:00
Tadas Baltrusaitis
165a708796
Decoupling C++ code so that AU detection works properly with a new PDM.
2017-06-20 14:55:59 -04:00
Tadas Baltrusaitis
596593cca3
Moving towards an optimized C++ version of CEN.
2017-06-19 16:35:11 -04:00
Tadas Baltrusaitis
ead2347581
Renaming everything to CEN in c++
2017-06-12 20:11:42 -04:00
Tadas Baltrusaitis
305af01326
Auto stash before merge of "develop" and "origin/develop"
...
- Adding new license files
- Replacing images with more suitable CC ones
2017-05-08 21:36:23 -04:00
TadasBaltrusaitis
58daee692e
Merge branch 'master' into feature/DCCNF
...
# Conflicts:
# .gitignore
# exe/FaceLandmarkImg/FaceLandmarkImg.cpp
# exe/FeatureExtraction/FeatureExtraction.cpp
# matlab_runners/Feature Point Experiments/results/in-the-wild-res-no-outline.pdf
# matlab_runners/Feature Point Experiments/results/landmark_detections.mat
# matlab_runners/Feature Point Experiments/run_OpenFace_feature_point_tests_300W.m
# matlab_runners/Gaze Experiments/mpii_1500_errs.mat
2017-04-10 11:04:30 -04:00
somacoder
86341fae30
Update LandmarkDetectorModel.h
...
Moving default boolean eye model assignment of false to cpp.
2017-02-23 13:45:09 -05:00
Tadas Baltrusaitis
dbdf008f90
First C++ version of DCLM
2016-12-13 14:25:04 -05:00
Guillaume Chanel
358cd6f9e2
Added the possibility to change the output videos codec by specifying the -oc option
...
A warning is now issued in the case the VideoWriter could not be instantiated, advising to change the codec
This change applies to FaceLandmarkVid* and FeatureExtraction executables
The option is used as "-oc CODEC_FOURCC" and defaults to DIVX. If the user inputs a FOURCC with a size different than 4, than the default codec is used
The option is handled by the function get_video_input_output_params in the LandMarkDetector namespace
2016-09-14 09:00:57 +02:00
Tadas Baltrusaitis
c1ff40399e
Bug fixes
2016-09-06 12:32:33 -04:00
Tadas Baltrusaitis
c1431fe815
Fixes with drawing antialiased lines and landmarks using sub-pixel precision.
2016-09-06 10:20:31 -04:00
Tadas Baltrusaitis
51ae195124
A number of small fixes, renamings and corrections.
2016-07-31 16:31:17 -04:00
unknown
57e58a6949
Master commit of OpenFace.
2016-04-28 15:40:36 -04:00
