| .. |
|
.editorconfig
|
Just used spaces for indents instead of Tabs
|
7 years ago |
|
activation_kernels.cu
|
Fixed activation=NORM_CHAN gradient
|
6 years ago |
|
activation_layer.c
|
ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example
|
6 years ago |
|
activation_layer.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
activations.c
|
Fixed activation=NORM_CHAN gradient
|
6 years ago |
|
activations.h
|
Fixed activation=NORM_CHAN gradient
|
6 years ago |
|
art.c
|
Some C OpenCV functions replaced by CPP functions
|
6 years ago |
|
avgpool_layer.c
|
Minor output fixes
|
6 years ago |
|
avgpool_layer.h
|
ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example
|
6 years ago |
|
avgpool_layer_kernels.cu
|
fixes for ci and included files
|
6 years ago |
|
batchnorm_layer.c
|
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 |
|
batchnorm_layer.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
blas.c
|
Added scale_x_y param to [yolo]-layer (for sigmoid).
|
6 years ago |
|
blas.h
|
Stretch conv-kernel
|
6 years ago |
|
blas_kernels.cu
|
Stretch conv-kernel
|
6 years ago |
|
box.c
|
diounms_sort() fixed
|
6 years ago |
|
box.h
|
Minor compile fix and references to DIoU-darknet repo and paper
|
6 years ago |
|
captcha.c
|
Fixed many warnings
|
6 years ago |
|
cifar.c
|
Moved all OpenCV functions to the image_opencv.cpp/h
|
6 years ago |
|
classifier.c
|
Some fixes
|
6 years ago |
|
classifier.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
coco.c
|
Added HTTP POST sender with detected objects, use: ./darknet detector demo ... -http_post_host webhook.site/898bbd9b-0ddd-49cf-b81d-1f56be98d870
|
6 years ago |
|
col2im.c
|
option to build project using cpp compiler if c not working/available
|
6 years ago |
|
col2im.h
|
Added dilation parameter for convolutional, conv_lstm and crnn layers
|
6 years ago |
|
col2im_kernels.cu
|
Added dilation parameter for convolutional, conv_lstm and crnn layers
|
6 years ago |
|
compare.c
|
Fixed many warnings
|
6 years ago |
|
connected_layer.c
|
Compile fix
|
6 years ago |
|
connected_layer.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
conv_lstm_layer.c
|
Sway conv-kernel
|
6 years ago |
|
conv_lstm_layer.h
|
Optimized memory allocation for Detection (inference only), without allocation memory for training
|
6 years ago |
|
convolutional_kernels.cu
|
Stretch conv-kernel
|
6 years ago |
|
convolutional_layer.c
|
Rotate conv-kernel
|
6 years ago |
|
convolutional_layer.h
|
Rotate conv-kernel
|
6 years ago |
|
cost_layer.c
|
Minor fix in cost_layer
|
6 years ago |
|
cost_layer.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
cpu_gemm.c
|
fully separate C-API from CPP-API
|
6 years ago |
|
crnn_layer.c
|
Sway conv-kernel
|
6 years ago |
|
crnn_layer.h
|
Optimized memory allocation for Detection (inference only), without allocation memory for training
|
6 years ago |
|
crop_layer.c
|
ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example
|
6 years ago |
|
crop_layer.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
crop_layer_kernels.cu
|
fixes for ci and included files
|
6 years ago |
|
dark_cuda.c
|
Minor fix
|
6 years ago |
|
dark_cuda.h
|
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 |
|
darknet.c
|
Added flag -letter_box for Detection
|
6 years ago |
|
darkunistd.h
|
Fix compilation for Windows with MinGW
|
6 years ago |
|
data.c
|
Minor fix
|
6 years ago |
|
data.h
|
Added label_smooth_eps=0.1 for [net] layer for Label Smoothing for Classifier
|
6 years ago |
|
deconvolutional_kernels.cu
|
fixes for ci and included files
|
6 years ago |
|
deconvolutional_layer.c
|
move as many defs as possible away from darknet.h
|
6 years ago |
|
deconvolutional_layer.h
|
ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example
|
6 years ago |
|
demo.c
|
Some fixes
|
6 years ago |
|
demo.h
|
Added HTTP POST sender with detected objects, use: ./darknet detector demo ... -http_post_host webhook.site/898bbd9b-0ddd-49cf-b81d-1f56be98d870
|
6 years ago |
|
detection_layer.c
|
ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example
|
6 years ago |
|
detection_layer.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
detector.c
|
Some fixes
|
6 years ago |
|
dice.c
|
Fixed many warnings
|
6 years ago |
|
dropout_layer.c
|
Fixed DropBlock [dropout] dropblock_size_abs=7 dropblock_size_rel=0.5
|
6 years ago |
|
dropout_layer.h
|
Fixed DropBlock [dropout] dropblock_size_abs=7 dropblock_size_rel=0.5
|
6 years ago |
|
dropout_layer_kernels.cu
|
Minor fix
|
6 years ago |
|
gaussian_yolo_layer.c
|
Added DropBlock. Use [dropout] dropblock=1 dropblock_size=0.5 probability=0.1
|
6 years ago |
|
gaussian_yolo_layer.h
|
Fixed [Gaussian_yolo] layer (tested for training and detection)
|
6 years ago |
|
gemm.c
|
Added init_cpu() function to init CPU just to speedup the 1st detection (if GPU=0)
|
6 years ago |
|
gemm.h
|
remove some unnecessary exports
|
6 years ago |
|
getopt.c
|
include some requested modifications
|
6 years ago |
|
getopt.h
|
Fix compilation for Windows with MinGW
|
6 years ago |
|
gettimeofday.c
|
remove some unnecessary exports
|
6 years ago |
|
gettimeofday.h
|
Fix compilation for Windows with MinGW
|
6 years ago |
|
go.c
|
Fixed some memory leaks in secondary functions
|
6 years ago |
|
gru_layer.c
|
ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example
|
6 years ago |
|
gru_layer.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
http_stream.cpp
|
Another one minor fix
|
6 years ago |
|
http_stream.h
|
Another one minor fix
|
6 years ago |
|
httplib.h
|
Added HTTP POST sender with detected objects, use: ./darknet detector demo ... -http_post_host webhook.site/898bbd9b-0ddd-49cf-b81d-1f56be98d870
|
6 years ago |
|
im2col.c
|
Another compile fix
|
6 years ago |
|
im2col.h
|
Added dilation parameter for convolutional, conv_lstm and crnn layers
|
6 years ago |
|
im2col_kernels.cu
|
Added dilation parameter for convolutional, conv_lstm and crnn layers
|
6 years ago |
|
image.c
|
Merge pull request #3501 from shooorf/master
|
6 years ago |
|
image.h
|
Fixed assisted_excitation and added also for [shortcut] layer
|
6 years ago |
|
image_opencv.cpp
|
Some fixes
|
6 years ago |
|
image_opencv.h
|
Some fixes
|
6 years ago |
|
layer.c
|
Some fixes
|
6 years ago |
|
layer.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
list.c
|
Fixed minor bugs and memory leaks
|
6 years ago |
|
list.h
|
Fixed minor bugs and memory leaks
|
6 years ago |
|
local_layer.c
|
move as many defs as possible away from darknet.h
|
6 years ago |
|
local_layer.h
|
ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example
|
6 years ago |
|
lstm_layer.c
|
Minor fix
|
6 years ago |
|
lstm_layer.h
|
Added LSTM sequence detector, and blur data augmentation (for OpenCV only)
|
6 years ago |
|
matrix.c
|
Fixed many warnings
|
6 years ago |
|
matrix.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
maxpool_layer.c
|
Sway conv-kernel
|
6 years ago |
|
maxpool_layer.h
|
Optimized memory allocation for Detection (inference only), without allocation memory for training
|
6 years ago |
|
maxpool_layer_kernels.cu
|
Optimized memory allocation for Detection (inference only), without allocation memory for training
|
6 years ago |
|
network.c
|
Fixed DropBlock bug for Conv-networks. When are used: random=1 and [dropout] dropblock=1
|
6 years ago |
|
network.h
|
Added letter_box=1 param in [net] section (cfg-file) for keeping aspect ratio during training
|
6 years ago |
|
network_kernels.cu
|
Fixed DropBlock bug for Conv-networks. When are used: random=1 and [dropout] dropblock=1
|
6 years ago |
|
nightmare.c
|
Moved all OpenCV functions to the image_opencv.cpp/h
|
6 years ago |
|
normalization_layer.c
|
move as many defs as possible away from darknet.h
|
6 years ago |
|
normalization_layer.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
option_list.c
|
Added GIoU
|
6 years ago |
|
option_list.h
|
Added GIoU
|
6 years ago |
|
parser.c
|
Dropped out items are has compensated
|
6 years ago |
|
parser.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
region_layer.c
|
Merge branch 'master' into master
|
6 years ago |
|
region_layer.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
reorg_layer.c
|
Minor output fixes
|
6 years ago |
|
reorg_layer.h
|
ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example
|
6 years ago |
|
reorg_old_layer.c
|
ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example
|
6 years ago |
|
reorg_old_layer.h
|
ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example
|
6 years ago |
|
rnn.c
|
Moved all OpenCV functions to the image_opencv.cpp/h
|
6 years ago |
|
rnn_layer.c
|
Minor fix
|
6 years ago |
|
rnn_layer.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
rnn_vid.c
|
All OpenCV C-functions replaced by CPP-functions
|
6 years ago |
|
route_layer.c
|
Revert to old Assisted Excitation version.
|
6 years ago |
|
route_layer.h
|
Added groups= and groupd_id= params to the [route] layer
|
6 years ago |
|
sam_layer.c
|
Minor fix
|
6 years ago |
|
sam_layer.h
|
Added [sam] layer
|
6 years ago |
|
scale_channels_layer.c
|
Added mosaic=1 data augmentation for Detector. Fixed blur=. Fixed [scale_channels] for ASFF.
|
6 years ago |
|
scale_channels_layer.h
|
Added Fusion features for ASFF and for BiFPN(EfficientDet)
|
6 years ago |
|
shortcut_layer.c
|
Fixed bug with [shortcut] layer and SWISH / MISH activations
|
6 years ago |
|
shortcut_layer.h
|
Fixed bug with [shortcut] layer and SWISH / MISH activations
|
6 years ago |
|
softmax_layer.c
|
ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example
|
6 years ago |
|
softmax_layer.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
super.c
|
Moved all OpenCV functions to the image_opencv.cpp/h
|
6 years ago |
|
swag.c
|
Moved all OpenCV functions to the image_opencv.cpp/h
|
6 years ago |
|
tag.c
|
Moved all OpenCV functions to the image_opencv.cpp/h
|
6 years ago |
|
tree.c
|
move as many defs as possible away from darknet.h
|
6 years ago |
|
tree.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
upsample_layer.c
|
Minor output fixes
|
6 years ago |
|
upsample_layer.h
|
ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example
|
6 years ago |
|
utils.c
|
Added ./darknet detector valid for KITTI and BDD (were previously MSCOCO and ImageNet)
|
6 years ago |
|
utils.h
|
Minor fix
|
6 years ago |
|
version.h
|
sync cmake version with hardcoded version
|
6 years ago |
|
version.h.in
|
sync cmake version with hardcoded version
|
6 years ago |
|
voxel.c
|
Some C OpenCV functions replaced by CPP functions
|
6 years ago |
|
writing.c
|
Moved all OpenCV functions to the image_opencv.cpp/h
|
6 years ago |
|
yolo.c
|
Added HTTP POST sender with detected objects, use: ./darknet detector demo ... -http_post_host webhook.site/898bbd9b-0ddd-49cf-b81d-1f56be98d870
|
6 years ago |
|
yolo_console_dll.cpp
|
accelerated the c++ example of usage DLL/SO library for images if compiled with OpenCV
|
6 years ago |
|
yolo_layer.c
|
Added DropBlock. Use [dropout] dropblock=1 dropblock_size=0.5 probability=0.1
|
6 years ago |
|
yolo_layer.h
|
improve compatibility with c++ compilers, prepare for CMake
|
6 years ago |
|
yolo_v2_class.cpp
|
Fixed time_step=1 for darknet.so/dll
|
6 years ago |
AlexeyAB
63396082d7