mirror of
https://gitcode.com/gh_mirrors/ope/OpenFace.git
synced 2026-05-20 14:17:58 +00:00
23 lines
1.1 KiB
Plaintext
23 lines
1.1 KiB
Plaintext
Scripts for evaluating CE-CLM, and CLNF methods on the IJB-FL dataset - http://www.bmva.org/bmvc/2016/papers/paper095/paper095.pdf
|
|
|
|
To run the models on the data using models trained on 300W:
|
|
- Script_CLNF_wild.m
|
|
|
|
To run the models on the data using models trained on 300W + MultiPIE:
|
|
- Script_CECLM_general.m
|
|
- Script_CLNF_general.m
|
|
|
|
To run CE-CLM model trained on 300W + MultiPIE + Menpo:
|
|
- Script CECLM_menpo.m
|
|
|
|
To visualize the results of the models against baselines (using inner face markup - 49, and full face markup - 68):
|
|
Display_ceclm_results_49.m
|
|
Display_ceclm_results_68.m
|
|
|
|
To construct the error table:
|
|
Construct_error_table.m
|
|
|
|
The 300W trained CLNF model performs best so it is used in comparisons, for CE-CLM 300W + MultiPIE works better so it is used. We do not use Menpo trained CE-CLM model for comparison as other models have not been trained on the more extensive Menpo data, but it is the best performing model.
|
|
|
|
For a fair comparison all the models and baselines are initialized using the bounding boxes generated by adding noise to ground truth bounding boxes.
|