OrgLion-ML
/
darknet
mirror of https://github.com/AlexeyAB/darknet.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
1,791 Commits 1 Branch 7 Tags 361 MiB
Commit Graph

1791 Commits

Author SHA1 Message Date
AlexeyAB fdb61f8cb4 Minor fix 2020-03-24 22:30:30 +03:00
AlexeyAB 5e904d5b1e adversarial attack - experimental 2020-03-24 22:23:15 +03:00
AlexeyAB a234a50223 Added efficientnet-lite3.cfg and activation=relu6 2020-03-23 21:56:32 +03:00
AlexeyAB bb5eb481d1 Minor fix 2020-03-23 20:03:56 +03:00
AlexeyAB 864d1062f8 Minor fix 2020-03-23 00:29:37 +03:00
Alexey 5f5ec84e40
Merge pull request #4783 from kseniaryabinova/chart_argument 
Added -chart argument
 2020-03-23 00:19:29 +03:00
Alexey 17dd701618
Merge pull request #4976 from mmaaz60/monitor_training 
Monitor training
 2020-03-23 00:15:57 +03:00
Muhammad Maaz 9407a81c9d Fix: Correct calculation of training time remaininig when resume training (src/classifier.c) 
Output training time remaining to console if darknet is not compiled with OpenCV
 2020-03-22 20:49:21 +05:00
Muhammad Maaz 8800212faa Adds support to print remaining training time on console if darknet is not compiled with OpenCV 2020-03-22 20:40:26 +05:00
Muhammad Maaz bd7690b019 Fix: Correct remaining training time in case someone resume training (src/detector.c) 2020-03-22 20:38:47 +05:00
AlexeyAB 5c2ddd301e Added param to cfg: [net] gaussian_noise=40 2020-03-22 17:38:07 +03:00
Muhammad Maaz 570f595247 Remove redundant code from classifier.c 2020-03-20 12:42:59 +05:00
Muhammad Maaz 1a6dd593c5 Fix: Use iteration instead of i for current iteration. 
Simplified the time remaining calculation logic.
 2020-03-19 17:15:42 +05:00
Muhammad Maaz 02e7109b8b
Merge branch 'master' into monitor_training 2020-03-19 13:31:51 +05:00
Muhammad Maaz d6253d5cd7 Logic Change: Implements rolling avg for remaining time calculation in classifier.c 2020-03-19 13:19:30 +05:00
Muhammad Maaz b77add049e Logic Change: Implements rolling avg for remaining time calculation in detector.c 2020-03-19 13:14:19 +05:00
AlexeyAB 92e6e8eece Minor fix 2020-03-15 18:08:00 +03:00
AlexeyAB 8ffc2b0b36 Minor fix 2020-03-15 14:06:03 +03:00
AlexeyAB 0c8e9ce4b2 Minor fix 2020-03-15 00:50:27 +03:00
AlexeyAB b24b61fb97 disable TC 2020-03-15 00:05:04 +03:00
AlexeyAB 18d877a1ac Fixed loss_scale 2020-03-15 00:04:18 +03:00
AlexeyAB fb4da5ce5f Clip for weight_updates for BiFPN 2020-03-14 15:31:01 +03:00
AlexeyAB 46ccac39e8 Minor fix 2020-03-14 13:43:33 +03:00
AlexeyAB 002177de00 Minor Fix 2020-03-14 13:19:56 +03:00
AlexeyAB 4ca7896402 Fixed constrain for BiFPN 2020-03-14 04:14:56 +03:00
AlexeyAB d11caf486d Fixed BiFPN and label_smothing for Detection 2020-03-14 03:24:46 +03:00
AlexeyAB d79d2815b9 clip float fix 2020-03-12 17:43:01 +03:00
AlexeyAB 54aa887462 Added clip=1 option for weighted-layers to constrain absolute weights value 2020-03-12 17:40:52 +03:00
AlexeyAB 9ac401fa67 BiFPN fix 2020-03-12 17:07:57 +03:00
AlexeyAB cf8409d7e1 Compile fix 2020-03-11 21:41:14 +03:00
AlexeyAB 4dff7cb769 final compile fix 2020-03-11 20:05:01 +03:00
AlexeyAB 56bd298297 another compile fix 2020-03-11 19:58:28 +03:00
AlexeyAB 374c769062 Compile fix 2020-03-11 19:54:39 +03:00
AlexeyAB 5e54523960 Added loss_scale for Mixed-Precision on Tensor-Cores 2020-03-11 19:47:13 +03:00
AlexeyAB 49a7cdd268 Compile fix 2020-03-11 17:20:27 +03:00
AlexeyAB 1a56ef588a Added flag -cuda_debug_sync for checking CUDA errors 2020-03-11 17:12:07 +03:00
Alexey e70b70db8f
Merge pull request #5002 from mandoo92/master 
Class_id Garbage Value Check
 2020-03-11 15:37:15 +03:00
Wastage 8c13ca1619
Class_id Garbage Value Check 
Added exception handling when Class_Id is garbage value (like negative)
 2020-03-11 15:33:59 +09:00
AlexeyAB a567a806a6 Set cur_iteration = 0; initially 2020-03-11 01:46:10 +03:00
AlexeyAB 6c4886485d Minor speedup of DropBlock (training) 2020-03-10 17:00:35 +03:00
Alexey c993a4bbe3
Merge pull request #4994 from Tclack88/master 
Update classifier.c
 2020-03-09 21:37:05 +03:00
Tclack88 992306b031
Update classifier.c 
declaring variables not allowed within `for loops` until C99. additionally. declaring int i multiple times within the same definition try_classifier  isn't necessary
 2020-03-09 09:45:50 -07:00
AlexeyAB b56e8d11cf Minor fix 2020-03-06 13:46:17 +03:00
Muhammad Maaz 1174bb7417 Add support to ignore first 50 iterations in calculating the remaining training time. 
For first 50 iterations chart will display 'nan hours' as remaining training time.
 2020-03-06 12:58:16 +05:00
Muhammad Maaz d1d2ad9d8f Merge branch 'monitor_training' of https://github.com/mmaaz60/darknet into monitor_training 2020-03-05 19:22:31 +05:00
Muhammad Maaz d124d552c0 Add feature to show approx. remaining training time to training chart. 2020-03-05 19:15:47 +05:00
Muhammad Maaz 324cc881ee Add support to display time remaining on the training chart. 2020-03-04 20:54:30 +05:00
Alexey b2fc7b624c
Merge pull request #4955 from Evert-Arends/master 
Update readme
 2020-03-03 21:56:05 +03:00
Evert Arends 4f95c78f54
Update readme 
Updated the readme to prevent reading mistakes and hours of pointless searching
 2020-03-03 19:27:53 +01:00
Alexey 60e0950c74
Update Readme.md 2020-03-02 18:15:47 +03:00