1175 Commits (d6294761be89ce0eeb62d08f7ed93adff5d5d2c2)
 

Author SHA1 Message Date
AlexeyAB fb1ee79576 Minor fix 7 years ago
Alexey 3256967119
Update Readme.md 7 years ago
AlexeyAB a621235783 Switch to Tensor Cores after 2000 iterations. 7 years ago
AlexeyAB 89c6213af0 When is used -map flag for training - calculate mAP for each 4 Epochs. 7 years ago
Alexey ca3bf2fa92
Update Readme.md 7 years ago
Alexey 89cb877689
Update Readme.md 7 years ago
AlexeyAB 7bd6b2f720 Compilation fix 7 years ago
AlexeyAB dc7f8a32ae mAP calculation during training, if is used flag -map 7 years ago
AlexeyAB 742bb7c7ce Compile fix 7 years ago
AlexeyAB 7c2f302321 Fixed nan issue for training with CUDNN_HALF=1 by using Tensor Cores 7 years ago
AlexeyAB 21a4ec9390 Saving loss-chart for each 100 iterations automatically 7 years ago
AlexeyAB 9f7d7c58b5 Minor fixes. Use CUDA 10.0 7 years ago
AlexeyAB 14ed6fcb6e Added -iou_thresh 0.05 flag for ./darknet detector map 7 years ago
AlexeyAB 25f65f6878 Added fast_binarize_weights_gpu() 7 years ago
Alexey 2c5e383c04
Update Readme.md 7 years ago
AlexeyAB 08e8e0c8c2 Minor fix 7 years ago
Alexey 31df5e2735
Update Readme.md 7 years ago
Alexey 7f4b859514
Merge pull request #1816 from vinliao/master 7 years ago
Vincent Liao f81b9209ff fix wrong path 7 years ago
AlexeyAB 31ac46ba22 Fixed bug for 32-bit compilation without GPU. 7 years ago
AlexeyAB d487bdf471 transpose 32x32 on GPU 7 years ago
AlexeyAB 9e2c894a32 Transpose on CPU fix 7 years ago
AlexeyAB e7ad4e6c77 Compile fix 7 years ago
AlexeyAB 00282aa1b8 Fixed maxpool_layer by using cuDNN. 7 years ago
AlexeyAB bdbbb2fd69 Minor fix 7 years ago
AlexeyAB acf1489981 Fixed detector test for 1-channel images (black-white / infrared) 7 years ago
AlexeyAB 3b59178dec Minor fix 7 years ago
AlexeyAB 76706dc4a6 Added yolov3-openimages.cfg and SELU activation 7 years ago
AlexeyAB 2bb44454a5 Minor fix 7 years ago
AlexeyAB 344f8c6d27 Fix building darknet.so on MacOS 7 years ago
AlexeyAB 7762372e5b Compilation fix for OpenCV 3.4.x and Jetson Xavier. 7 years ago
AlexeyAB 7ee4135910 Fix OpenCV compilation. maxpool_layer on GPU uses cuDNN. 7 years ago
Alexey dbc75aec77
Merge pull request #1724 from eon129/master 7 years ago
erick 38801979b2 Classifier now is working. The file softmax_layer.c was outdated 7 years ago
AlexeyAB 24b60456c7 Version 0.2.5 - fixed ) 7 years ago
AlexeyAB 0cf56d1ccf Version 0.2.5 ) 7 years ago
AlexeyAB 6c8642b3eb Added darknet53.cfg and resnext152-32x4d.cfg 7 years ago
AlexeyAB c02216120b Compile fix 7 years ago
AlexeyAB 5cc2a7e20d Added mistakes checking 7 years ago
AlexeyAB 67f33ff5dc Another compile fix 7 years ago
AlexeyAB e92c635f35 Compile fix 7 years ago
AlexeyAB c0e2512af2 Activation improvement, more robust timer. 7 years ago
AlexeyAB e203ab9046 Minor fixes 7 years ago
Alexey 129417ae7f
Update Readme.md 7 years ago
AlexeyAB 7dd97537fb XNOR-net tiny-yolo_xnor.cfg ~2x faster than cuDNN on CUDA (nVidia GPU Maxwell) 7 years ago
AlexeyAB 0224ba3d0d Compile fix 7 years ago
AlexeyAB 03e95320a1 XNOR coalesced memory access, and avoid bank conflicts 7 years ago
Alexey 8e0b265067
Update Readme.md 7 years ago
Alexey b829fee30b
Update Readme.md 7 years ago
AlexeyAB ca43bbdaae Fixed openmp bugs for XNOR 7 years ago