OrgLion-ML
/
darknet
mirror of https://github.com/AlexeyAB/darknet.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
2,172 Commits 1 Branch 7 Tags 361 MiB
Commit Graph

2172 Commits

Author SHA1 Message Date
Alexey d4c10b0262
Merge pull request #5400 from ali-babaei/master 
[ fix ] - Not printing Iteration info in log file
 2020-05-05 20:13:16 +03:00
Alexey 97df6ac2b4
Merge pull request #5479 from cenit/dev/cenit/appveyor_removal 
remove appveyor CI
 2020-05-05 20:11:33 +03:00
Stefano Sinigardi 502fd51cd1 remove appveyor badge 2020-05-05 00:36:48 +02:00
Stefano Sinigardi cba6153a41 remove appveyor CI 2020-05-04 19:52:06 +02:00
Alexey 37b62bc08c
Merge pull request #5417 from cenit/dev/cenit/ci_updates 
ci upgrades and half precision for cc >=7.0
 2020-05-04 18:29:20 +03:00
Stefano Sinigardi 861192df19 shorten github actions names 2020-05-03 16:36:05 +02:00
Wang Xinyu 102e31ba66
Update readme, add tensorrt yolov3-spp, yolov4 2020-05-02 20:57:44 +08:00
Juan Altmayer Pizzorno a34682e67c - adjusted BatchNorm epsilon of normalize_cpu to be the same as 
normalize_gpu's kernel;
 2020-05-01 16:05:37 -04:00
JaledMC 2a9ef5246c
out_filename parameter bug 
The change from arparse parameter output_file to out_filename crash with this two lines
 2020-05-01 20:34:30 +02:00
JaledMC 02da35eb50
Change output_file to out_filename 2020-05-01 20:21:09 +02:00
JaledMC 52c7314340 python wrapper cleaning and new features 
a darknet module and both scripts for video and image inference, with the features of C code
 2020-05-01 18:30:53 +02:00
AlexeyAB 6cbb75d10b Minor fix for yolov4-custom.cfg 2020-05-01 18:45:40 +03:00
Stefano Sinigardi 551e57dc8b fix linux make and add windows cygwin on github actions 2020-05-01 16:00:36 +02:00
Stefano Sinigardi ac7436dccd ported build configs from circleCI 2020-05-01 09:29:03 +02:00
Stefano Sinigardi 24ad413a79 add mingw and cuda on github actions, restored cuda 10.2 on appveyor as a test 2020-05-01 09:28:51 +02:00
Stefano Sinigardi f2786ba19d expand github action ci coverage, leave only cygwin on appveyor. Next step will be cuda on github actions 2020-04-30 20:36:36 +02:00
Stefano Sinigardi 72b3712df8 force release mode 2020-04-30 19:55:55 +02:00
Stefano Sinigardi a993060d09 remove unnecessary system dependencies on github actions 2020-04-30 18:54:25 +02:00
Stefano Sinigardi c3dc2c4a0d use Release as default build type 2020-04-30 18:47:23 +02:00
Stefano Sinigardi 234218b961 add GitHub Actions 2020-04-30 16:47:56 +02:00
qboticslabs 185213438e Added sample scripts for yolov4 2020-04-30 00:04:27 -07:00
Stefano Sinigardi a3f6c2b58e merge with master 2020-04-30 08:41:51 +02:00
AlexeyAB f14054ec2b Fixed Cmake for CUDA CC 7.0, 7.2, 7.5 2020-04-30 02:20:42 +03:00
Stefano Sinigardi 98e4d246e1 make cuda version parametric on appveyor 2020-04-29 23:38:50 +02:00
Stefano Sinigardi 6afe964d4f upgrade CUDA, cmake and VS on CI 2020-04-29 22:31:07 +02:00
Stefano Sinigardi 1c64c2d892 enable cc70,cc72,cc75 for half_precision, add message for omp missing on macOS 2020-04-29 20:24:08 +02:00
Stefano Sinigardi fe879f3baf simplify cmake due to minimum project requirement already gone to 3.12 2020-04-29 20:24:08 +02:00
Stefano Sinigardi be49ab30cd omp support on macOS 2020-04-29 20:24:00 +02:00
Ali Babaei 885abb5046
Merge pull request #1 from ali-babaei/ali-babaei-patch-1 
[ fix ] - Not printing Iteration info in log file
 2020-04-29 10:26:43 +04:30
Ali Babaei 1c1275fe88
[ fix ] - Not printing Iteration info in log file 
When we redirect output of training into log files, while the net.cudnn_half is True, iteration information line, which contains "avg loss" is missed.
Using \n and fflush() fixed the issue. Each one of them may be enough to fix the issue.
 2020-04-29 10:23:40 +04:30
AlexeyAB 36c73c5b9e Some explanations for training 2020-04-28 19:20:50 +03:00
AlexeyAB 6d38218a04 Minor fix 2020-04-28 19:20:22 +03:00
AlexeyAB 65506eb04a Minor fix 2020-04-27 16:40:43 +03:00
AlexeyAB 83b3d46ede Fixed minor bug with closing ./darknet detector demo ... 2020-04-27 16:14:22 +03:00
Alexey 8e272fa868
Update Readme.md 2020-04-27 15:48:34 +03:00
AlexeyAB 6ebaef3095 Added GELU activation 2020-04-27 04:36:39 +03:00
AlexeyAB 6033baabc9 Minor fix - filename of chart (Loss & TopK) - training Classifier 2020-04-26 15:51:17 +03:00
AlexeyAB 379952208e Minor fix 2020-04-26 14:19:20 +03:00
Alexey 8db3fe4ef6
Update Readme.md 2020-04-25 18:05:36 +03:00
AlexeyAB 6f718c2578 Merge branch 'master' of github.com:AlexeyAB/darknet 2020-04-25 14:59:05 +03:00
AlexeyAB 893b889b2f Cmake is fixed for V100 (CC=7.0) 2020-04-25 14:58:36 +03:00
Alexey 2fc7fbbc0e
Update Readme.md 2020-04-24 16:22:13 +03:00
Alexey b1b2d5cfef
Update Readme.md 2020-04-24 04:02:02 +03:00
Alexey 3d4242a6e5
Update Readme.md 2020-04-23 15:23:39 +03:00
AlexeyAB 4131ae1d6e Yolo v4 2020-04-23 14:49:06 +03:00
AlexeyAB b573eab63f Minor fix 2020-04-22 20:49:27 +03:00
Alexey 88f28f7fcc
Merge pull request #4099 from enesozi/master 
Batch inference added
 2020-04-22 14:46:38 +03:00
AlexeyAB 7c1f9105f0 Minor fix 2020-04-21 04:25:43 +03:00
AlexeyAB 1fb4606d5d Minor fix 2020-04-19 19:45:04 +03:00
AlexeyAB 4786d557f9 Fixed memory leak for Training with OPENCV=1 - create pool of CPU-threads only once (bug in OpenCV - it allocates memory for each thread without deallocation) 2020-04-18 19:01:20 +03:00