|
|
6cbf08321a
|
get rid of learning_rate_max
|
2019-03-19 00:02:01 +00:00 |
|
|
|
53081900e5
|
make option quiet
|
2019-03-18 23:37:37 +00:00 |
|
|
|
d64693eb77
|
add SGDR policy
|
2019-03-18 23:26:04 +00:00 |
|
|
|
75f2a3e7cf
|
Added object Detection & Tracking using conv-rnn layer on frames from video
|
2019-03-02 03:32:24 +03:00 |
|
|
|
b3579380dc
|
improve compatibility with c++ compilers, prepare for CMake
|
2019-02-15 17:27:12 +01:00 |
|
|
|
0543278a5b
|
Partial fixed
|
2019-02-07 00:15:31 +03:00 |
|
|
|
285088adc4
|
Fixed checking CC for enabling Tensor Cores
|
2019-02-06 01:55:42 +03:00 |
|
|
|
12b6e93893
|
CHECK_CUDA is used everywhere
|
2019-02-05 16:18:36 +03:00 |
|
|
|
5446d19576
|
Checks Compute Capability and forcibly disables Tensor Cores for CC < 7.0
|
2019-02-04 23:28:40 +03:00 |
|
|
|
2d747cab2b
|
Minor fixes
|
2019-02-02 03:16:30 +03:00 |
|
|
|
c7309c1fdb
|
Fixed CRNN (RNN based on Convolution) layer
|
2019-02-01 01:30:02 +03:00 |
|
|
|
c71354ab2e
|
Added cudaGetLastError() for cudaHostAlloc() to reset last cuda error
|
2019-01-31 14:22:07 +03:00 |
|
|
|
640bdbc063
|
LSTM, RNN, GRU - use connected_layer that uses cuDNN. Fixed CRNN for conv-layer with cuDNN.
|
2019-01-28 23:50:51 +03:00 |
|
|
|
110b5240a4
|
Fixed LSTM-layer
|
2019-01-28 20:22:14 +03:00 |
|
|
|
00b87281f3
|
Fixed RNN (RNN, GRU, LSTM) with cuDNN (batch-norm)
|
2019-01-27 03:42:44 +03:00 |
|
|
|
9576cd4d89
|
Fixed memory allocation
|
2019-01-26 23:25:09 +03:00 |
|
|
|
5e778cd91e
|
add LSTM layer
|
2019-01-23 22:02:09 -06:00 |
|
|
|
0e022d0912
|
Fixed timer
|
2019-01-18 21:29:06 +03:00 |
|
|
|
bf6b40f4e9
|
Another CUDA performance improvements
|
2019-01-18 16:29:54 +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 |
|
|
|
64e478db07
|
Fix training approach (convolutional layer)
|
2018-12-27 00:31:28 +03:00 |
|
|
|
3969ce30ed
|
Speedup Tensor Cores: 1st layer uses FP32 and pre-allocate GPU memory for Tensor Cores
|
2018-12-11 23:48:58 +03:00 |
|
|
|
7c2f302321
|
Fixed nan issue for training with CUDNN_HALF=1 by using Tensor Cores
|
2018-12-07 22:40:10 +03:00 |
|
|
|
38801979b2
|
Classifier now is working. The file softmax_layer.c was outdated
|
2018-10-06 14:12:02 -05:00 |
|
|
|
24b60456c7
|
Version 0.2.5 - fixed )
|
2018-10-03 23:47:31 +03:00 |
|
|
|
0cf56d1ccf
|
Version 0.2.5 )
|
2018-10-03 23:45:06 +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 |
|
|
|
03e95320a1
|
XNOR coalesced memory access, and avoid bank conflicts
|
2018-09-17 23:39:25 +03:00 |
|
|
|
043289426b
|
max pool layer is fixed
|
2018-08-04 03:11:10 +03:00 |
|
|
|
cfc5fedbb6
|
Just used spaces for indents instead of Tabs
|
2018-07-10 23:29:15 +03:00 |
|
|
|
e066cad1ec
|
Added warning if width or height isn't divisible by 32 for default Yolo-networks
|
2018-06-15 17:25:58 +03:00 |
|
|
|
1c05ebf522
|
Minor fix
|
2018-06-07 03:39:30 +03:00 |
|
|
|
4cf4a89f05
|
Minor fix
|
2018-06-02 00:33:17 +03:00 |
|
|
|
f9ecf6fd3f
|
For Release build - equality check: output of [convolutional] == input of [yolo].
|
2018-05-22 02:37:52 +03:00 |
|
|
|
8b5344ee2d
|
Added BFLOPs output for network configurations
|
2018-05-14 13:34:40 +03:00 |
|
|
|
a2f3644e87
|
Merge pull request #675 from IlyaOvodov/Flip_Fix
Fix of issue #674: parameter "flip" is added to [net] parameters for cla…
|
2018-04-21 23:56:46 +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 |
|
|
|
e18a303d1c
|
Fixed utils.c for short lines.
|
2018-04-21 15:19:58 +03:00 |
|
|
|
6aa140b3c6
|
Disable burn_in for FP16 Tensor Cores
|
2018-04-15 16:57:05 +03:00 |
|
|
|
943f6e874b
|
Added Focal Loss to yolo-layer
|
2018-04-05 23:27:02 +03:00 |
|
|
|
35cc0aaa15
|
Added max_boxes for yolo v3
|
2018-03-30 15:51:54 +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 |
|
|
|
b659d93a4a
|
Changed cmd and sh files. Added new cfg files for old Yolo v2.
|
2018-03-28 23:23:37 +03:00 |
|
|
|
d9ae3dd681
|
Added Yolo v3
|
2018-03-28 02:59:03 +03:00 |
|
|
|
5e448c00f3
|
Added Focal loss. Use focal_loss=1 in the [region] layer in your cfg-file.
alpha = 0.5, gamma = 2
|
2018-03-05 19:59:29 +03:00 |
|
|
|
fe44d3d0f2
|
Fixed reorg_layer. Old reorg can be used as [reorg_old] in the cfg-file.
|
2018-03-03 18:09:46 +03:00 |
|
|
|
a2071e1585
|
Parameter (max) in the cfg-file has an effect on the Yolo-training
|
2018-02-10 01:48:38 +03:00 |
|
|
|
9ff40baa4f
|
Fixes for training Yolo on small objects
|
2018-02-08 01:04:40 +03:00 |
|
|
|
db3a3c54c5
|
Some fixes
|
2018-02-03 15:35:13 +03:00 |
|
