|
b78db932cd
|
fix missing pthread link for downstream users
|
2019-06-12 17:17:40 +02:00 |
|
|
1b7a0dca09
|
revert #3389
|
2019-06-12 16:45:48 +02:00 |
|
|
7701a8cf54
|
Merge branch 'dev/alexey/master' into dev/cenit/fixes
|
2019-06-12 16:44:30 +02:00 |
|
|
e4f6b276e5
|
Merge pull request #3389 from adujardin/master
Fix Ubuntu cmake compilation
|
2019-06-12 12:09:30 +03:00 |
|
|
f1f45b295c
|
Fix Ubuntu cmake compilation (nvcc fatal fopenmp + pthread link uselib)
|
2019-06-12 09:23:57 +02:00 |
|
|
f14c6e2fd9
|
fully restore opencv option which got lost somehow
|
2019-06-10 10:56:23 +02:00 |
|
|
f1b6a6e008
|
fixes for clang/mac
|
2019-06-10 10:33:20 +02:00 |
|
|
378d49e1c3
|
Bug fix for MS COCO json output
|
2019-06-09 18:46:07 +03:00 |
|
|
94c806ffad
|
final fix
|
2019-06-09 03:07:04 +03:00 |
|
|
85b0722af7
|
Another compile fix
|
2019-06-09 01:15:24 +03:00 |
|
|
d1be8ddb33
|
compile fix
|
2019-06-09 00:19:44 +03:00 |
|
|
88ce9dcca6
|
Added dilation parameter for convolutional, conv_lstm and crnn layers
|
2019-06-08 19:41:44 +03:00 |
|
|
12db38ccbf
|
Fixed input_shortcut_gpu() for layers with different numbers of channels
|
2019-06-08 17:42:53 +03:00 |
|
|
3ff27b1cdd
|
Mixup bug fix
|
2019-06-07 14:17:43 +03:00 |
|
|
57baf1a487
|
Added Mixup data augmentation if is used mixup=1
|
2019-06-06 02:55:11 +03:00 |
|
|
2347913ef1
|
Merge pull request #2952 from cenit/dev/cenit/include
[headers] remove many installed files which should remain private, add more fixes for downstream projects
|
2019-06-05 17:37:28 +03:00 |
|
|
ff0dbcbb7d
|
Fix network resizing for resize_conv_lstm_layer()
|
2019-06-05 15:51:03 +03:00 |
|
|
abba310982
|
Minor fix in cost_layer
|
2019-06-05 01:04:16 +03:00 |
|
|
1f6f2e1162
|
Compile fix
|
2019-06-04 21:46:11 +03:00 |
|
|
eac26226a7
|
Added scale_x_y param to [yolo]-layer (for sigmoid).
In previous commit is used GIoU(generalized-iou) from https://github.com/generalized-iou/g-darknet
|
2019-06-04 21:20:59 +03:00 |
|
|
6e13527f06
|
Added GIoU
|
2019-06-01 01:27:18 +03:00 |
|
|
55dcd1bcb8
|
Compile fix
|
2019-05-27 22:10:07 +03:00 |
|
|
24f7d94ab4
|
Fixed resizing REORG_OLD layer
|
2019-05-27 20:55:42 +03:00 |
|
|
2b7fea761f
|
Merge pull request #2923 from willbattel/save-best-map
Save weights with best mAP during training
|
2019-05-27 19:02:49 +03:00 |
|
|
a3d5cc4664
|
Merge branch 'master' into dev/cenit/include
|
2019-05-25 20:27:19 +02:00 |
|
|
3aca0b7166
|
conv-LSTM training speedup
|
2019-05-24 18:48:11 +03:00 |
|
|
9c9344a1ff
|
Added flag -letter_box for Detection
|
2019-05-21 23:47:47 +03:00 |
|
|
034243d1ff
|
Compile fix
|
2019-05-21 18:06:43 +03:00 |
|
|
0109a8dda9
|
Some conv-lstm improvements (inference speedup)
|
2019-05-21 18:01:08 +03:00 |
|
|
b9ea49af25
|
Fixed reorg layer is [reorg3d], old reorg layer is [reorg]
|
2019-05-20 23:58:55 +03:00 |
|
|
ae3ce1b181
|
Minor fixes
|
2019-05-20 22:37:42 +03:00 |
|
|
578d1c0fba
|
[cmake+cuda] improve friendliness of architecture selection
|
2019-05-20 15:17:14 +02:00 |
|
|
0ae5191580
|
Use Tensor Cores for forward-inference in conv-LSTM
|
2019-05-17 02:31:26 +03:00 |
|
|
4b1ecfb419
|
Minor fix
|
2019-05-17 02:17:55 +03:00 |
|
|
335ae91568
|
Minor fix
|
2019-05-14 17:29:18 +03:00 |
|
|
038289eb7d
|
Some conv-lstm, sgdr and other fixes
|
2019-05-14 14:35:22 +03:00 |
|
|
5e242dfe4d
|
remove deprecated json file
|
2019-05-14 11:41:25 +02:00 |
|
|
d853658fcf
|
fix symbols usage
|
2019-05-14 09:46:18 +02:00 |
|
|
920b29f15f
|
fixes for ci and included files
|
2019-05-14 09:23:02 +02:00 |
|
|
d21dc00c6e
|
move towards using only modern cmake - part 3
|
2019-05-13 18:51:31 +02:00 |
|
|
52dabbbd02
|
move towards using only modern cmake - part 2
|
2019-05-13 17:23:02 +02:00 |
|
|
f27f7cc5d0
|
move towards using only modern cmake
|
2019-05-13 00:05:27 +02:00 |
|
|
4f72fcc015
|
Added grouped convolutional (depth-wise convolutional)
|
2019-05-10 16:46:48 +03:00 |
|
|
a7e5976c1b
|
Added sequential subdivisions
|
2019-05-09 22:47:23 +03:00 |
|
|
31dc6c8680
|
Added LSTM sequence detector, and blur data augmentation (for OpenCV only)
|
2019-05-07 16:28:31 +03:00 |
|
|
84ee1f42c6
|
[travis] disable vcpkg's built opencv[cuda] also on cuda-enabled configs, since it causes internal compiler errors. Waiting for updates from vcpkg
|
2019-04-30 19:28:17 +02:00 |
|
|
3a20020264
|
[ci] extend timeout for vcpkg, add all vcpkg configs to allowed failures
|
2019-04-30 16:15:57 +02:00 |
|
|
21e6372a5b
|
[ci] allow vcpkg failures, export CC and CXX symbols, use stb from vcpkg when not testing integrated libs
|
2019-04-30 15:50:27 +02:00 |
|
|
cce34712f6
|
Merge pull request #3029 from adujardin/fix_optflow_zed
Fix cv exception when using both optflow and the ZED
|
2019-04-24 17:29:48 +03:00 |
|
|
42d08fd820
|
Fix cv exception when using both TRACK_OPTFLOW and ZED_STEREO
|
2019-04-24 15:18:41 +02:00 |
|