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

628 Commits

Author SHA1 Message Date
Jud White bcdf943ca7
reversed order 
- oops.
 2018-03-25 15:51:48 -05:00
Jud White 8b7121b34a
fix link to issue #500 
#nnn alone doesn't work in readme/wiki markdown
 2018-03-25 15:50:20 -05:00
Jud White c6ecf1e042
README.md: add notes to How to compile on Windows 2018-03-25 15:41:48 -05:00
AlexeyAB 8f1f5cbf83 3.5x times accelerated data augmentation using OpenCV for training Yolo on DGX and multi-GPU 2018-03-24 23:35:05 +03:00
AlexeyAB 101de2b07a More stable web-cam 2018-03-21 00:40:01 +03:00
AlexeyAB fe4f01b1d8 Fixed uses of WebCam for OpenCV 3.x 2018-03-20 22:10:46 +03:00
Alexey 3e5abe0680
Update Readme.md 2018-03-20 03:14:20 +03:00
AlexeyAB ced198e939 Fixed gpu_id for DLL/SO 2018-03-20 02:17:26 +03:00
AlexeyAB 537d135feb Improve training performance - batch-norm using cuDNN. 2018-03-20 02:16:51 +03:00
AlexeyAB 2f52cfeb07 Fixed compile error 2018-03-17 01:12:00 +03:00
AlexeyAB e947bf29af C wrappers 2018-03-17 01:03:56 +03:00
AlexeyAB 164ba34279 Fixed bug, that save weights-file for each iteration 2018-03-16 14:58:21 +03:00
AlexeyAB 371f21171a shortcut_layer resize for random=1 2018-03-16 01:49:01 +03:00
AlexeyAB df076653e0 Minor fix 2018-03-13 19:04:39 +03:00
AlexeyAB 15c89e7a71 Added include for sprintf 2018-03-12 14:11:53 +03:00
AlexeyAB 880cf187d8 Fixed multi-GPU training for Tensor Cores 2018-03-09 19:44:46 +03:00
AlexeyAB a6c51e3b75 Fixes for small objects. And fixes of densenet201_yolo.cfg, resnet50_yolo.cfg, resnet152_yolo.cfg 2018-03-09 01:42:58 +03:00
AlexeyAB 100d6f7801 Remove 1 additional conv 3x3 kernel layer from resnet152_yolo.cfg and resnet50_yolo.cfg 2018-03-06 02:38:54 +03:00
AlexeyAB ae1768e583 Removed random=1 from resnet152_yolo.cfg. Until resize_network() isn't supported for [shortcut] layer 2018-03-05 23:26:09 +03:00
AlexeyAB e90afa6ec1 resnet152_yolo.cfg uses learning_rate, steps, scales, decay, momentum as in the RetinaNet 2018-03-05 23:07:33 +03:00
AlexeyAB 0c07837397 Added resnet152_yolo.cfg with focal_loss=1 and stopbackward=1 in the last shortcut layer. 2018-03-05 20:31:43 +03:00
AlexeyAB 5e448c00f3 Added Focal loss. Use focal_loss=1 in the [region] layer in your cfg-file. 
alpha = 0.5, gamma = 2
 2018-03-05 19:59:29 +03:00
AlexeyAB f0bc634a74 Fixed saving video file 2018-03-05 13:25:27 +03:00
Alexey 09fdb67d66
Update Readme.md 2018-03-05 01:43:56 +03:00
AlexeyAB c123f320fc Show avg-loss chart during Training, if compiled with OpenCV. Use -dont_show to disable. 2018-03-04 23:41:23 +03:00
AlexeyAB 48586c8d4d Compile fix 2018-03-04 18:15:56 +03:00
AlexeyAB 74f98da211 Show IoU, save anchors to file.Show anchors in the window if used -show 2018-03-04 17:59:23 +03:00
AlexeyAB f39160f6e8 Added: calc_anchors 2018-03-04 03:09:40 +03:00
AlexeyAB fe44d3d0f2 Fixed reorg_layer. Old reorg can be used as [reorg_old] in the cfg-file. 2018-03-03 18:09:46 +03:00
AlexeyAB e16c901163 minor fix 2018-03-02 00:16:26 +03:00
AlexeyAB be9ccb7d7f Added F1 score to accuracy statistic 2018-03-02 00:09:52 +03:00
Alexey 1e84a2804e
Update Readme.md 2018-03-01 18:38:58 +03:00
Alexey 671735fb00
Update Readme.md 2018-03-01 18:36:14 +03:00
AlexeyAB 7caf345d36 One more fix 2018-03-01 16:42:30 +03:00
AlexeyAB 18d5670d64 Compile fix 2018-03-01 16:33:40 +03:00
AlexeyAB 5cd147031b Added param -dont_show to detect objects on servers without display, like Amazon EC2 2018-03-01 16:05:39 +03:00
AlexeyAB 35a66b73a2 Changed class to class_id 2018-03-01 15:14:58 +03:00
Alexey 17b22d7ce7
Update Readme.md 2018-03-01 03:10:32 +03:00
AlexeyAB 490d02505b Fixed VideoWriter 2018-02-26 21:48:09 +03:00
Alexey e96a454ca1
Update Readme.md 2018-02-26 01:13:55 +03:00
AlexeyAB 48d713fd49 Fine-tuning densenet201_yolo.cfg and resnet50_yolo.cfg 2018-02-26 01:09:14 +03:00
AlexeyAB cad4d1618f Added support for Tensor Cores CC >= 7.0 (V100). For FP16/32 (mixed precision) define CUDNN_HALF should be used. 2018-02-25 16:29:44 +03:00
AlexeyAB 85eafd3d59 Added partial.cmd 2018-02-25 15:23:11 +03:00
AlexeyAB 3ff4797b4c Added gen_anchors.py 2018-02-25 14:48:08 +03:00
Alexey 175e47317e
Update Readme.md 2018-02-24 02:35:38 +03:00
AlexeyAB cd2bdec090 Updated to CUDA 9.1. And fixed no_gpu dependecies. 2018-02-23 15:05:31 +03:00
AlexeyAB 6332ea99ab one more fix 2018-02-23 00:13:08 +03:00
AlexeyAB b2b5756d86 Added __float2half_rn() and __half2float() 2018-02-22 23:52:43 +03:00
AlexeyAB f558d5c39c Fix 2018-02-22 23:16:36 +03:00
AlexeyAB dda993f3dd Use half_float16 instead of float32 if defined both CUDNN and CUDNN_HALF. Use Tensor Cores. 2018-02-22 22:54:40 +03:00