OrgLion-ML
/
darknet
mirror of https://github.com/AlexeyAB/darknet.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity
1,133 Commits 1 Branch 7 Tags 361 MiB
Commit Graph

1133 Commits

Author SHA1 Message Date
AlexeyAB cccc90b340 CMakeLists.txt temporary fix for CUDA 2019-02-22 18:47:10 +03:00
AlexeyAB d1ee38ca05 Use both $(cudnn) and $(CUDNN) environment variables in darknet.vcxproj & yolo_cpp_dll.vcxproj 2019-02-22 18:08:24 +03:00
Alexey 7872cbf198
Update Readme.md 2019-02-22 17:53:27 +03:00
Alexey 954feac226
Update Readme.md 2019-02-22 17:03:36 +03:00
Alexey 14650fb649
Merge pull request #2412 from cenit/dev/cenit/yoloAlexey_cmake 
add CMakeLists.txt and necessary modules
 2019-02-22 16:41:18 +03:00
Stefano Sinigardi da9c0be371 [CMakeLists.txt] add a compatibility include directive to workaround some regressions in enable_language(CUDA) 2019-02-22 14:22:10 +01:00
Stefano Sinigardi d8291858d5 [FindCUDNN] add another hint for newly suggested ENV variable 2019-02-22 09:14:41 +01:00
AlexeyAB 9e084c588a Fixed wrong cast for XNOR-net 2019-02-22 03:39:27 +03:00
AlexeyAB ac5b9552cf OpenCV definition for yolo_console_dll.vcxproj 2019-02-22 03:27:38 +03:00
Alexey b5336c1e0f
Merge pull request #2394 from cenit/dev/cenit/yoloAlexey_v2 
improve compatibility with c++ compilers
 2019-02-22 03:00:29 +03:00
Stefano Sinigardi 20757e217f restore manual control of CUDA while keeping default enabled 2019-02-20 15:29:56 +01:00
Stefano Sinigardi 839f7c0f04 remove some unnecessary exports 2019-02-20 11:51:17 +01:00
Stefano Sinigardi f950085a45 automatically detect CUDA and use it, without any possible manual intervention 2019-02-20 11:42:53 +01:00
Stefano Sinigardi 9c64f885a8 improve CMake default behaviour to use integrated libs 2019-02-19 23:11:40 +01:00
Stefano Sinigardi 00de023601 fully separate C-API from CPP-API 2019-02-19 15:57:18 +01:00
AlexeyAB 5e850c2489 Minor fixes 2019-02-18 18:12:05 +03:00
Stefano Sinigardi 6e7c7976d7 move as many defs as possible away from darknet.h 2019-02-18 11:33:25 +01:00
Stefano Sinigardi cbc1c6d8ca improve CMake alternative, add instructions in README 2019-02-18 09:34:20 +01:00
Stefano Sinigardi 4ae778defc include some requested modifications 2019-02-18 00:09:08 +01:00
Stefano Sinigardi b3579380dc improve compatibility with c++ compilers, prepare for CMake 2019-02-15 17:27:12 +01:00
Stefano Sinigardi c88ae98289 add CMakeLists.txt and necessary modules 2019-02-15 17:19:35 +01:00
Alexey 3e2ef94130
Update Readme.md 2019-02-14 01:06:35 +03:00
AlexeyAB 21c9e9c2ba Minor fix 2019-02-13 16:54:22 +03:00
AlexeyAB 3d9c8530a0 Use Tensor Cores only when (channels % 8 == 0) and (filters % 8 == 0) 2019-02-12 23:13:25 +03:00
AlexeyAB 28106c0fd8 Optimized memory allocation for XNOR on CPU 2019-02-12 22:16:11 +03:00
AlexeyAB 449fcfed75 Fix for GCC on ARM 32/64-bit 2019-02-12 22:15:35 +03:00
AlexeyAB 00e992a600 Compile fix 2019-02-12 02:12:46 +03:00
AlexeyAB 5448e07445 Try to fuse conv_xnor+shortcut -> conv_xnor 2019-02-12 02:05:15 +03:00
AlexeyAB 9e138adf09 more accurate time measurements in Demo 2019-02-12 02:01:10 +03:00
AlexeyAB 7dff7365cb Minor demo fix 2019-02-11 23:16:30 +03:00
AlexeyAB f154d2070a Fixed RNN (LSTM, RNN, CRNN, GRU) for CUDNN_HALF=1 2019-02-08 00:51:41 +03:00
AlexeyAB 9e07605bc5 get_connected_workspace_size() and get_convolutional_workspace_size() 2019-02-08 00:51:20 +03:00
AlexeyAB 6832290eee Fixed set_batch_network(), when workspace larger for smaller batch 2019-02-08 00:49:51 +03:00
AlexeyAB 58de6b2d3d Minor fix for CHECK_CUDA() 2019-02-08 00:48:27 +03:00
AlexeyAB 98103552fb Minor fix 2019-02-07 18:19:34 +03:00
AlexeyAB 6c28da5def Draw top5 accuracy on the Loss-chart for training Classifier 2019-02-07 18:05:58 +03:00
AlexeyAB fc663f6efe Another minor fix 2019-02-07 15:02:36 +03:00
AlexeyAB 9bb7455a0e Minor fix 2019-02-07 14:47:43 +03:00
Alexey c999f53e9d
Merge pull request #2359 from aughey/master 
Change for py  code
 2019-02-07 14:43:01 +03:00
AlexeyAB 7587d47c46 Partial fixed 2019-02-06 18:54:38 -06:00
AlexeyAB 0543278a5b Partial fixed 2019-02-07 00:15:31 +03:00
John Aughey 022ce74fe9 Rewriting darknet_video.py to reuse darknet.py as a lib 2019-02-06 14:59:23 -06:00
Alexey 64b217aa86
Update Readme.md 2019-02-06 14:51:02 +03:00
AlexeyAB c50b0e0c8a Minor Python and C API improvement 2019-02-06 14:38:12 +03:00
Alexey b76f1c0006
Merge pull request #2352 from aughey/master 
Changes to better support python bindings
 2019-02-06 14:23:26 +03:00
AlexeyAB 285088adc4 Fixed checking CC for enabling Tensor Cores 2019-02-06 01:55:42 +03:00
AlexeyAB e1bbeb8367 CUDNN_HALF and CC 7.5 by default in darknet.sln 2019-02-05 11:59:58 -06:00
AlexeyAB fa1415e3c2 CUDNN_HALF and CC 7.5 by default in darknet.sln 2019-02-05 20:43:07 +03:00
John Aughey c00d3c92db Making a fast API compatible way to copy image data. 
This can improve on the python array_to_image function
where we already have an allocated image struct and simply
need to copy the data into the correct format/shape without
reallocating.

Aside: I think array_to_image does two frees because the pointer
data_as returns doesn't own the memory that is ultimately freed
in free_image.
 2019-02-05 11:40:21 -06:00
John Aughey 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