Liubov Batanina
ad63d24dba
Merge pull request #18096 from l-bat:update_onnx_importer
...
* Added ReduceSum to ONNX importer
* Fix comments
* Fix Mul
4 years ago
Liubov Batanina
339b963e6b
Fix MatMul and Add axes
4 years ago
Yashas Samaga B L
2171cae8ff
Merge pull request #17976 from YashasSamaga:dnn-fusion-tests-fix-ocl
...
dnn: add exhaustive fusion tests, enable more eltwise fusions
* add eltwise fusion tests, enable more eltwise fusions
* merge weighted eltwise tests with eltwise tests
4 years ago
Liubov Batanina
f3cebb3e1b
Merge pull request #18077 from l-bat:reduce_sum
...
* Supported ReduceSum op
* Skip test
4 years ago
YashasSamaga
f0149cdae2
fix compile-time errors, disable unsupported tests
4 years ago
Liubov Batanina
6226ea0085
Fix bug in ONNX Gather op
4 years ago
Vadim Pisarevsky
1537ecd931
* added depth-wise convolution; gives ~20-30% performance improvement in MobileSSD networks
...
* hopefully, eliminated compile warnings, errors, as well as failure in one test
* * fixed a few typos
* decreased buffer size in some cases
* added more optimal im2row branch in the case of 1x1 convolutions
* tuned fastConv to reduce the number of passes over arrays
backport of commit 77b01deb80
4 years ago
Ilya Churaev
5fd3d36fe8
Removed get_output_as_single_output_node method
4 years ago
danielenricocahall
8457e471fd
add relu as activation option in darknet
...
add relu option
add relu as activation option in darknet
simplify the setParams if-else ladder
add relu as activation option in darknet
correct activation_param type
format
format
add relu as activation option in darknet
spacing
spacing
add relu as activation option in darknet
4 years ago
Ilya Churaev
246de2b7f5
Replaced copy_with_new_args to clone_with_new_inputs
4 years ago
Ilya Churaev
e8c26963e9
Fixed removing is_parameter, is_constant, is_output
4 years ago
Liubov Batanina
d695208727
Merge pull request #17967 from l-bat:non_const_weights_for_conv
...
* Supported convolution with non-const weights
* Fix opencl blobs
* Update tests
4 years ago
Alexander Alekhin
1c8ee3f957
Merge pull request #17885 from alalek:dnn_ocl_slice_update
...
DNN: OpenCL/slice update
* dnn(ocl/slice): make slice kernel VTune friendly
- more unique names
- inline code of copy functions
* dnn(ocl/slice): prefer to spawn more work groups
- even in case with 1D copy
- perf improvement up to 2x of kernel time (due to changed configuration 128x1x1 => 128x32x1)
* dnn(ocl/slice): cache kernel exec info
4 years ago
Dmitry Kurtaev
cf8f65d806
Do not use size_t for nGraph layers
4 years ago
YashasSamaga
a3106d424b
add MVNOp
4 years ago
Vadim Pisarevsky
77b01deb80
Merge pull request #17858 from vpisarev:dnn_depthwise_conv
...
* added depth-wise convolution; gives ~20-30% performance improvement in MobileSSD networks
* hopefully, eliminated compile warnings, errors, as well as failure in one test
* * fixed a few typos
* decreased buffer size in some cases
* added more optimal im2row branch in the case of 1x1 convolutions
* tuned fastConv to reduce the number of passes over arrays
4 years ago
Yashas Samaga B L
f53f491cd2
Merge pull request #17939 from YashasSamaga:cuda4dnn-fix-eltwise-fusion
...
* fix eltwise fusion segfault, more eltwise fusions, fix power fusion
* add assertion
4 years ago
kadi soheib
6bed5c181b
Corrected Comment as requested by reviewer.
4 years ago
YashasSamaga
ae293f27cf
add DetectionOutputOp
4 years ago
Sinitsina
0ac2f0e04c
mish_functor_update
4 years ago
Giles Payne
4cf76754d3
Add Objective-C/Swift wrappers for opencv_contrib modules
4 years ago
Ilya Churaev
aaf65bb3af
Fixed removing is_parameter, is_constant, is_output
4 years ago
Ilya Churaev
0291dd3ef8
Replaced copy_with_new_args to clone_with_new_inputs
4 years ago
Liubov Batanina
a35d4f9029
Support Gather for variable inputs
4 years ago
Ilya Churaev
a46ca98c57
Revert "Fixed removing is_parameter, is_constant, is_output"
4 years ago
Ilya Churaev
33db2ac928
Fixed removing is_parameter, is_constant, is_output
4 years ago
Alexander Alekhin
971cc3354b
dnn(test): adjust tests for OpenVINO 2020.4 (4.x branch)
4 years ago
Alexander Alekhin
81e027eef7
dnn: fix OpenCL implementation of Slice layer
4 years ago
Alexander Alekhin
1c371d07b5
dnn(test): adjust tests for OpenVINO 2020.4
4 years ago
Alexander Alekhin
55e8549839
dnn: eliminate IE deprecation warning
4 years ago
Alexander Alekhin
435b6df989
dnn: use OpenVINO 2020.4 defines
...
original commit: 2813aa7eb9
4 years ago
Dmitry Kurtaev
cc584760d3
Fix TensorFlow->ONNX imports
4 years ago
YashasSamaga
1949056423
improved diagnostics for build issues
4 years ago
YashasSamaga
ead1dcf308
error if cuda4dnn depends are not resolved
4 years ago
Alexander Alekhin
5cb8619eca
dnn(ie): enable KEY_CPU_THREADS_NUM for Windows
4 years ago
YashasSamaga
37e2afb8f6
fix concat fusion for cuda4dnn
4 years ago
Yashas Samaga B L
d0e6d2438c
Merge pull request #17363 from YashasSamaga:cuda4dnn-eltwise-fusion2
...
cuda4dnn(conv): fuse eltwise with convolutions
* fuse eltwise with convolutions
* manually rebase to avoid bad git merge
4 years ago
Alexander Alekhin
d5713c657b
dnn(slice): disable buggy OCV/OCL implementation
4 years ago
Alexander Alekhin
99c4b76a6d
dnn(test): add YOLOv4-tiny tests
4 years ago
Ilya Churaev
d69a7a3bbf
Fixed header paths for some nGraph ops
...
* Added dependency on IE version
backport of commit: 992c908b56
4 years ago
Ilya Churaev
992c908b56
Merge pull request #17756 from ilyachur:feature/ichuraev/fix_ngraph_headers
...
* Fixed header paths for some nGraph ops
* Added dependency on IE version
4 years ago
YashasSamaga
cbdaa93e54
reduce slice, concat to copy; enable more concat fusions
4 years ago
YashasSamaga
b7eec216e9
generalize axis for concat fusion
4 years ago
YashasSamaga
4988e131fd
transfer output blobs in background
4 years ago
kadi soheib
17c430da88
Updated comment.
4 years ago
kadi soheib
96a501c08b
Adding comment from source code to documentation.
4 years ago
Liubov Batanina
65dbbf712d
Merge pull request #17733 from l-bat:tiny_yolov4
...
* Supported yolov4-tiny
* Added comments
4 years ago
YashasSamaga
62a63021c7
add cuDNN 8 support
4 years ago
cyy
206c843f36
Merge pull request #17499 from cyyever:fix_CUDA11
...
Fix cuda11
* use cudnn_version.h to detect version when it is available
* remove nppi from CUDA11
* use ocv_list_filterout
* dnn(cuda): temporary disable CUDNN 8.0
4 years ago
Ilya Lavrenov
e58ce89b10
Conditional compilation for IR v7 support
...
backported commit 86905754e4
4 years ago