Commit Graph

88 Commits

Author SHA1 Message Date
75f2a3e7cf Added object Detection & Tracking using conv-rnn layer on frames from video 2019-03-02 03:32:24 +03:00
6e7c7976d7 move as many defs as possible away from darknet.h 2019-02-18 11:33:25 +01:00
b3579380dc improve compatibility with c++ compilers, prepare for CMake 2019-02-15 17:27:12 +01:00
c50b0e0c8a Minor Python and C API improvement 2019-02-06 14:38:12 +03:00
7e9416aa80 Making a pointer version of network_predict for python.
The python binding requires the network struct to be passed
as a pointer to it rather than a struct copy.
2019-02-05 11:35:45 -06:00
a590609b1b Compile fix 2019-01-12 13:50:51 +03:00
3ff5084590 Added include/darknet.h 2019-01-06 23:51:38 +03:00
527578744b Minor fix 2018-12-29 22:56:38 +03:00
dc827f4c1c Minor fix for mAP calculation during training 2018-12-27 00:30:05 +03:00
f38d060137 Fixed mAP chart during training for CUDNN=1 2018-12-25 02:34:32 +03:00
7bd6b2f720 Compilation fix 2018-12-09 18:28:51 +03:00
7c2f302321 Fixed nan issue for training with CUDNN_HALF=1 by using Tensor Cores 2018-12-07 22:40:10 +03:00
7dd97537fb XNOR-net tiny-yolo_xnor.cfg ~2x faster than cuDNN on CUDA (nVidia GPU Maxwell) 2018-09-22 02:01:14 +03:00
0a326e7afe XNOR-net on CPU AVX2 2018-08-08 02:45:47 +03:00
db550bd804 Expose optimize_picture() in DLL 2018-06-27 11:56:21 +08:00
83b2ae66e1 Expose YOLODLL_API layer* get_network_layer(network* net, int i); 2018-06-10 09:45:39 +08:00
132251d723 You can do: fuse_conv_batchnorm(network net) from DLL/SO-library 2018-06-04 00:37:08 +03:00
89c11f83ed Fixed darknet.py - uses batch=1 by default 2018-05-16 15:05:46 +03:00
9207607a59 Fix issue #674: parameter "flip" is added to [net] parameters for classifier and detector
flip=0 switches flip augmentation off.
Default is flip=1 which is consistent with a previous behaviour.
2018-04-21 23:22:16 +03:00
fc496d52bf Yolo can be used from Python 2.x using /darknet.py on Linux or darknet/x64/darknet.py on Windows 2018-04-12 22:32:57 +03:00
1b2c70f82a Detection is accelerated by 7 percent (fused conv and batch_norm layers) 2018-04-03 16:42:00 +03:00
9fbd1936eb small_object can be used in [net] in cfg-file for objects 1x1 pix on FullHD image 2018-03-30 14:32:41 +03:00
0039fd2678 Yolo v3 using SO/DLL library 2018-03-29 20:47:17 +03:00
d9ae3dd681 Added Yolo v3 2018-03-28 02:59:03 +03:00
880cf187d8 Fixed multi-GPU training for Tensor Cores 2018-03-09 19:44:46 +03:00
aeb15b3cb9 Detection and Tracking work well 2018-01-08 01:47:50 +03:00
b714004546 Fixed bug with: net->seen 2017-10-26 18:04:26 +03:00
ae74d0ef31 Fixed fread() for net->seen 2017-10-21 23:56:07 +03:00
a6cbaeecde Added support DLL (dynamic link library) - yolo_cpp_dll.dll 2017-03-15 23:39:18 +03:00
352ae7e65b ADAM 2016-10-26 08:35:44 -07:00
d8adaf8ea6 tree stuff 2016-10-21 13:16:43 -07:00
73f7aacf35 better multigpu 2016-09-20 11:34:49 -07:00
5c067dc447 good chance I didn't break anything 2016-09-12 13:55:20 -07:00
6b38dcdce0 adding new tiny-yolo 2016-09-07 22:27:56 -07:00
8f1b4e0962 updates and things 2016-09-01 16:48:41 -07:00
aebe937710 what do you even write here? 2016-08-11 11:54:24 -07:00
845ab75796 some more stuff 2016-08-05 15:27:07 -07:00
e7072b8489 checkpoint 2016-06-20 13:18:59 -07:00
13209df7bb art, cudnn 2016-05-13 11:59:43 -07:00
054e2b1954 not sure 2016-05-12 13:36:11 -07:00
c7b10ceadb so much need to commit 2016-05-06 16:25:16 -07:00
16d06ec0db stuff 2016-02-29 13:54:12 -08:00
913d355ec1 lots of stuff 2016-01-28 12:30:38 -08:00
db0397cfaa shortcut layers, msr networks 2015-12-14 11:57:10 -08:00
0305fb4d99 Some changes 2015-11-26 11:48:01 -08:00
8c5364f585 New YOLO 2015-11-09 11:31:39 -08:00
8fd18add6e CVPR Experiments 2015-11-03 19:23:42 -08:00
c40cdeb402 lots of comparator stuff 2015-10-09 12:50:43 -07:00
393dc8eb6f stable 2015-09-09 12:48:40 -07:00
b5936b499a lots of stuff 2015-09-04 17:52:44 -07:00