OrgLion-ML
/
darknet
mirror of https://github.com/AlexeyAB/darknet.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
1,695 Commits 1 Branch 7 Tags 361 MiB
Commit Graph

1695 Commits

Author SHA1 Message Date
Wastage 8c13ca1619
Class_id Garbage Value Check 
Added exception handling when Class_Id is garbage value (like negative)
 2020-03-11 15:33:59 +09:00
AlexeyAB a567a806a6 Set cur_iteration = 0; initially 2020-03-11 01:46:10 +03:00
AlexeyAB 6c4886485d Minor speedup of DropBlock (training) 2020-03-10 17:00:35 +03:00
Alexey c993a4bbe3
Merge pull request #4994 from Tclack88/master 
Update classifier.c
 2020-03-09 21:37:05 +03:00
Tclack88 992306b031
Update classifier.c 
declaring variables not allowed within `for loops` until C99. additionally. declaring int i multiple times within the same definition try_classifier  isn't necessary
 2020-03-09 09:45:50 -07:00
AlexeyAB b56e8d11cf Minor fix 2020-03-06 13:46:17 +03:00
Alexey b2fc7b624c
Merge pull request #4955 from Evert-Arends/master 
Update readme
 2020-03-03 21:56:05 +03:00
Evert Arends 4f95c78f54
Update readme 
Updated the readme to prevent reading mistakes and hours of pointless searching
 2020-03-03 19:27:53 +01:00
Alexey 60e0950c74
Update Readme.md 2020-03-02 18:15:47 +03:00
AlexeyAB 81290b0737 Fixed label_smoothing for Detector 2020-03-02 17:36:08 +03:00
AlexeyAB c814d56ec1 Added [net] dynamic_minibatch=1 for increasing mini_batch_size when random=1 is used 2020-03-02 15:27:43 +03:00
AlexeyAB df9e602819 Fixed bug in MJPEG_PORT - clear socket after closing the connection 2020-03-01 18:02:54 +03:00
AlexeyAB ef979a1fd2 For CPU and GPU structures in the darknet.h have the same size 2020-03-01 14:11:08 +03:00
AlexeyAB 10a586140c Minor fix. Fixed forward MISH on CPU 2020-02-27 18:03:58 +03:00
AlexeyAB f6baa62c9b Accelerated BiFPN back-propagation 2020-02-24 20:48:49 +03:00
AlexeyAB 3cb9125b95 Another one fix of gradient for BiFPN 2020-02-24 20:01:53 +03:00
AlexeyAB cfa40fe890 Fixed gradient for BiFPN 2020-02-24 19:49:20 +03:00
AlexeyAB c83c21459b Fixed gradient for ASFF 2020-02-24 19:14:44 +03:00
Alexey 7567ba0dd4
Merge pull request #4907 from adujardin/zedsdk_3_support 
Shorter sl::Mat cast function (Related to #4762)
 2020-02-24 14:54:49 +03:00
Aymeric DUJARDIN 876eafd3b1 Shorter sl::Mat cast function 2020-02-24 10:21:57 +01:00
AlexeyAB 26366d6535 DropBlock is fixed 2020-02-23 01:27:43 +03:00
AlexeyAB 6fb817f68b Accelerated DropBlock on GPU 2020-02-22 01:04:55 +03:00
AlexeyAB 0ee9c8668f Fixed CBN 2020-02-21 19:22:30 +03:00
Alexey 1de03f948c
Merge pull request #4896 from tiagoshibata/opencv4-AlexeyAB 
Support building with OpenCV 4
 2020-02-21 02:24:47 +03:00
Alexey a67a3d7880
Merge pull request #4762 from adujardin/zedsdk_3_support 
Adding support for ZED SDK 3.0 (with 2.8 support maintained)
 2020-02-21 02:24:34 +03:00
AlexeyAB 64fb042c63 Averaging Mean/Variance for several mini_batches inside 1 batch. Path to CBN. 2020-02-20 23:45:12 +03:00
Tiago Koji Castro Shibata 187918f564 Enable C++11 for OpenCV 4 2020-02-20 10:02:14 -08:00
Tiago Koji Castro Shibata bc7209ab31 Fix compilation with latest OpenCV 
C APIs were removed and must be replaced with C++ calls
 2020-02-20 10:02:10 -08:00
AlexeyAB f106f07d0d Minor fix 2020-02-20 19:22:59 +03:00
AlexeyAB 8d87df2388 Minor fix 2020-02-20 19:03:54 +03:00
AlexeyAB 653eceb1a7 Compile fix 2020-02-17 04:21:20 +03:00
AlexeyAB d2f26776bb Weights initialization is improved for [shortcut], and inference of [shortcut] is accelerated by normalizing during initialization. 2020-02-17 04:12:27 +03:00
AlexeyAB e910f4a839 NAN in batchnorm_layer is fixed 2020-02-16 18:23:49 +03:00
AlexeyAB 8dc4833e7f Minor fix 2020-02-14 18:28:10 +03:00
AlexeyAB d51d89053a Added error message 2020-02-02 14:27:39 +03:00
AlexeyAB 2223a4b51a minor fix 2020-01-30 19:26:13 +03:00
AlexeyAB 7bf83018e4 Fixed Fully connected layers: [connected], [rnn], [gru], [lstm] 2020-01-30 17:00:34 +03:00
Alexey 61499b27a4
Merge pull request #4773 from jing-vision/master 
Expose crop_image and resize_min as LIB_API
 2020-01-29 19:43:35 +03:00
vinjn 3000c3111f Expose crop_image and resize_min as LIB_API 2020-01-29 22:58:43 +08:00
AlexeyAB 2862b28dc7 Training bug fixed. 2020-01-29 15:57:10 +03:00
AlexeyAB 3be369d47b Minor fix 2020-01-28 18:30:48 +03:00
AlexeyAB 298805cefe Added new [convolutional] activation=normalize_channels_softmax_maxval for ASFF 2020-01-28 03:44:24 +03:00
Aymeric DUJARDIN a9f634dd18 Adding support for ZED SDK 3.0 (with 2.8 support maintained) 2020-01-27 19:12:08 +01:00
AlexeyAB 4b59770886 Added max_delta=10 or 1 to the [yolo] and [Gaussian_yolo] layers, to limit delta and reduce the probability of Nan. 2020-01-23 21:49:00 +03:00
AlexeyAB f0fd61b829 Minor fix 2020-01-23 21:07:42 +03:00
AlexeyAB ecf1aeb7e7 -benchmark_layers for backward too (for training) 2020-01-23 16:51:29 +03:00
AlexeyAB 56cd545267 Improved inference FPS for [shortcut] layer 2020-01-22 17:19:02 +03:00
AlexeyAB 57264d1372 Fixed resnet152_trident.cfg 2020-01-22 16:49:19 +03:00
AlexeyAB 678ba01335 Minor fix for shortcut multilayer if it doesn't use weights 2020-01-22 15:47:48 +03:00
AlexeyAB 2a9fe045f3 Minor fix 2020-01-16 20:32:15 +03:00