67 Commits (3abbd858084c9f3634a30307f36a0d23303796b6)

Author SHA1 Message Date
AlexeyAB 8cb3ee4e79 diounms_sort() fixed 6 years ago
AlexeyAB 4f70fc14e9 Added DIoU and CIoU to [yolo] and [Gaussian_yolo] 6 years ago
AlexeyAB 6e5bdf1282 Bug fix 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 ded620ac6b fixed memory deallocation 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 bf8ea4183d Added MISH activation, use activation=mish in [convolutional] layers 6 years ago
AlexeyAB 52e3bb252f Use non-blocking sockets for JSON_server and MJPEG_server 6 years ago
AlexeyAB b3a2495298 Added Gaussian YOLOv3 layer [Gaussian_yolo] 6 years ago
AlexeyAB be5d0d6693 Added assisted_excitation=1 for [convolutional] layer on GPU 6 years ago
AlexeyAB 11b8b2bddf Added antialiasing=1 param for [convolutional]-layer on GPU 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 2fa9792c56 Added [sam] layer 6 years ago
Stefano Sinigardi b9e7cd3d35 introduce functions to detect build features 6 years ago
AlexeyAB 54e2d0b0e8 Added ability to use letter_box resizing in darknet.py sample 6 years ago
AlexeyAB d4402d29c2 Added maxpool_depth= and out_channels= params to [maxpool] 6 years ago
AlexeyAB 88cccfcad4 Added Swish-activation 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 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 1f6f2e1162 Compile fix 6 years ago
AlexeyAB eac26226a7 Added scale_x_y param to [yolo]-layer (for sigmoid). 6 years ago
AlexeyAB 6e13527f06 Added GIoU 6 years ago
AlexeyAB 9c9344a1ff Added flag -letter_box for Detection 6 years ago
AlexeyAB 038289eb7d Some conv-lstm, sgdr and other fixes 6 years ago
Stefano Sinigardi 920b29f15f fixes for ci and included files 6 years ago
AlexeyAB a7e5976c1b Added sequential subdivisions 6 years ago
AlexeyAB 31dc6c8680 Added LSTM sequence detector, and blur data augmentation (for OpenCV only) 6 years ago
AlexeyAB 099b71d1de Removed IplImage completely 6 years ago
AlexeyAB 8c970498a2 Minor fix 6 years ago
AlexeyAB d7a95aefb2 Added flag -show_imgs for Training, to show augmented images with bboxes 6 years ago
AlexeyAB f19d1440cb Moved all OpenCV functions to the image_opencv.cpp/h 6 years ago
AlexeyAB f482590691 Added -map_points flag for mAP calculation for MSCOCO, PascalVOC2007 / 2010-2012, ImageNet 6 years ago
AlexeyAB fbf7a5fa4c Minor fix 6 years ago
AlexeyAB 9dddf82ab6 Compile fix. And minor fixes 6 years ago
Josh Veitch-Michaelis d64693eb77 add SGDR policy 6 years ago
AlexeyAB 84be2e8316 Minor fix 6 years ago
AlexeyAB 4cd10ee547 Another one fix 6 years ago
AlexeyAB d762df531f Compile fix 6 years ago
AlexeyAB b6e15f1656 ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example 6 years ago
AlexeyAB 75f2a3e7cf Added object Detection & Tracking using conv-rnn layer on frames from video 6 years ago
Stefano Sinigardi 00de023601 fully separate C-API from CPP-API 6 years ago
Stefano Sinigardi 6e7c7976d7 move as many defs as possible away from darknet.h 6 years ago
Stefano Sinigardi b3579380dc improve compatibility with c++ compilers, prepare for CMake 6 years ago
AlexeyAB 21c9e9c2ba Minor fix 6 years ago
AlexeyAB 28106c0fd8 Optimized memory allocation for XNOR on CPU 6 years ago