OrgLion-ML
/
darknet
mirror of https://github.com/AlexeyAB/darknet.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
2,266 Commits 1 Branch 7 Tags 361 MiB
Commit Graph

62 Commits

Author SHA1 Message Date
umbralada ac4e765a4a
added free_alphabet function; this function used for free alphabet. (#1805) 2023-09-01 23:15:01 +02:00
AlexeyAB 4098e4882c Minor fix 2020-05-20 19:51:06 +03:00
AlexeyAB b3c9f373d1 adversarial attack - minor improvement 2020-03-25 02:35:05 +03:00
vinjn 3000c3111f Expose crop_image and resize_min as LIB_API 2020-01-29 22:58:43 +08:00
AlexeyAB 114a7f942b Added command line param -dontuse_opencv for training Classifier. Also use GaussianBlur instead of bilateralFilter for blur=1 for training Classifier and Detector. 2019-12-28 18:46:10 +03:00
AlexeyAB 9c02df864e Fixed assisted_excitation and added also for [shortcut] layer 2019-09-04 18:50:56 +03:00
AlexeyAB f19d1440cb Moved all OpenCV functions to the image_opencv.cpp/h 2019-04-04 22:57:05 +03:00
AlexeyAB 9dddf82ab6 Compile fix. And minor fixes 2019-03-19 20:21:34 +03:00
Stefano Sinigardi 839f7c0f04 remove some unnecessary exports 2019-02-20 11:51:17 +01:00
Stefano Sinigardi b3579380dc improve compatibility with c++ compilers, prepare for CMake 2019-02-15 17:27:12 +01:00
AlexeyAB c50b0e0c8a Minor Python and C API improvement 2019-02-06 14:38:12 +03:00
John Aughey c00d3c92db Making a fast API compatible way to copy image data. 
This can improve on the python array_to_image function
where we already have an allocated image struct and simply
need to copy the data into the correct format/shape without
reallocating.

Aside: I think array_to_image does two frees because the pointer
data_as returns doesn't own the memory that is ultimately freed
in free_image.
 2019-02-05 11:40:21 -06:00
AlexeyAB d2b5e142b3 Minor fix 2019-01-14 13:56:42 +03:00
AlexeyAB 3ff5084590 Added include/darknet.h 2019-01-06 23:51:38 +03:00
AlexeyAB 1e512b2308 Letter box is disabled in the darknet.py by defualt 2018-06-04 22:11:05 +03:00
IlyaOvodov 1b5afb4583 Output improvements for detector results: 
When printing detector results, output was done in random order, obfuscating results for interpreting. Now:
1. Text output includes coordinates of rects in (left,right,top,bottom in pixels) along with label and score
2. Text output is sorted by rect lefts to simplify finding appropriate rects on image
3. If several class probs are > thresh for some detection, the most probable is written first and coordinates for others are not repeated
4. Rects are imprinted in image in order by their best class prob, so most probable rects are always on top and not overlayed by less probable ones
5. Most probable label for rect is always written first
Also:
6. Message about low GPU memory include required amount

Upd:
* struct detection changes reverted to keep it unchanged
* cmd line key "-ext_output" is added to manage extended output (rect coords in detector test mode)

# Conflicts:
#	src/detector.c
 2018-05-08 14:09:35 +03:00
AlexeyAB a0e288f0dc Increased speed of darknet.py. Fixed functions related to resize_image(). 2018-05-01 02:17:49 +03:00
AlexeyAB 6e3afec85a Fixed Python detection 2018-04-17 14:21:23 +03:00
AlexeyAB fc496d52bf Yolo can be used from Python 2.x using /darknet.py on Linux or darknet/x64/darknet.py on Windows 2018-04-12 22:32:57 +03:00
AlexeyAB d9ae3dd681 Added Yolo v3 2018-03-28 02:59:03 +03:00
AlexeyAB 2baa7bde54 Fixed classifier for AlexNet and Resnet50 2017-09-15 20:31:48 +03:00
Joseph Redmon 62235e9aa3 cpu batch norm works 2016-11-18 21:51:36 -08:00
Joseph Redmon c7a700dc22 new font strategy 2016-11-05 14:09:21 -07:00
Joseph Redmon 481b57a96a So I have this new programming paradigm....... 2016-09-24 23:12:54 -07:00
Joseph Redmon 6b38dcdce0 adding new tiny-yolo 2016-09-07 22:27:56 -07:00
Joseph Redmon 8f1b4e0962 updates and things 2016-09-01 16:48:41 -07:00
Joseph Redmon aebe937710 what do you even write here? 2016-08-11 11:54:24 -07:00
Joseph Redmon 845ab75796 some more stuff 2016-08-05 15:27:07 -07:00
Joseph Redmon ec3d050a76 hope i didn't break anything 2016-06-02 15:25:24 -07:00
Joseph Redmon d1965bdb96 Go 2016-03-13 23:18:42 -07:00
Joseph Redmon 16d06ec0db stuff 2016-02-29 13:54:12 -08:00
Joseph Redmon 1578ec70d7 idk 2016-01-18 15:40:14 -08:00
Joseph Redmon 0305fb4d99 Some changes 2015-11-26 11:48:01 -08:00
Joseph Redmon b394337824 killed some warnings, cam control 2015-11-17 11:09:00 -08:00
Joseph Redmon a9e16d914a more writing stuff 2015-09-22 17:34:48 -07:00
Joseph Redmon 8bcdee8658 Some bug fixes, random stuff 2015-09-01 11:22:03 -07:00
Joseph Redmon 9d42f49a24 changing data loading 2015-08-24 18:27:42 -07:00
Joseph Redmon e625b32e06 Should fix for OpenCV 3.0 2015-08-14 08:45:52 -07:00
Joseph Redmon e56d1eff13 Switch to fast resize 2015-07-21 11:46:24 -07:00
Joseph Redmon 8ed0a5538e faster resize? 2015-07-21 11:38:36 -07:00
Joseph Redmon a08ef29e08 NIGHTMARE!!!! 2015-07-10 16:38:14 -07:00
Joseph Redmon 3b864c2254 width and stuff 2015-07-10 16:36:08 -07:00
Joseph Redmon cbc9984a17 NIPS 2015-06-10 00:11:41 -07:00
Joseph Redmon d97331b88f level adjustment for images 2015-04-15 00:32:32 -07:00
Joseph Redmon 5a49c1d962 rotation 2015-04-09 23:00:33 -07:00
Joseph Redmon 4f50e29365 big change to images 2015-04-09 15:18:54 -07:00
Joseph Redmon a05c4bd2e9 sqrt 2015-04-01 10:25:50 -07:00
Joseph Redmon f98bf6bbdb We do our OWN resizing! 2015-03-28 16:11:37 -07:00
Joseph Redmon 5f4a5f59b0 captcha stuff 2015-02-23 18:52:05 -08:00
Joseph Redmon 79fffcce3c Better imagenet distributed training 2014-12-11 13:15:26 -08:00