|
|
be5d0d6693
|
Added assisted_excitation=1 for [convolutional] layer on GPU
|
2019-09-03 01:35:05 +03:00 |
|
|
|
9e26472b1a
|
Added antialiasing=1 param for [maxpool]-layer on GPU and CPU
|
2019-09-02 15:25:42 +03:00 |
|
|
|
8d80a65288
|
Max pool layer can use stride=2 or stride_x=2 stride_y=4 (isn't tested well)
|
2019-08-27 14:04:39 +03:00 |
|
|
|
d4402d29c2
|
Added maxpool_depth= and out_channels= params to [maxpool]
|
2019-06-30 13:53:11 +03:00 |
|
|
|
7d4143332d
|
Minor output fixes
|
2019-06-29 16:52:49 +03:00 |
|
|
|
f0582446f2
|
Fixed Depth-wise (grouped) convolution for CPU and GPU (CUDNN=0/1)
|
2019-06-15 02:32:57 +03:00 |
|
|
|
b6e15f1656
|
ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example
|
2019-03-18 02:48:52 +03:00 |
|
|
|
e82505d20e
|
Fixed random values
|
2019-02-28 16:55:30 +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 |
|
|
|
58de6b2d3d
|
Minor fix for CHECK_CUDA()
|
2019-02-08 00:48:27 +03:00 |
|
|
|
f38d060137
|
Fixed mAP chart during training for CUDNN=1
|
2018-12-25 02:34:32 +03:00 |
|
|
|
dc7f8a32ae
|
mAP calculation during training, if is used flag -map
|
2018-12-09 18:18:47 +03:00 |
|
|
|
7ee4135910
|
Fix OpenCV compilation. maxpool_layer on GPU uses cuDNN.
|
2018-10-10 13:51:36 +03:00 |
|
|
|
8436251a05
|
maxpool_layer on CPU uses AVX2 and OpenMP
|
2018-08-21 20:44:18 +03:00 |
|
|
|
e6c97a53a7
|
Maxpool fixes
|
2018-08-07 23:19:50 +03:00 |
|
|
|
043289426b
|
max pool layer is fixed
|
2018-08-04 03:11:10 +03:00 |
|
|
|
b8e6e80c6d
|
Added spatial Yolo v3 yolov3-spp.cfg
|
2018-08-03 14:35:03 +03:00 |
|
|
|
8b5344ee2d
|
Added BFLOPs output for network configurations
|
2018-05-14 13:34:40 +03:00 |
|
|
|
62235e9aa3
|
cpu batch norm works
|
2016-11-18 21:51:36 -08:00 |
|
|
|
fc9b867dd9
|
🔥 🔥 :dragonite:
|
2016-11-16 00:15:46 -08:00 |
|
|
|
481b57a96a
|
So I have this new programming paradigm.......
|
2016-09-24 23:12:54 -07:00 |
|
|
|
8f1b4e0962
|
updates and things
|
2016-09-01 16:48:41 -07:00 |
|
|
|
1578ec70d7
|
idk
|
2016-01-18 15:40:14 -08:00 |
|
|
|
8bcdee8658
|
Some bug fixes, random stuff
|
2015-09-01 11:22:03 -07:00 |
|
|
|
d00f0a1ccd
|
Changes to make routing work better
|
2015-07-21 16:09:33 -07:00 |
|
|
|
a08ef29e08
|
NIGHTMARE!!!!
|
2015-07-10 16:38:14 -07:00 |
|
|
|
c39dfd188a
|
Fixed maxpool after change
|
2015-05-11 14:36:45 -07:00 |
|
|
|
516f019ba6
|
route handles input images well....ish
|
2015-05-11 13:46:49 -07:00 |
|
|
|
4f50e29365
|
big change to images
|
2015-04-09 15:18:54 -07:00 |
|
|
|
dcb000b553
|
refactoring and added DARK ZONE
|
2015-03-11 22:20:15 -07:00 |
|
|
|
0f645836f1
|
Detection is back, baby\!
|
2015-02-10 19:41:03 -08:00 |
|
|
|
809f924db2
|
CUDA so fast
|
2015-01-22 16:38:24 -08:00 |
|
|
|
cb1f33c6ae
|
Fixed race condition in server
|
2014-12-08 11:48:57 -08:00 |
|
|
|
d407bffde9
|
checkpoint
|
2014-11-18 13:51:04 -08:00 |
|
|
|
158bb1bee9
|
softmax on gpu
|
2014-10-21 14:49:18 -07:00 |
|
|
|
9b3c7136f3
|
Fixing up maxpool layer
|
2014-10-16 15:17:23 -07:00 |
|
|
|
7add111509
|
maxpool fixed, good on mnist
|
2014-08-09 08:16:37 -07:00 |
|
|
|
d9f1b0b16e
|
probably how maxpool layers should be
|
2014-08-08 12:04:15 -07:00 |
|
|
|
70d622ea54
|
Added batch to col2im, padding option
|
2014-07-13 22:07:51 -07:00 |
|
|
|
2ea63c0e99
|
Better VOC handling and resizing
|
2014-03-12 21:57:34 -07:00 |
|
|
|
f7a17f82eb
|
Convolutional layers working w/ matrices
|
2014-01-28 16:28:42 -08:00 |
|
|
|
b715671988
|
Works well on MNIST
|
2013-12-05 13:17:16 -08:00 |
|
|
|
0d6bb5d44d
|
Working?
|
2013-12-02 16:41:40 -08:00 |
|
|
|
2db9fbef2b
|
Parsing, image loading, lots of stuff
|
2013-11-13 10:50:38 -08:00 |
|
|
|
d7286c2732
|
Loading may or may not work. But probably.
|
2013-11-06 16:09:41 -08:00 |
|
|
|
41bcfac86f
|
First Commit!
|
2013-11-04 11:11:01 -08:00 |
|
