OpenFace

mirror of https://gitcode.com/gh_mirrors/ope/OpenFace.git synced 2026-04-28 07:00:21 +00:00

Files

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

face_detections

Cleaning up JANUS predictions using CEN

2017-05-03 15:46:45 -04:00

results

Sparse response map computation speedup for CEN.

2017-08-09 12:11:02 -04:00

cen_general_mapping.mat

Sparse response map computation speedup for CEN.

2017-08-09 12:11:02 -04:00

cen_menpo_mapping.mat

Sparse response map computation speedup for CEN.

2017-08-09 12:11:02 -04:00

Collect_menpo_train_imgs.m

Cleaning up JANUS predictions using CEN

2017-05-03 15:46:45 -04:00

compute_error_menpo_1.m

Cleaning up JANUS predictions using CEN

2017-05-03 15:46:45 -04:00

early_term_cen_of.txt

- Choosing better CE-CLM models for C++ (more general and work well in a broader setting)

2017-09-13 19:39:11 +01:00

early_term_cen.txt

Sparse response map computation speedup for CEN.

2017-08-09 12:11:02 -04:00

iterate_piece_wise.m

Cleaning up JANUS predictions using CEN

2017-05-03 15:46:45 -04:00

learn_error_pred_general.m

Fixing paths in error mapping.

2017-06-14 15:44:04 -04:00

learn_error_pred_menpo.m

Fixing paths in error mapping.

2017-06-14 15:44:04 -04:00

output_corrections.m

Moving towards an optimized C++ version of CEN.

2017-06-19 16:35:11 -04:00

ranking_score_grad.m

Cleaning up JANUS predictions using CEN

2017-05-03 15:46:45 -04:00

ranking_score.m

Cleaning up JANUS predictions using CEN

2017-05-03 15:46:45 -04:00

readme.txt

- Choosing better CE-CLM models for C++ (more general and work well in a broader setting)

2017-09-13 19:39:11 +01:00

Script_CECLM_general_cross_data_multi_hyp.m

Fix with learning error mapping.

2017-06-14 09:58:42 -04:00

Script_CECLM_menpo_multi_hyp.m

Fix with learning error mapping.

2017-06-14 09:58:42 -04:00

readme.txt

This function allows to learn a better relationship between landmark 
detection likelihoods and the resulting landmark error.

First run:
Script_CECLM_general_cross_data_multi_hyp.m
Script_CECLM_menpo_multi_hyp.m

Then:
learn_error_pred_general.m
learn_error_pred_menpo.m

To use in C++ also generate the early_term_cen_of.txt file using output_corrections.m, this is already generated so no need to re-run it.