github
/
darknet
mirror of https://github.com/AlexeyAB/darknet.git
1
0
Fork 0
Code Issues Releases Wiki Activity
1546 Commits
1 Branch
7 Tags
380 MiB
Tag: Branch: Tree: 2a873f3448
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '2a873f3448'
${ noResults }
Commit Graph

203 Commits (2a873f34485c75d44a346f92ba7dcf2e2aa57a15)

Author SHA1 Message Date
AlexeyAB 2a873f3448 Added label_smooth_eps=0.1 for [net] layer for Label Smoothing for Classifier
6 years ago
AlexeyAB 318919e1cb Added label_smooth_eps=0.1 for [yolo] and [Gaussian_yolo] layer for Label Smoothing
6 years ago
AlexeyAB 5d0352f961 Fixed CPU-RAM + GPU-processing bug for Dropout-layer
6 years ago
AlexeyAB e5d464d3d0 Added mosaic=1 data augmentation for Classifier
6 years ago
AlexeyAB 55cfc272fb Fixed bug with [shortcut] layer and SWISH / MISH activations
6 years ago
AlexeyAB 4fcb1b8e42 Addex cutmix=1 and fixed mixup=1 for Classifier
6 years ago
AlexeyAB 68db8efb27 Added Fusion features for ASFF and for BiFPN(EfficientDet)
6 years ago
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
6 years ago
AlexeyAB 48914023da Added init_cpu() function to init CPU just to speedup the 1st detection (if GPU=0)
6 years ago
AlexeyAB 8cb3ee4e79 diounms_sort() fixed
6 years ago
AlexeyAB 4f70fc14e9 Added DIoU and CIoU to [yolo] and [Gaussian_yolo]
6 years ago
AlexeyAB 920de66bfa gaussian_yolo: added uc_normalizer and minor fix for iou_normalizer for GIoU.
6 years ago
AlexeyAB 0cf4c16c9f Added GIoU to [Gaussian_yolo]. Added iou_thresh=0.213 to [Gaussian_yolo].
6 years ago
AlexeyAB e7e85b358c Added delta_yolo_box_accumulate(). Added iou_thresh=0.213 parameter to [yolo] layer IoU(anchor,truth).
6 years ago
AlexeyAB f42923350b Minor fix in batchnorm_layer (side effect in python samples)
6 years ago
AlexeyAB c516b6cb0a Take TopK from obj.data file for Classifier
6 years ago
AlexeyAB 9fe201807e Revert to old Assisted Excitation version.
6 years ago
AlexeyAB d91d59a22f Optimized memory allocation for Detection (inference only), without allocation memory for training
6 years ago
AlexeyAB 0fa9c8f105 Added groups= and groupd_id= params to the [route] layer
6 years ago
AlexeyAB 704bd1138e Fixed params.net in parse_convolutional() and parse_route()
6 years ago
AlexeyAB e345b8793c Fixed ./darknet partial for Anti-aliasing
6 years ago
AlexeyAB 52e3bb252f Use non-blocking sockets for JSON_server and MJPEG_server
6 years ago
AlexeyAB 69b7a19f5b minor fix
6 years ago
AlexeyAB f8c72acd42 Added scale_x_y to [Gaussian_yolo]. Fixed blur=10;
6 years ago
AlexeyAB f18338de26 Fixed [Gaussian_yolo] layer (tested for training and detection)
6 years ago
AlexeyAB 72f6de30b2 another compile fix
6 years ago
AlexeyAB b3a2495298 Added Gaussian YOLOv3 layer [Gaussian_yolo]
6 years ago
AlexeyAB 1c71f00153 Fixed shortcut_layer for antialiasing
6 years ago
AlexeyAB 9c02df864e Fixed assisted_excitation and added also for [shortcut] layer
6 years ago
AlexeyAB be5d0d6693 Added assisted_excitation=1 for [convolutional] layer on GPU
6 years ago
AlexeyAB 9e26472b1a Added antialiasing=1 param for [maxpool]-layer on GPU and CPU
6 years ago
AlexeyAB 11b8b2bddf Added antialiasing=1 param for [convolutional]-layer on GPU
6 years ago
AlexeyAB a4a06c337a Addex stride_x= and stride_y= for [convolutional] layer for MatrixNet
6 years ago
AlexeyAB 660a9b225c compile fix
6 years ago
AlexeyAB 58906ef812 minor fix: Unexpected end of wights-file!
6 years ago
AlexeyAB 4acf924aaf minor fix
6 years ago
AlexeyAB 8d80a65288 Max pool layer can use stride=2 or stride_x=2 stride_y=4 (isn't tested well)
6 years ago
AlexeyAB c1f184249e Added assisted_excitation_forward for training on CPU
6 years ago
AlexeyAB 4bf9b223a2 Fix sam layer
6 years ago
AlexeyAB 2fa9792c56 Added [sam] layer
6 years ago
Alexey 6761e832cc
Bug fix for TridentNet
6 years ago
Stefano Sinigardi ae0306e851 option to build project using cpp compiler if c not working/available
6 years ago
AlexeyAB d4402d29c2 Added maxpool_depth= and out_channels= params to [maxpool]
6 years ago
AlexeyAB c9129c2078 Added letter_box=1 param in [net] section (cfg-file) for keeping aspect ratio during training
6 years ago
AlexeyAB cc41339805 Added [scale_channels] layer for squeeze-and-excitation blocks
6 years ago
AlexeyAB f0582446f2 Fixed Depth-wise (grouped) convolution for CPU and GPU (CUDNN=0/1)
6 years ago
AlexeyAB bd689f91ac Added TridentNet (state-of-art on MS COCO)
6 years ago
AlexeyAB 88ce9dcca6 Added dilation parameter for convolutional, conv_lstm and crnn layers
6 years ago
AlexeyAB 57baf1a487 Added Mixup data augmentation if is used mixup=1
6 years ago
AlexeyAB eac26226a7 Added scale_x_y param to [yolo]-layer (for sigmoid).
6 years ago