github/deepface
1
1
Fork 0
mirror of https://github.com/serengil/deepface.git synced 2025-06-06 19:45:21 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,595 Commits 1 Branch 14 Tags 57 MiB
Commit Graph

552 Commits

Author SHA1 Message Date
Sefik Ilkin Serengil
19f057a712 new structure for vgg-face model 2024-01-08 16:57:07 +00:00
Sefik Ilkin Serengil
f23ab85fd1 using type hinting for backend functions 2023-12-24 14:38:14 +00:00
Sefik Ilkin Serengil
27f0619e9d load img from url was loading rgb instead of bgr 2023-12-24 13:12:35 +00:00
Sefik Ilkin Serengil
308ab61b41 modular tests 2023-12-24 13:06:07 +00:00
Sefik Ilkin Serengil
bd6393daa0
Merge pull request #863 from bhky/master 
Simplify face alignment procedure
 2023-12-21 09:52:37 +00:00
Sefik Ilkin Serengil
0c0dfb8090
Update DeepFace.py 
model type check
 2023-12-18 12:06:49 +00:00
Sefik Ilkin Serengil
19f7cf620d
Update DeepFace.py 
build_model return type
 2023-12-18 11:56:56 +00:00
Sefik Ilkin Serengil
e91e48bd6c
Update DeepFace.py 2023-12-18 09:35:37 +00:00
Sefik Ilkin Serengil
e4a43fd86b
Update DeepFace.py 
functional may come from keras or tf.keras. hard to manage in typing. used any for build_model.
 2023-12-18 09:31:54 +00:00
Sefik Ilkin Serengil
8a5f2875fc
Merge pull request #922 from RazaProdigy/typehints 
Adding Type Hints for Enhanced Code Clarity and Maintenance
 2023-12-18 09:30:32 +00:00
RazaProdigy
aa96a76cb2 Removed typo from code 2023-12-18 13:25:36 +04:00
RazaProdigy
90a0282ed9 Refine type hints as per PR review 2023-12-18 13:18:57 +04:00
RazaProdigy
cfff58792a Added type hints 2023-12-17 13:59:32 +04:00
Sefik Ilkin Serengil
bd0a3ec17e yunet alignment issue sorted 2023-12-16 20:11:23 +00:00
xuwei
7b1451ac50 fix(represent): change somthing according to comments and adapt pylint 2023-12-14 12:29:35 +00:00
xuwei
8c6dad0147 fix(represent): 1. support represent user given image 2. img_path support pathlib.Path 2023-12-14 06:57:49 +00:00
Sefik Ilkin Serengil
2cc5f39853 some improvements 
- loading image from url was loading as rgb instead of bar
- we are returning image name in load image function to throw
meaningful message for no face found case
- we started to use imread again, and throw exception if file
name contains non English character
- get rid of the duplicate if statement in extract faces
 2023-12-08 22:18:52 +00:00
Sefik Ilkin Serengil
76a6bce824 some improvements 
- pickle file is out dated, then user informed with meaningful message.
- response df of find, we were just showing source image's region,
we just added the target image's region
 2023-12-08 22:15:34 +00:00
Sefik Ilkin Serengil
adfb29dfc7 raise legible error message for optional import 2023-12-08 22:13:20 +00:00
Sefik Ilkin Serengil
fceeccb14b timestamp added for log messages 2023-12-08 22:12:52 +00:00
Sefik Ilkin Serengil
fff6481431 raising legible error message 
some libraries are optional. if an user tries to import these
before installation, then not legible message was gotten.
now, we will throw legible message.
 2023-12-08 22:12:25 +00:00
Sefik Ilkin Serengil
63b397aa8e review comments resolved 2023-12-06 21:07:31 +00:00
Sefik Ilkin Serengil
125895398e modules added into logger 2023-12-06 20:55:00 +00:00
Sefik Ilkin Serengil
5464ac511c logger instead of print 2023-12-06 19:32:38 +00:00
Sefik Ilkin Serengil
bb2b28e1d9
Update DeepFace.py 2023-11-22 12:02:21 +00:00
Sefik Ilkin Serengil
37c94467f3
Update DeepFace.py 2023-11-22 11:57:55 +00:00
Sefik Ilkin Serengil
f2068df6a8
Update DeepFace.py 2023-11-22 11:49:55 +00:00
Nicolò Di Domenico
c268e396a8
fix missing normalization when skipping face detection 2023-11-15 10:47:24 +01:00
Sefik Ilkin Serengil
8eb8d96a54 old version of model.predict stored 2023-10-22 19:46:02 +01:00
Sefik Ilkin Serengil
68eaafc614
Merge pull request #857 from Villyli/master 
change model.predict() to model(), notably improve memory leak (issue #697)
 2023-10-22 19:41:11 +01:00
haddyadnan
1bcc065a11 refactor try block 2023-10-19 12:55:58 -07:00
haddyadnan
cca3422b54 Add error msg for failed import 2023-10-19 12:40:36 -07:00
haddyadnan
c53366b75a order result in descending order of probability 2023-10-19 12:09:41 -07:00
haddyadnan
d037d2a2d7 Merge branch 'master' into facenet_pytorch 
merge master
 2023-10-19 11:32:54 -07:00
haddyadnan
f07be2226f include faster mtcnn implementation 2023-10-19 11:32:39 -07:00
adnanHaddy
0a389deaf1 Include detected face confidence 2023-10-18 12:27:54 -07:00
Bosco Yung
dc75d76813 Simply face alignment procedure 2023-10-18 17:17:34 +09:00
lilw5
1d57b2f7f3 change model.predict() to model(), improve mem leak notably 2023-10-10 11:16:44 +08:00
maxpopovych
50105b21e6 opencvzoo branch changed from master to main, fix applied to sface remote repo 2023-09-08 08:57:12 +02:00
Awshr
1cec1d8f4a find method documentation modified 2023-07-27 09:21:02 +03:00
Anthr@X
9bf9542273 fix linter errors 2023-07-24 15:57:48 +10:00
Anthr@X
fc09756cfc
Merge branch 'master' into fixyunet 2023-07-14 17:16:38 +10:00
Anthr@X
3e7f6dfb58 fix comment length 2023-07-14 14:57:20 +10:00
Anthr@X
a456b43d57 fix line too long 2023-07-14 14:34:05 +10:00
Anthr@X
b97f74e186 fix linting and add comments 2023-07-13 22:13:32 +10:00
Anthr@X
498658d084 Fix yunet return negative coordinates 2023-07-13 11:30:00 +10:00
Sefik Ilkin Serengil
8bb52c0317 some linting comments after yunet implementation 2023-07-09 12:41:31 +01:00
Anthr@X
b52d1e8015 restore original size and move coordinates accordingly 2023-07-09 01:05:17 +10:00
Anthr@X
34d1f1250a return empty list if detected no face. 2023-07-09 00:23:31 +10:00
Anthr@X
a90bf8e1c0 Fix hard coded file name in message 2023-07-08 23:29:28 +10:00
Anthr@X
5e55fafdb5 Add Yunet detector 2023-07-08 23:17:50 +10:00
Vincent STRAGIER
80d4dbb64e Use original utralytics module for YOLO. 2023-06-28 19:53:51 +02:00
Vincent STRAGIER
64f93d1fcc Change yolov8n to yolov8. 2023-06-24 00:05:48 +02:00
Vincent STRAGIER
9792af410d Fix linting error. 2023-06-23 23:46:22 +02:00
Vincent STRAGIER
dcf94150f2 Refactoring and requirements. 2023-06-23 23:31:50 +02:00
Vincent STRAGIER
776bd11707 Remove broken models. 2023-06-23 20:49:05 +02:00
Vincent STRAGIER
0510613004 Comment out broken models. 2023-06-23 20:45:58 +02:00
Vincent STRAGIER
205eb0e23d Revert OpenCvWrapper.py 2023-06-23 20:41:29 +02:00
Vincent STRAGIER
0c50eb7178 Remove unwanted line return. 2023-06-23 20:34:51 +02:00
Vincent STRAGIER
16d37711d5 Remove unwanted line returns. 2023-06-23 20:33:47 +02:00
Vincent STRAGIER
dc0fa0cec6 Merging from master 2023-06-23 20:26:51 +02:00
Vincent STRAGIER
195de6e85f Merge remote-tracking branch 'upstream/HEAD' into YOLOv8 2023-06-23 17:58:13 +02:00
Vincent STRAGIER
1a3e869737 Better type checking. 2023-06-23 17:37:19 +02:00
Vincent STRAGIER
1506a67725 Revert some grammar changes. 2023-06-23 16:53:34 +02:00
Vincent STRAGIER
22ffc280bb Merge remote-tracking branch 'upstream/HEAD' into analyze_raise_on_empty_actions 2023-06-23 15:50:04 +02:00
miawoltn
011a0987a7 enhancement for deepface home path creation 2023-06-11 07:38:27 +01:00
Vincent STRAGIER
052abd26c7 Merge branch 'analyze_raise_on_empty_actions' into YOLOv8 2023-06-09 13:51:30 +02:00
Vincent STRAGIER
08988fcd0d Merging from master 2023-06-09 13:32:43 +02:00
Vincent STRAGIER
e845c00c24 Partial grammatical uniformisation of analys**. 2023-06-05 14:30:19 +02:00
Vincent STRAGIER
4ff75ecfc2 Remove unwanted changes and fix linting. 2023-06-05 14:06:10 +02:00
Vincent STRAGIER
0e9d7b7915 Grammar. 2023-06-05 13:56:47 +02:00
Vincent STRAGIER
f88a560f21 Fix linting errors. 2023-06-05 13:54:40 +02:00
Vincent STRAGIER
a380cfffbb Remove unwanted changes, and add comments. 2023-06-05 13:47:55 +02:00
Vincent STRAGIER
c96a2e4456 Add some comments. 2023-06-05 12:30:57 +02:00
Vincent STRAGIER
c09fc43d45 Add some comments about the changes. 2023-06-05 12:27:18 +02:00
Vincent STRAGIER
907db28625 Restore "no result" guard. 2023-05-24 20:50:49 +02:00
Vincent STRAGIER
769a497896 Correct laterality of the eyes landmarks. 2023-05-23 23:54:21 +02:00
Vincent STRAGIER
6c06996686 Remove "show" from the YOLOv8 detector. 2023-05-23 23:17:55 +02:00
Vincent STRAGIER
b32c31aea3 Remove broken models. 2023-05-23 23:01:34 +02:00
Vincent STRAGIER
659633f286 All available YOLOv8-face models 2023-05-23 23:00:49 +02:00
Vincent STRAGIER
b08695ac39 Clean the new wrapper. 2023-05-23 20:53:29 +02:00
Vincent STRAGIER
1b33865e05 Add alignment. 2023-05-23 20:51:35 +02:00
Vincent STRAGIER
ed38c03eae Add eyes landmarks. 2023-05-23 19:30:54 +02:00
Vincent STRAGIER
b452bd26ac Add YOLOv8n-face, with confidence 2023-05-23 19:18:38 +02:00
Vincent STRAGIER
e643f56b75 Unlinted changes 2023-05-23 14:47:22 +02:00
miawoltn
0ade149ee6 add missing parameter descriptions 2023-05-09 12:28:27 +01:00
Sefik Ilkin Serengil
52ad8e46be
Update functions.py 2023-04-29 17:37:54 +01:00
Sefik Ilkin Serengil
16fa3c2969
Read img restored 2023-04-29 17:23:15 +01:00
Sefik Ilkin Serengil
aa4e4abe30
imread restored 2023-04-29 15:27:30 +01:00
RayVik
8d91ea2f21
Update functions.py 2023-04-28 19:03:57 +03:00
RayVik
6522fa7d02
Update functions.py 2023-04-28 18:39:20 +03:00
RayVik
06ca8161bc
Update functions.py 2023-04-28 02:39:58 +03:00
RayVik
d3f78558ff
Fix bug with unicode filenames 2023-04-27 15:49:32 +03:00
Sefik Ilkin Serengil
d64800f2c0 bug 708 - deepid input shape 2023-04-22 10:52:04 +01:00
DonghwanKIM0101
decd220e6c issue 435, measure eyes' size 
@thelostpeace comments that the data is [x, y, w, h], not [x1, y1, x2, y2].
 2023-04-21 22:05:12 +09:00
Matthew Liechty
b23749509f
Update DeepFace.py 2023-03-09 11:02:22 -05:00
Vincent STRAGIER
03d7d1931f Reformat using black with settings.json 2023-03-01 14:01:15 +01:00
Vincent STRAGIER
3a325f5540 Reformat with black and pylint. 2023-03-01 13:40:46 +01:00
Vincent STRAGIER
0d176360ad Remove type hints (PEP484) 2023-03-01 13:05:04 +01:00
Vincent STRAGIER
7b0f34cbb1 Close #532, add docstring and some refactoring. 2023-03-01 12:44:47 +01:00
Sefik Ilkin Serengil
7414066a73
docstring 2023-02-24 12:05:13 +00:00
Sefik Ilkin Serengil
75f3eb7577 deprecated functions 2023-02-24 11:54:58 +00:00
Sefik Ilkin Serengil
a010c4188f deprecated functions 2023-02-24 11:37:57 +00:00
Sefik Ilkin Serengil
d04ab28bd3 deprecated functions added 2023-02-23 10:04:22 +00:00
Sefik Ilkin Serengil
ab8470f96f
resize bug while skipped detector 2023-02-10 14:05:40 +00:00
Sefik Ilkin Serengil
f9ec08ec04
restore 2023-02-10 13:49:52 +00:00
Sefik Ilkin Serengil
067e8f8c19
restore 2023-02-10 13:34:34 +00:00
Sefik Ilkin Serengil
8f667eecc8
resizing bug in represent for skipped detector 2023-02-10 13:17:50 +00:00
Sefik Ilkin Serengil
ea43de9baa
if detector is skipped, then resizing is missing in representation 2023-02-10 13:11:30 +00:00
Sefik Ilkin Serengil
ded49bbfa1
Merge pull request #649 from alenpaulvarghese/typo-fix 
fixed a typo in the comment string
 2023-01-30 21:23:46 +00:00
Sefik Ilkin Serengil
95e157e1d9 dict keys instead of items 2023-01-30 21:22:36 +00:00
roydenwa
7fbf474270
Unpack detection tuple to get detection dict 2023-01-30 21:31:04 +01:00
AlenPaulVarghese
3d52f3ee7e
fixed a typo in the comment string 2023-01-30 17:52:24 +05:30
Sefik Ilkin Serengil
e679c7206a cleaner codes 2023-01-29 23:44:09 +00:00
Sefik Ilkin Serengil
2d39ade138 clean code refactoring 2023-01-29 21:39:54 +00:00
Sefik Ilkin Serengil
029f3dfa43
Merge pull request #648 from ekkolon/improve-model-feature-maintainability 
refactor: use const for model feature labels
 2023-01-29 17:35:04 +00:00
Sefik Ilkin Serengil
889d5d5fd4 cleaning github action warnings 2023-01-29 16:41:19 +00:00
Nelson Dominguez
96025c1118 refactor: use const for model feature labels 
This commit moves the feature labels for the Emotion, Gender and Race model to their
respective modules.
 2023-01-29 17:32:38 +01:00
Sefik Ilkin Serengil
8f07aede24 linting warnings 2023-01-29 11:41:40 +00:00
Sefik Ilkin Serengil
aa7a8af9ff workflow test 2023-01-29 01:08:13 +00:00
Sefik Ilkin Serengil
7a978d29c5 linting 2023-01-29 00:45:25 +00:00
Sefik Ilkin Serengil
be4b41fa79
docstring 2023-01-27 10:11:55 +00:00
Sefik Ilkin Serengil
f4ce488ab7
target size as is 2023-01-26 17:00:53 +00:00
Sefik Ilkin Serengil
e3d73ca89d
deep id target size 2023-01-26 16:59:52 +00:00
Sefik Ilkin Serengil
89de20cc98
target size bug 2023-01-26 16:02:44 +00:00
Ronald Pereira
6e6215e4b9 updated PR to remove model parameter 2023-01-26 11:49:56 -03:00
Ronald Pereira
d24aeae030 updated docstring indentation 2023-01-26 10:56:58 -03:00
Ronald Pereira
e14d7d6afc .represent model parameter was being ignored if built and passed to function call 2023-01-26 10:54:24 -03:00
Sefik Ilkin Serengil
9f50eec4cd
read me 2023-01-24 23:08:02 +00:00
Sefik Ilkin Serengil
700867c7db new interface 2023-01-24 22:57:35 +00:00
Sefik Ilkin Serengil
dec0c34b2d new interface 2023-01-23 23:51:20 +00:00
Sefik Ilkin Serengil
9c6434a145 conflict 2023-01-23 21:56:30 +00:00
Sefik Ilkin Serengil
b62e3671f8 handling many faces 2023-01-23 21:54:52 +00:00
Sefik Ilkin Serengil
9c3f30db1a
doc string 2023-01-16 16:57:55 +00:00
Sefik Ilkin Serengil
e31cfe4bc8
doc string 2023-01-16 15:41:07 +00:00
Yiğit Ö. Ünver
4e3631c579
case handling analyze function with single actions 2022-12-11 21:49:02 +03:00
Nelson Dominguez
2fbec20859
style: fix minor spelling error in print message 2022-10-24 15:22:42 +02:00
Sefik Ilkin Serengil
db3a0f2fe8
Merge branch 'master' into regions 2022-10-24 11:24:36 +03:00
Sefik Ilkin Serengil
11d3061c9f verbose condition 2022-10-23 17:56:23 +01:00
Sefik Ilkin Serengil
51d10000c7 verboss off for just tf models 2022-10-23 17:55:10 +01:00
Sefik Ilkin Serengil
bbc3c6d59b
Merge pull request #580 from Andrea-Oliveri/confidence 
Added confidence to FaceDetector.detect_face and .detect_faces methods
 2022-10-23 19:27:48 +03:00
Sefik Ilkin Serengil
f26bb45b09 verbose off anyway 2022-10-23 17:23:58 +01:00
Andrea Oliveri
eeca8775ca Fixed minor bug: all regions now are (left, top, width, height) 2022-10-23 16:33:00 +02:00
Andrea Oliveri
d96b4bdbc5 Added confidence to FaceDetector.detect_face and .detect_faces methods 2022-10-23 15:49:26 +02:00
Hoan Nguyen
a807284e2a
feat(verbose): Silent tensorflow models output to stdout 2022-10-21 10:01:12 +02:00
Sefik Ilkin Serengil
5d767e2d49 code style 2022-06-22 14:11:35 +01:00
sasael
3f2fa48bee Taking gender_prediction directly 2022-06-22 15:36:20 +03:00
sasael
2135941912 - Added doReverted keras.models 
- Running test_nonbinary_gender.py in unit_tests.py
 2022-06-22 15:34:39 +03:00
sasael
449bea3770 Merge branch 'master' of https://github.com/shirasael/si-deepface 2022-06-18 19:54:27 +03:00
sasael
07220feb2d bugfixes 2022-06-18 19:46:21 +03:00
Sefik Ilkin Serengil
dc57b9d43f
enforce_detection desc 2022-06-15 17:20:43 +01:00
sasael
3f29c6a606 Added dominant_gender and probabilities for man / woman results in analyze function 2022-06-12 15:35:53 +03:00
Sefik Ilkin Serengil
2bd5a5d572 script 2022-05-23 23:56:30 +01:00
Sefik Ilkin Serengil
631cf64236 sface class 2022-05-10 22:39:54 +01:00
Sefik Ilkin Serengil
11df8d529f sface cleaner 2022-05-10 20:09:31 +01:00
Sefik Ilkin Serengil
f3d2a1f95a SFace thresholds 2022-05-10 00:36:21 +01:00
Sefik Ilkin Serengil
f89eb9264d sface threshold 2022-05-09 21:58:09 +01:00
Sefik Ilkin Serengil
cddc78f48d sface updates 2022-05-09 21:51:33 +01:00
Sefik Ilkin Serengil
8eafd08fc9
Merge branch 'master' into master 2022-05-09 21:44:14 +01:00
Rodrigo Andrade
3c0d84e34b fix input shape size 2022-05-08 21:35:25 -03:00
Rodrigo Andrade
1d18013978 fix typo 2022-05-08 21:27:56 -03:00
Rodrigo Andrade
a5ecdc1d8c use preprocessing from opencv 2022-05-08 21:27:42 -03:00
Rodrigo Andrade
9852bbe482 added sface 2022-05-08 21:19:52 -03:00
Rodrigo Andrade
f74e944dc6 sface wrapper 2022-05-08 21:19:41 -03:00
Onur Atakan ULUSOY
709cdc8109
Import fire 2022-05-09 00:13:53 +03:00
Onur Atakan ULUSOY
78358f7812
Merge branch 'master' into adding_command_line_interface 2022-05-08 23:23:06 +03:00
Onur Atakan ULUSOY
2d0aad07bb Save Operation for CLI 2022-05-08 23:20:42 +03:00
Sefik Ilkin Serengil
7a313f8fb0 main 2022-05-08 20:25:43 +01:00
Sefik Ilkin Serengil
31de8d7461 fire removed 2022-05-08 20:17:52 +01:00
Onur Atakan ULUSOY
a7cbf6da63 Added command line interface via fire library 2022-05-08 13:24:03 +03:00
Sefik Ilkin Serengil
fb68d4a8f8
numpy bgr 2022-05-01 09:26:49 +01:00
EigenEmara
8ceadea6ae Allow silent operation for find() 2022-04-15 10:23:01 +02:00
renhaa
4c0cdefe82
Fix typo in analyze docstring 
```python
models['race'] = DeepFace.build_model('race')
```
gives
``` 
ValueError: Invalid model_name passed - race
```
Should be capital "Race"
```python
models['race'] = DeepFace.build_model('Race')
```
 2022-03-15 09:29:48 +01:00
Sefik Ilkin Serengil
d080107998 issue 435 2022-03-11 20:43:56 +00:00
Sefik Ilkin Serengil
5171484957
simplified code 2022-01-19 12:07:57 +03:00
Sefik Ilkin Serengil
3485c348bc
previous code 2022-01-19 11:55:31 +03:00
sotirismos
4e2f8aba88 enhanced cropping of detected faces 2022-01-18 22:33:22 +02:00
Sefik Ilkin Serengil
12f34aa53f
Merge pull request #346 from blueprintparadise/master 
Add MediapipeWrapper as a detector
 2022-01-12 21:47:24 +03:00
Sefik Ilkin Serengil
b4122698b6
verify outputs 2022-01-12 17:18:18 +03:00
Sefik Ilkin Serengil
36ef4dc3f1 bug fix after pr 2022-01-08 09:41:56 +03:00
Sefik Ilkin Serengil
ea10243c7e
target_size in detectFace 2021-12-24 11:44:46 +03:00
Kanan_Mahammadli
799eb6c7a0 Modified functions.py so that it can read from https 2021-12-22 19:09:15 +03:00
Sefik Ilkin Serengil
96f7540199
division by 0 fixed 2021-11-13 11:26:48 +03:00
Sefik Ilkin Serengil
1ad0ffc6d9
continue if no face detected 2021-11-13 11:22:28 +03:00
Bosco Yung
a2f7ce6f97
Fix wrong img variable 2021-11-11 16:20:02 +08:00
Bosco Yung
9b816648e0
Remove extra BGR2RGB call in RetinaFaceWrapper 
I suggest removing the extra BGR2RGB call.

While the RetinaFace model does expect RGB images, the corresponding conversion will be done in the RetinaFace preprocessing:
0c8d3ed8bd/retinaface/commons/preprocess.py (L45)

The extra BGR2RGB call here will in fact make the final channel order wrong, because OpenCV does not know about the channel order, each call will simply swap the channels.

Thanks!
 2021-11-10 16:01:51 +08:00
blueprintparadise
4fc81fd2ef
Update MediapipeWrapper.py 2021-09-28 17:02:32 +05:30
blueprintparadise
f07f278d22
Update FaceDetector.py 2021-09-28 16:28:20 +05:30
blueprintparadise
ae10f5a352
Add files via upload 2021-09-28 16:26:15 +05:30
fpaludi
dbfebea430 Remove mutable objects from analyze arguments. Add tests to validate 2021-09-22 19:56:23 -03:00
Roelof Ruis
5a61a20ecf specify model directory via DEEPFACE_HOME env variable 2021-08-23 15:26:36 +02:00
Roelof Ruis
5b280dcb81 function name snake case 2021-08-23 15:08:47 +02:00
Sefik Ilkin Serengil
b024060284 ability to skip pre-processing 2021-08-19 17:37:01 +03:00
Sefik Ilkin Serengil
885f89dd52 issue 309 - lfw with detectors 2021-08-19 17:32:41 +03:00
Sefik Ilkin Serengil
d1e16f68b5 normalize_input simplified 2021-08-01 22:51:55 +03:00
Sefik Ilkin Serengil
e4484ac309 issue 131 normalization 2021-07-31 22:14:52 +03:00
Sefik Ilkin Serengil
b4631f1562 align arg for detectFace 2021-07-30 17:06:16 +03:00
Sefik Ilkin Serengil
3962545c82 issue 289 2021-07-27 18:50:56 +03:00
Sefik Ilkin Serengil
d3e03c3e5a detector argument for stream 2021-07-27 00:15:15 +03:00
Sefik Ilkin Serengil
74704452a3 bug 284 2021-07-13 09:39:43 +03:00
Sefik Ilkin Serengil
922682c1fa facenet 512 2021-07-12 23:25:37 +03:00
Sefik Ilkin Serengil
8d304056a8 progress bar 2021-07-10 22:20:27 +03:00
Martin Knoche
99fa752555
Added prog_bar keyword argument 
To be able to disable tqdm progress bars in "analyze" method
 2021-07-09 14:21:37 +02:00
Sefik Ilkin Serengil
a904d9007c google drive to github release 2021-07-03 00:27:35 +03:00
Sefik Ilkin Serengil
ed9367b8f1
resize approach 2021-07-02 09:30:27 +03:00
Sefik Ilkin Serengil
94236318ac
comments for resize 2021-07-01 17:17:46 +03:00
Libo-Xu
74d2f98883
Finish the TODO in function "preprocess_face" 
Resize the detected face image proportionally then add black pixels to resize it to target_size, which avoids the transformation on the detected faces resulting from resizing directly.
 2021-07-01 10:40:11 +08:00
Sefik Ilkin Serengil
5e2c530835 singleton comment 2021-06-27 00:56:27 +03:00
Sefik Ilkin Serengil
d73dcd5f23 region duplication simlified 2021-06-26 23:19:39 +03:00
Sefik Ilkin Serengil
a35b31d242 Merge branch 'master' of https://github.com/serengil/deepface 2021-06-26 23:13:54 +03:00
Sefik Ilkin Serengil
0fc1672c89 lightweight api 2021-06-26 23:13:46 +03:00
Sefik Ilkin Serengil
2c2aaa0ede
retinaface is not a must dependency 2021-06-25 16:01:47 +03:00
Sefik Ilkin Serengil
ea1497e35d eye detection procedure 2021-06-24 16:09:34 +03:00
Sefik Ilkin Serengil
057f06c09c detectFace bug + robust eye detector 2021-06-24 15:59:59 +03:00
Sefik Ilkin Serengil
18c96e492e performance improvement 2021-06-24 09:30:45 +03:00
Sefik Ilkin Serengil
8458e107c7 no need to use initialize_detector function anymore 2021-06-24 00:35:47 +03:00
Sefik Ilkin Serengil
e0809bf490 face recognition models as global 2021-06-24 00:11:06 +03:00
Sefik Ilkin Serengil
9f31012ef4 detector as a global variable 2021-06-24 00:00:20 +03:00
Sefik Ilkin Serengil
62baee3b45 more robust eye detector for opencv 2021-06-23 23:36:40 +03:00
Sefik Ilkin Serengil
8071733ddf opencv detector is default 2021-06-23 13:46:47 +03:00
Sefik Ilkin Serengil
67149c629b stream bug 2021-06-15 18:36:47 +03:00
Sefik Ilkin Serengil
4267953dc3 retinaface as default detector 2021-06-13 17:12:38 +03:00
Sefik Ilkin Serengil
804fbaa511 52 version causes trouble for stream 2021-05-28 09:32:06 +03:00
Sefik Ilkin Serengil
9af7c33ff7 version 0.0.52 2021-05-27 22:41:51 +03:00
Sefik Ilkin Serengil
3cd55fcf00
mtcnn is not a mandatory lib 2021-05-27 16:43:48 +03:00
Sefik Ilkin Serengil
1812391a3c align argument 2021-04-29 21:38:08 +03:00
Sefik Ilkin Serengil
73d1950133 initialize detector in represent 2021-04-29 21:19:49 +03:00
Sefik Ilkin Serengil
91aa422677 some comments 2021-04-29 21:04:08 +03:00
Sefik Ilkin Serengil
d11f08958e global eye detector for opencv and ssd 2021-04-29 21:00:25 +03:00
Sefik Ilkin Serengil
f4c78457c2 retinaface perf 2021-04-29 09:11:33 +03:00
Sefik Ilkin Serengil
0bdc341ce7 clean code in detectors interface 2021-04-28 23:03:15 +03:00
Sefik Ilkin Serengil
b898f97b38 detector mechanism 2021-04-28 21:42:58 +03:00
Sefik Ilkin Serengil
974f8bf27b retinaface added 2021-04-26 21:37:01 +03:00
Sefik Ilkin Serengil
b0f152ab31 ignore tf2 warnings 2021-04-11 14:25:22 +03:00
Sefik Ilkin Serengil
45b4714f47 represent function referenced in verify 2021-04-11 14:19:33 +03:00
Sefik Ilkin Serengil
d43aacb87e represent function 2021-04-10 12:30:24 +03:00
olive380
1b2ac91dfc
Fix bounding box for dlib 
Change right --> top
 2021-03-29 16:04:44 +02:00
Sefik Ilkin Serengil
83a2be7a5d stream video 2021-03-21 18:38:06 +03:00
Sefik Serengil
fee02411b3 issue 197 2021-03-09 22:16:34 +03:00
Sefik Serengil
97be78b004 face region fixes 2021-02-17 20:18:04 +03:00
Sean Yong
1f8bea146e Fixed bug with ssd facebox region 2021-02-17 13:55:49 +08:00
Sean Yong
e22072142e Added retrieve bounding box from analysis 2021-02-17 13:23:01 +08:00
Sefik Ilkin Serengil
d37e8930fc
issue 185 2021-02-11 11:58:22 +03:00
Sefik Serengil
e295cbfb55 issue 182 resolved 2021-02-05 20:57:57 +03:00
Sefik Ilkin Serengil
2dea7aeeba
issue 175 2021-01-25 21:26:33 +03:00
Sefik Serengil
286d48395d issue 162, deepid find 2021-01-13 22:41:17 +03:00
serengil
27843d69b4 boosting gdown dependency 2020-12-26 21:38:23 +03:00
serengil
0ef832c081 bug fixed for numpy inputs 2020-12-22 11:40:28 +03:00
serengil
6be5b2d41a analyze function is cleaner 2020-12-21 23:30:00 +03:00
serengil
5cfdb3b179 arcface added 2020-12-14 15:04:41 +03:00