github
/
darknet
mirror of https://github.com/AlexeyAB/darknet.git
1
0
Fork 0
Code Issues Releases Wiki Activity
1877 Commits
1 Branch
7 Tags
380 MiB
Tag: Branch: Tree: a553899505
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'a553899505'
${ noResults }
Commit Graph

67 Commits (a553899505414ea6e8d8cb4ee7bde2a78f8f6faa)

Author SHA1 Message Date
Stefano Sinigardi b3579380dc improve compatibility with c++ compilers, prepare for CMake
6 years ago
AlexeyAB 3ff5084590 Added include/darknet.h
6 years ago
AlexeyAB 64e478db07 Fix training approach (convolutional layer)
6 years ago
AlexeyAB 7c2f302321 Fixed nan issue for training with CUDNN_HALF=1 by using Tensor Cores
7 years ago
AlexeyAB 7ee4135910 Fix OpenCV compilation. maxpool_layer on GPU uses cuDNN.
7 years ago
erick 38801979b2 Classifier now is working. The file softmax_layer.c was outdated
7 years ago
AlexeyAB 03e95320a1 XNOR coalesced memory access, and avoid bank conflicts
7 years ago
AlexeyAB c0e01fd63c Test for XNOR-conv on CUDA
7 years ago
AlexeyAB 007878393f Temporary Slow implementation of XNOR on CUDA (shared_memory)
7 years ago
AlexeyAB c4a9e3422e Temporary implementation of XNOR on CUDA
7 years ago
AlexeyAB 9753b72aeb temp fix, don't use it
7 years ago
AlexeyAB f606b5456e XNOR-net 21 FPS on CPU yolov2-tiny.cfg
7 years ago
AlexeyAB a9fef1bd66 Bug fixes. Tested im2col_cpu_custom_transpose - bad way.
7 years ago
AlexeyAB 0a326e7afe XNOR-net on CPU AVX2
7 years ago
AlexeyAB 8b5344ee2d Added BFLOPs output for network configurations
7 years ago
AlexeyAB 9bae70b225 Accelerated by another 5% using FP16/32 Batch-norm for Tensor Cores.
7 years ago
AlexeyAB eb9c88ef73 Fixed bug in Tensor Cores V100 (1. Desc in Batch norm, 2. Manually selected algo).
7 years ago
AlexeyAB 9fbd1936eb small_object can be used in [net] in cfg-file for objects 1x1 pix on FullHD image
7 years ago
AlexeyAB b659d93a4a Changed cmd and sh files. Added new cfg files for old Yolo v2.
7 years ago
AlexeyAB d9ae3dd681 Added Yolo v3
7 years ago
AlexeyAB 537d135feb Improve training performance - batch-norm using cuDNN.
7 years ago
AlexeyAB 5e448c00f3 Added Focal loss. Use focal_loss=1 in the [region] layer in your cfg-file.
7 years ago
AlexeyAB fe44d3d0f2 Fixed reorg_layer. Old reorg can be used as [reorg_old] in the cfg-file.
7 years ago
AlexeyAB cad4d1618f Added support for Tensor Cores CC >= 7.0 (V100). For FP16/32 (mixed precision) define CUDNN_HALF should be used.
7 years ago
AlexeyAB dda993f3dd Use half_float16 instead of float32 if defined both CUDNN and CUDNN_HALF. Use Tensor Cores.
7 years ago
AlexeyAB 9ff40baa4f Fixes for training Yolo on small objects
7 years ago
AlexeyAB 9ac78d8b84 Fine tuning, use stopbackward=1 in the cfg-file in that layer where Backward should be stopped.
7 years ago
Joseph Redmon 0d6b107ed2 hey
9 years ago
Joseph Redmon 4b60afcc64 stuff and things
9 years ago
Joseph Redmon 252e3b1916 :charizard: :charizard: :charizard:
9 years ago
Joseph Redmon c7a700dc22 new font strategy
9 years ago
Joseph Redmon 352ae7e65b ADAM
9 years ago
Joseph Redmon d8adaf8ea6 tree stuff
9 years ago
Joseph Redmon 481b57a96a So I have this new programming paradigm.......
9 years ago
Joseph Redmon 5c067dc447 good chance I didn't break anything
9 years ago
Joseph Redmon 8f1b4e0962 updates and things
9 years ago
Joseph Redmon 845ab75796 some more stuff
9 years ago
Joseph Redmon 9361292c42 updates
9 years ago
Joseph Redmon afb8b4f98b CVPR prep
9 years ago
Joseph Redmon 8a767f1066 stuff for carlo
9 years ago
Joseph Redmon 4625a16ffd tactics
9 years ago
Joseph Redmon ec3d050a76 hope i didn't break anything
9 years ago
Joseph Redmon 13209df7bb art, cudnn
9 years ago
Joseph Redmon c7b10ceadb so much need to commit
9 years ago
Joseph Redmon cff59ba135 go updates
9 years ago
Joseph Redmon d1965bdb96 Go
9 years ago
Joseph Redmon 16d06ec0db stuff
9 years ago
Joseph Redmon c604f2d994 ...
9 years ago
Joseph Redmon 913d355ec1 lots of stuff
9 years ago
Joseph Redmon 1578ec70d7 idk
9 years ago