Alexander Alekhin
6eba1a4d44
dnn: auto network dump through parameter
5 years ago
Alexander Alekhin
fa4871b013
dnn: don't require setInput in .dump()
5 years ago
Dmitry Kurtaev
005f38fb45
Fix dnn::ResizeLayer to manage varying input shapes
5 years ago
Alexander Alekhin
a4bd7506a5
core: CV_STRONG_ALIGNMENT macro
...
Should be used to guard unsafe type casts of pointers
5 years ago
Liubov Batanina
4a19ac5aca
Move instruction
5 years ago
Liubov Batanina
d9474648f0
Fix diff
5 years ago
Liubov Batanina
0687cffe21
Support logSoftMax
5 years ago
Liubov Batanina
a3ae69893c
Extend nGraph Deconvolution layer support
5 years ago
Liubov Batanina
55b03dcaba
Refactoring
5 years ago
Alexander Alekhin
6670e6b0bb
dnn: prevent unloading of InferenceEngine plugins
5 years ago
Liubov Batanina
7e5b5390ba
Fix comments
5 years ago
Alexander Alekhin
b21a861c5b
dnn(test): adjust test tolerance for MYRIAD
5 years ago
Liubov Batanina
35c24480ae
Fix axis
5 years ago
Liubov Batanina
832ca0734d
Refactoring
5 years ago
Liubov Batanina
fada959b4b
Fix comment
5 years ago
Liubov Batanina
c6936f5a77
Support lrn with SPATIAL_NRM
5 years ago
Liubov Batanina
d825caf18e
Update check params
5 years ago
Liubov Batanina
97455f1593
Remove useless condition
5 years ago
Liubov Batanina
08ba63da02
Add global pool flags
5 years ago
ashishiva3@gmail.com
f29bc22005
Convolutional padding parsing modified
5 years ago
Julien
886220b9be
Merge pull request #16273 from JulienMaille:wrapper_available_target
...
* add a wrapper for getAvailableTargets
* add java wrapper on Target enum
5 years ago
Alexander Alekhin
55d54b56bf
dnn(onnx): handle unaligned access in ONNX importer
5 years ago
Julien Maille
a696348ec5
FIX: disable dnn cuda input_shortcut on _half for CC<5.3
5 years ago
Yashas Samaga B L
d85e67d3ec
Merge pull request #16063 from YashasSamaga:cuda4dnn-shortcut-unequal
...
support eltwise sum with different number of input channels in CUDA backend
* add shortcut primitive
* add offsets in shortcut kernel
* skip tests involving more than two inputs
* remove redundant modulus operation
* support multiple inputs
* remove whole file indentation
* skip acc in0 trunc test if weighted
* use shortcut iff channels are unequal
5 years ago
Dmitry Kurtaev
8b9e8a805d
MVN support through nGraph
5 years ago
Alexander Alekhin
2638c5e9b7
dnn: dump layer's blobs on getMemoryShapes() error
5 years ago
Julien
ced3df73da
Fix: rsqrt(float) was improperly put in the ifdef for half
5 years ago
YashasSamaga
fd369a5004
fix and optimize ROIPooling
5 years ago
Dmitry Kurtaev
d92a883de1
Different way to reset Myriad device
5 years ago
Julien
4e2ef8c8f5
Merge pull request #16218 from JulienMaille:cuda-dnn-for-older-gpus
...
Enable cuda4dnn on hardware without support for __half
* Enable cuda4dnn on hardware without support for half (ie. compute capability < 5.3)
Update CMakeLists.txt
Lowered minimum CC to 3.0
* UPD: added ifdef on new copy kernel
* added fp16 support detection at runtime
* Clarified #if condition on atomicAdd definition
* More explicit CMake error message
5 years ago
Dmitry Kurtaev
7c741f54fa
Wrap custom OpenCV layers to try-catch
5 years ago
Dmitry Kurtaev
0d896af8ec
Fix uninitialized value
5 years ago
Liubov Batanina
be86338a79
Enable acrossSpatial normalizeL2 on Myriad
5 years ago
Dmitry Kurtaev
c1c84d2fd1
ONNX graphs simplifier
5 years ago
Dmitry Kurtaev
8f1e36f7c1
Disable some tests for Myriad target of nGraph
...
Add lightweight IE hardware targets checks
nGraph: Concat with paddings
Enable more nGraph tests
Restore FP32->FP16 for GPU plugin of IE
try to fix buildbot
Use lightweight IE targets check only starts from R4
5 years ago
Liubov Batanina
9ed372b297
Update get memory shapes
5 years ago
Liubov Batanina
4625337179
Add docs reduce mean
5 years ago
Liubov Batanina
e9e3af0aaa
Add global pool by axis test
5 years ago
Liubov Batanina
a33d50084d
Add global_pooling_dim flags
5 years ago
Liubov Batanina
7eba3a7c96
Add pack description
5 years ago
Dmitry Kurtaev
f954f0830c
Sort text TensorFlow graphs
5 years ago
YashasSamaga
48eecafc89
simplify code to help MSVC 19.10 and lower
5 years ago
Dmitry Kurtaev
76cfa65d55
AddV2 from TensorFlow
5 years ago
YashasSamaga
01f97f150c
perfor fp conversions on GPU
5 years ago
YashasSamaga
17a35587e1
use optimized cuDNN path for conv + bias + relu
5 years ago
Liubov Batanina
752653c70b
Update global pooling
5 years ago
Brian Wignall
f9c514b391
Fix spelling typos
...
backport commit 659ffaddb4
5 years ago
Brian Wignall
659ffaddb4
Fix spelling typos
5 years ago
Liubov Batanina
cf477f7e9f
Fix global axis
5 years ago
Liubov Batanina
543e0302d3
Support global pooling by axis
5 years ago