OrgLion-ML
/
darknet
mirror of https://github.com/AlexeyAB/darknet.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
1,790 Commits 1 Branch 7 Tags 361 MiB
Commit Graph

115 Commits

Author SHA1 Message Date
AlexeyAB 6ebaef3095 Added GELU activation 2020-04-27 04:36:39 +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 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
AlexeyAB d4b2ed9d22 Added param train_only_bn=1 to train only Batch-normalization for this and previous layers 2020-04-17 19:06:15 +03:00
AlexeyAB 68062fa4fb Added param to [yolo] iou_thresh_kind=giou iou_thresh=0.213 2020-03-31 21:12:41 +03:00
AlexeyAB 4cd21785fc Minor fix 2020-03-31 19:15:33 +03:00
AlexeyAB 6a77b8dc9a Show receptive field 2020-03-29 20:00:03 +03:00
AlexeyAB 8cb1f0c44f Minor fix 2020-03-26 02:34:01 +03:00
AlexeyAB 9919612006 Added attention during training: [net] adversarial_lr=0.05 attention=1 2020-03-26 01:25:04 +03:00
AlexeyAB 978c2e00ed self-adversarial training 2020-03-26 00:16:57 +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
Alexey 5f5ec84e40
Merge pull request #4783 from kseniaryabinova/chart_argument 
Added -chart argument
 2020-03-23 00:19:29 +03:00
AlexeyAB 5c2ddd301e Added param to cfg: [net] gaussian_noise=40 2020-03-22 17:38:07 +03:00
AlexeyAB d11caf486d Fixed BiFPN and label_smothing for Detection 2020-03-14 03:24:46 +03:00
AlexeyAB 5e54523960 Added loss_scale for Mixed-Precision on Tensor-Cores 2020-03-11 19:47:13 +03:00
AlexeyAB c814d56ec1 Added [net] dynamic_minibatch=1 for increasing mini_batch_size when random=1 is used 2020-03-02 15:27:43 +03:00
AlexeyAB ef979a1fd2 For CPU and GPU structures in the darknet.h have the same size 2020-03-01 14:11:08 +03:00
AlexeyAB 6fb817f68b Accelerated DropBlock on GPU 2020-02-22 01:04:55 +03:00
AlexeyAB 64fb042c63 Averaging Mean/Variance for several mini_batches inside 1 batch. Path to CBN. 2020-02-20 23:45:12 +03:00
Ksenya Ryabinova f441b3025a Added -chart argument 2020-01-31 16:04:34 +03:00
Alexey 61499b27a4
Merge pull request #4773 from jing-vision/master 
Expose crop_image and resize_min as LIB_API
 2020-01-29 19:43:35 +03:00
vinjn 3000c3111f Expose crop_image and resize_min as LIB_API 2020-01-29 22:58:43 +08:00
AlexeyAB 298805cefe Added new [convolutional] activation=normalize_channels_softmax_maxval for ASFF 2020-01-28 03:44:24 +03:00
AlexeyAB 4b59770886 Added max_delta=10 or 1 to the [yolo] and [Gaussian_yolo] layers, to limit delta and reduce the probability of Nan. 2020-01-23 21:49:00 +03:00
AlexeyAB f1643cbf2e Added: weights_normalizion = relu or softmax for [shortcut] layer 2020-01-09 23:53:13 +03:00
AlexeyAB a66bc8d6ff Resizing Detector: random=1 (/1.4 - x1.4), random=3 (/3.0 - x3.0), random=0 (no resizing). Added param: resize_step=32 to the [net] section: use resize_step=128 for 7 subsampling layers. 2020-01-09 19:25:02 +03:00
AlexeyAB 9bd88d7fd7 weighted [shortcut] layer 2020-01-08 02:20:42 +03:00
AlexeyAB b267e34487 multilayer [shortcut] in progress 2020-01-06 23:27:41 +03:00
AlexeyAB 489ea7fdce Minor fix 2020-01-01 21:38:06 +03:00
AlexeyAB 2c08a20b22 Added flag -benchmark_layers for: classifier demo, detector test, detector train 2019-12-28 23:03:30 +03:00
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 af54d95184 Added stretch_sway 2019-12-22 16:00:20 +03:00
AlexeyAB 005714a10c Added [local_avgpool] layer 2019-12-20 20:28:35 +03:00
AlexeyAB e33ecb785e Added param counters_per_class=100,200,... <for each class> to [yolo] and [Gaussian_yolo] to solve class-imbalance-problem 2019-12-17 18:03:42 +03:00
AlexeyAB 1626f9d495 Some fixes 2019-12-16 17:53:58 +03:00
AlexeyAB 5e035565ff Rotate conv-kernel 2019-12-14 18:11:09 +03:00
AlexeyAB a08c872564 Sway conv-kernel 2019-12-14 03:07:01 +03:00
AlexeyAB 642c065c0e Fixed DropBlock [dropout] dropblock_size_abs=7 dropblock_size_rel=0.5 2019-12-13 01:22:03 +03:00
AlexeyAB 1df3ddc7d6 Added DropBlock. Use [dropout] dropblock=1 dropblock_size=0.5 probability=0.1 2019-12-11 13:16:41 +03:00
AlexeyAB 2a873f3448 Added label_smooth_eps=0.1 for [net] layer for Label Smoothing for Classifier 2019-12-08 17:25:01 +03:00
AlexeyAB 318919e1cb Added label_smooth_eps=0.1 for [yolo] and [Gaussian_yolo] layer for Label Smoothing 2019-12-08 16:39:28 +03:00
AlexeyAB c9c745ccf1 Added [convolutional] activation=normalize_channels_softmax 2019-12-06 23:25:12 +03:00
AlexeyAB 68db8efb27 Added Fusion features for ASFF and for BiFPN(EfficientDet) 2019-11-28 20:34:01 +03:00
AlexeyAB 0d98f20be1 You can train with mini_batch=128 (batch=256 subdivisions=2) on GPU 8 GB VRAM + 128 GB CPU-RAM and more. Set in cfg-file: optimized_memory=3 and workspace_size_limit_MB=2000 or 4000 2019-11-26 23:18:04 +03:00
AlexeyAB 48914023da Added init_cpu() function to init CPU just to speedup the 1st detection (if GPU=0) 2019-11-25 18:10:39 +03:00
AlexeyAB 8cb3ee4e79 diounms_sort() fixed 2019-11-23 18:59:29 +03:00
AlexeyAB 4f70fc14e9 Added DIoU and CIoU to [yolo] and [Gaussian_yolo] 2019-11-23 16:42:43 +03:00
AlexeyAB 6e5bdf1282 Bug fix 2019-11-16 18:16:37 +03:00