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

1877 Commits (a553899505414ea6e8d8cb4ee7bde2a78f8f6faa)
 

Author SHA1 Message Date
AlexeyAB 0ee9c8668f Fixed CBN
5 years ago
Alexey 1de03f948c
Merge pull request #4896 from tiagoshibata/opencv4-AlexeyAB
5 years ago
Alexey a67a3d7880
Merge pull request #4762 from adujardin/zedsdk_3_support
5 years ago
AlexeyAB 64fb042c63 Averaging Mean/Variance for several mini_batches inside 1 batch. Path to CBN.
5 years ago
Tiago Koji Castro Shibata 187918f564 Enable C++11 for OpenCV 4
5 years ago
Tiago Koji Castro Shibata bc7209ab31 Fix compilation with latest OpenCV
5 years ago
AlexeyAB f106f07d0d Minor fix
5 years ago
AlexeyAB 8d87df2388 Minor fix
5 years ago
AlexeyAB 653eceb1a7 Compile fix
5 years ago
AlexeyAB d2f26776bb Weights initialization is improved for [shortcut], and inference of [shortcut] is accelerated by normalizing during initialization.
5 years ago
AlexeyAB e910f4a839 NAN in batchnorm_layer is fixed
5 years ago
AlexeyAB 8dc4833e7f Minor fix
5 years ago
AlexeyAB d51d89053a Added error message
5 years ago
Ksenya Ryabinova f441b3025a Added -chart argument
5 years ago
AlexeyAB 2223a4b51a minor fix
5 years ago
AlexeyAB 7bf83018e4 Fixed Fully connected layers: [connected], [rnn], [gru], [lstm]
5 years ago
Alexey 61499b27a4
Merge pull request #4773 from jing-vision/master
5 years ago
vinjn 3000c3111f Expose crop_image and resize_min as LIB_API
5 years ago
AlexeyAB 2862b28dc7 Training bug fixed.
5 years ago
AlexeyAB 3be369d47b Minor fix
5 years ago
AlexeyAB 298805cefe Added new [convolutional] activation=normalize_channels_softmax_maxval for ASFF
5 years ago
Aymeric DUJARDIN a9f634dd18 Adding support for ZED SDK 3.0 (with 2.8 support maintained)
5 years ago
AlexeyAB 4b59770886 Added max_delta=10 or 1 to the [yolo] and [Gaussian_yolo] layers, to limit delta and reduce the probability of Nan.
5 years ago
AlexeyAB f0fd61b829 Minor fix
5 years ago
AlexeyAB ecf1aeb7e7 -benchmark_layers for backward too (for training)
5 years ago
AlexeyAB 56cd545267 Improved inference FPS for [shortcut] layer
5 years ago
AlexeyAB 57264d1372 Fixed resnet152_trident.cfg
5 years ago
AlexeyAB 678ba01335 Minor fix for shortcut multilayer if it doesn't use weights
5 years ago
AlexeyAB 2a9fe045f3 Minor fix
5 years ago
AlexeyAB 3902712947 minor fix
5 years ago
AlexeyAB d88a9eb0d9 Tensor Cores fix
5 years ago
AlexeyAB 14172d42b6 Fixed weights_normalizion=softmax for [shortcut] layer
5 years ago
AlexeyAB 04f78ddf72 Fixed bugs from PR
5 years ago
AlexeyAB 04a050cf07 Fixed [shortcut] resize for swish/mish
5 years ago
AlexeyAB 2247c5fcd7 minor fixes
5 years ago
Alexey a19e18df3e
Merge pull request #3815 from cyyever/master
5 years ago
AlexeyAB 67c91e6bef Minor fix
5 years ago
AlexeyAB 619e39fc71 Fixed bug in [shortcut]
5 years ago
cyy 300406e26a fix macro
5 years ago
cyy 8bd01dd8da
Merge branch 'master' into master
5 years ago
AlexeyAB 2116cba1ed [shortcut] uses activation=linear by default
5 years ago
AlexeyAB f1643cbf2e Added: weights_normalizion = relu or softmax for [shortcut] layer
5 years ago
AlexeyAB 0dbd0e1ef0 compile fix
5 years ago
AlexeyAB 283333b52f Added network resizing for SAM layer
5 years ago
AlexeyAB a66bc8d6ff Resizing Detector: random=1 (/1.4 - x1.4), random=3 (/3.0 - x3.0), random=0 (no resizing). Added param: resize_step=32 to the [net] section: use resize_step=128 for 7 subsampling layers.
5 years ago
AlexeyAB 6878ecc2e2 Minor fix
5 years ago
AlexeyAB cfac917b75 Minor performance improvement
5 years ago
cyy 9d2e6f9a23 fix compiling errors
5 years ago
AlexeyAB 40006b6e9b Compile fix
5 years ago
AlexeyAB 9bd88d7fd7 weighted [shortcut] layer
5 years ago