Commit Graph

6961 Commits

Author SHA1 Message Date
Davis King 4470280946 Fixed load_image_dataset()'s skip_empty_images() option. It wasn't skipping
images that only have ignore boxes when you load into mmod_rects like it should
have been.
2017-10-07 14:05:58 -04:00
Davis King c2a9dee846 merged 2017-10-04 16:22:19 -04:00
Davis King 7352ef0ed7 merged 2017-10-04 16:22:10 -04:00
Davis King 2425dcaf6d Fixed spelling error 2017-10-04 16:21:11 -04:00
Davis King 00b05ab353 Made links in the faq never contain ' 2017-10-01 09:51:32 -04:00
Davis King f66ff3b488 Added faq about common object detection problems 2017-10-01 09:51:17 -04:00
Davis King b9238fa5eb Clarified docs 2017-10-01 08:44:03 -04:00
Hung-Wei Chiu ea9aae0f5f Fix warning (#851)
* remove unused variable

* modify variable type from int to size_t

* fix previous delete, we need to call chinese_whispers here but we don't need its result now
2017-09-29 11:20:11 -04:00
Juha Reunanen fa2f35fee3 cont layer: allow to set the number of filters at runtime (#845)
* cont layer: allow to set the number of filters at runtime
(implementation essentially copied from con layer)

* Document the new constructor cont_(num_con_outputs o), and the function set_num_filters
2017-09-28 05:48:17 -04:00
Davis King 6283a4b51c merged 2017-09-27 06:48:04 -04:00
Davis King 178f4205e2 Made cmake error messages a little clearer 2017-09-26 11:49:29 -04:00
Davis King 9987c0eac9 Merge branch 'visionworkz-master' 2017-09-22 21:52:42 -04:00
Davis King 67e6957b1e Clarified comment and updated requirements.txt 2017-09-22 21:52:15 -04:00
Davis King 76333612bb Merge branch 'master' of git://github.com/visionworkz/dlib into visionworkz-master 2017-09-22 21:46:22 -04:00
Davis King 64942d92c4 Fixed a bug in how the mmod_options automatically determines detection window
sizes.  It would pick a bad size in some cases.
2017-09-20 21:10:59 -04:00
Varun Chatterji 7e94daad4d Cleaned up example file. 2017-09-19 23:08:54 +08:00
Davis King 3d4bd975e6 Made unit test more robust 2017-09-19 06:29:49 -04:00
Varun Chatterji 5f26972551 Added code to get face_chip images.. 2017-09-19 13:08:51 +08:00
Davis King bd6f918318 merged 2017-09-18 13:07:17 -04:00
Varun Chatterji 9fe352d696 Added size and padding as optional parameters 2017-09-18 19:54:26 +08:00
Davis King cabad6d5fb Fixed a bug in the random_cropper where it might crash due to division by 0
if small images are given as input.
2017-09-17 15:16:41 -04:00
Davis King da968fa52c Record last changeset and set PATCH version to 99 2017-09-17 08:28:45 -04:00
Davis King 3e192c03d4 Added tag v19.7 for changeset fb51c77524ff 2017-09-17 08:28:29 -04:00
Davis King ba9c71d66a Created release v19.7 2017-09-17 08:28:29 -04:00
Davis King cf3f157ef7 updated docs 2017-09-17 08:24:27 -04:00
Davis King 02248a2f56 updated docs 2017-09-17 07:10:37 -04:00
Davis King 836b2e0322 updated docs 2017-09-17 06:57:01 -04:00
Davis King fd396afe3d updated docs 2017-09-16 16:28:21 -04:00
Davis King c24b67d5e6 updated docs 2017-09-16 16:15:22 -04:00
Davis King b7786a285b updated docs 2017-09-16 16:13:32 -04:00
Davis King d39b843de0 Added another car finding example 2017-09-16 15:35:58 -04:00
Davis King 4737009c11 Clarified comments 2017-09-16 15:35:37 -04:00
Davis King 8bfd227930 Changed to slightly better default recommendations for parameters. 2017-09-16 15:14:13 -04:00
Davis King de32c75c15 Merge branch 'visionworkz-master' 2017-09-16 14:54:56 -04:00
Davis King 532552627a Cleaned up code and comments.
In particular, these new functions don't need to be inside the face
recognition class.  So I moved them out.  I also fixed many incorrect
copy/pasted comments and clarified parts of the example code.
2017-09-16 14:53:11 -04:00
Davis King 5cf80dda6a Merge branch 'master' of git://github.com/visionworkz/dlib into visionworkz-master 2017-09-16 14:18:44 -04:00
Davis King b4bd6f8dee More cleanup 2017-09-16 14:10:09 -04:00
Davis King ffe1167952 Made deserialize print more informative error messages. 2017-09-16 14:08:41 -04:00
Davis King 57b6cd1b80 clarified error message 2017-09-16 14:01:34 -04:00
Davis King 37e0b9ea68 Updated comments. 2017-09-15 22:16:00 -04:00
Davis King 68d39c708f Changed TIME_THIS() to use std::chrono::high_resolution_clock 2017-09-15 21:58:03 -04:00
Davis E. King 0f8b227e47 Fixed typo in comment 2017-09-15 21:02:39 -04:00
Davis King fb5cae063b Added this program for historical reference. 2017-09-15 20:20:08 -04:00
Davis King 41c2f217c6 Changed code to recommend users use the new 5 point face landmarking model. 2017-09-15 19:58:27 -04:00
Davis King f56ba6b04f Changed code to recommend users to use the new 5 point face landmarking model. 2017-09-15 19:57:54 -04:00
Davis King 80222b5987 Fixed grammar 2017-09-15 19:57:33 -04:00
Davis King 4fcc5faa39 Fixed grammar 2017-09-15 19:57:16 -04:00
Davis King f84194f643 Upgraded face recognition input validation checks to allow use of 5 point face
landmarking models.
2017-09-15 19:56:38 -04:00
Davis King 1c7bbbd4b6 Upgraded render_face_detections() and get_face_chip_details() to support 5
point face landmark models.
2017-09-15 19:55:47 -04:00
Davis King 3fff7f8414 Added more options to control how the feature pool region is defined. 2017-09-15 19:54:22 -04:00