github
/
darknet
mirror of https://github.com/AlexeyAB/darknet.git
1
0
Fork 0
Code Issues Releases Wiki Activity
1447 Commits
1 Branch
7 Tags
380 MiB
Tag: Branch: Tree: d91d59a22f
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'd91d59a22f'
${ noResults }
Commit Graph

188 Commits (d91d59a22fea9c266f06c2ae5edb23d38fd83c20)

Author SHA1 Message Date
AlexeyAB d91d59a22f Optimized memory allocation for Detection (inference only), without allocation memory for training
6 years ago
AlexeyAB f18338de26 Fixed [Gaussian_yolo] layer (tested for training and detection)
6 years ago
AlexeyAB b3a2495298 Added Gaussian YOLOv3 layer [Gaussian_yolo]
6 years ago
AlexeyAB e33019e669 Fixed stride_x and stride_y. Fixed AntiAliasing. Minor fixes.
6 years ago
AlexeyAB 102ab710a9 Fixed fuse_conv_batchnorm() for TridentNet
6 years ago
AlexeyAB 2fa9792c56 Added [sam] layer
6 years ago
AlexeyAB 5a6afe96d3 Fixed scale_channels_layer resize
6 years ago
AlexeyAB 54e2d0b0e8 Added ability to use letter_box resizing in darknet.py sample
6 years ago
AlexeyAB cc41339805 Added [scale_channels] layer for squeeze-and-excitation blocks
6 years ago
AlexeyAB ff0dbcbb7d Fix network resizing for resize_conv_lstm_layer()
6 years ago
AlexeyAB 55dcd1bcb8 Compile fix
6 years ago
AlexeyAB 24f7d94ab4 Fixed resizing REORG_OLD layer
6 years ago
AlexeyAB ae3ce1b181 Minor fixes
6 years ago
AlexeyAB 038289eb7d Some conv-lstm, sgdr and other fixes
6 years ago
AlexeyAB 4f72fcc015 Added grouped convolutional (depth-wise convolutional)
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 8c970498a2 Minor fix
6 years ago
AlexeyAB 4e47429d82 Another part of OpenCV C-functions replaced by CPP-functions
6 years ago
AlexeyAB f19d1440cb Moved all OpenCV functions to the image_opencv.cpp/h
6 years ago
Josh Veitch-Michaelis 6cbf08321a get rid of learning_rate_max
6 years ago
Josh Veitch-Michaelis d64693eb77 add SGDR policy
6 years ago
AlexeyAB b3254ed523 Fixed many warnings
6 years ago
AlexeyAB dd0fdfb684 Compile fix
6 years ago
AlexeyAB 75f2a3e7cf Added object Detection & Tracking using conv-rnn layer on frames from video
6 years ago
AlexeyAB e82505d20e Fixed random values
6 years ago
Stefano Sinigardi b3579380dc improve compatibility with c++ compilers, prepare for CMake
6 years ago
AlexeyAB 28106c0fd8 Optimized memory allocation for XNOR on CPU
6 years ago
David Smith ba1f1363c0 fix assorted compile warnings
6 years ago
AlexeyAB 00e992a600 Compile fix
6 years ago
AlexeyAB 5448e07445 Try to fuse conv_xnor+shortcut -> conv_xnor
6 years ago
AlexeyAB 6832290eee Fixed set_batch_network(), when workspace larger for smaller batch
6 years ago
AlexeyAB c50b0e0c8a Minor Python and C API improvement
6 years ago
John Aughey 7e9416aa80 Making a pointer version of network_predict for python.
6 years ago
John Aughey 8726d7b0db Optimizing network_predict_image to resize only if necessary.
6 years ago
AlexeyAB c71354ab2e Added cudaGetLastError() for cudaHostAlloc() to reset last cuda error
6 years ago
AlexeyAB 090d934c0f Minor speedup on CPU
6 years ago
David Smith 5e778cd91e add LSTM layer
6 years ago
Antek S. Baranski 8960fbfb3f gcc on OSX required explicit return value for empty (char *) in detection_to_json
6 years ago
AlexeyAB 81f7fc2c7b Fixed network resize memory allocation
6 years ago
AlexeyAB 0e022d0912 Fixed timer
6 years ago
AlexeyAB bf6b40f4e9 Another CUDA performance improvements
6 years ago
AlexeyAB 5c55137687 Minor fix
6 years ago
jureviciusr 95904cf65a
Bad memory allocation
6 years ago
AlexeyAB 5ee166032a Use detector test...-out result.json -dont_show < train.txt to save results to JSON-file
6 years ago
AlexeyAB e6eba22adb Graceful shutdown closes sockets
6 years ago
AlexeyAB c31a245665 Experimental. Use -json_port 8070 to allow connection to the port:8070 to get json-stream
6 years ago
AlexeyAB 3ff5084590 Added include/darknet.h
6 years ago
AlexeyAB c75fbb5f2e Minor fix
6 years ago
AlexeyAB dc827f4c1c Minor fix for mAP calculation during training
6 years ago