27a6be8763
Fix #12407
7 years ago
2cf34c0fe5
dnn: fix tests build with disabled OpenCL
7 years ago
f10fd64630
dnn: update "guard" inline namespace
...
- differ from 3.4 branch
7 years ago
c7cf8fb35c
Import SSDs from TensorFlow by training config ( #12188 )
...
* Remove TensorFlow and protobuf dependencies from object detection scripts
* Create text graphs for TensorFlow object detection networks from sample
7 years ago
a11d944f51
dnn: Remove a duplicated code snippet for flatten layer
...
Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>
7 years ago
9f1218b00b
Merge pull request #11897 from Jakub-Golinowski:hpx_backend
...
* Add HPX backend for OpenCV implementation
Adds hpx backend for cv::parallel_for_() calls respecting the nstripes chunking parameter. C++ code for the backend is added to modules/core/parallel.cpp. Also, the necessary changes to cmake files are introduced.
Backend can operate in 2 versions (selectable by cmake build option WITH_HPX_STARTSTOP): hpx (runtime always on) and hpx_startstop (start and stop the backend for each cv::parallel_for_() call)
* WIP: Conditionally include hpx_main.hpp to tests in core module
Header hpx_main.hpp is included to both core/perf/perf_main.cpp and core/test/test_main.cpp.
The changes to cmake files for linking hpx library to above mentioned test executalbles are proposed but have issues.
* Add coditional iclusion of hpx_main.hpp to cpp cpu modules
* Remove start/stop version of hpx backend
7 years ago
50bceea038
Include preprocessing nodes to object detection TensorFlow networks ( #12211 )
...
* Include preprocessing nodes to object detection TensorFlow networks
* Enable more fusion
* faster_rcnn_resnet50_coco_2018_01_28 test
7 years ago
c557193b8c
dnn(test): use dnnBackendsAndTargets() param generator
7 years ago
3e6b3a6856
dnn(perf): fix and merge Convolution tests
...
- OpenCL tests didn't run any OpenCL kernels
- use real configuration from existed models (the first 100 cases)
- batch size = 1
7 years ago
ea43e28a37
Replace Slice layer to Crop in Faster-RCNN networks from Caffe
7 years ago
72f422c7dc
java: fix LIST_GET macro
7 years ago
ca51bbb7ff
dnn: fix variance setting bug for PriorBoxLayer
...
- The size of second channel should be size[2] of output tensor,
- The Scalar should be {variance[0], variance[0], variance[0], variance[0]}
for _variance.size() == 1 case.
Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>
7 years ago
4062ef5fcb
Fix lifetime of networks which are loaded from Model Optimizer IRs
7 years ago
3e027df583
Enable more deep learning tests using Intel's Inference Engine backend
7 years ago
7f73b105ca
core: std::string more changes
7 years ago
21f3987d53
python: add support for NMSBoxes
7 years ago
472b71ecef
Merge pull request #12243 from dkurt:dnn_tf_mask_rcnn
...
* Support Mask-RCNN from TensorFlow
* Fix a sample
7 years ago
096366738b
dnn(build): fix CV_Assert() usage
7 years ago
f25450791b
dnn(test): mark unstable OpenCL tests
7 years ago
808c89adc1
Fixed windows build with InferenceEngine
7 years ago
c61bc3a0cb
Update documentation and samples
7 years ago
d2e08a524e
core: repair CV_Assert() messages
...
Multi-argument CV_Assert() is accessible via CV_Assert_N() (with malformed messages).
7 years ago
eff0f9d3f8
Fixed windows build with InferenceEngine
7 years ago
8b197c58e6
openvino: use 2018R3 defines
7 years ago
781721ca50
experimental version++
7 years ago
f056c0f137
UINT8 face detection network using Intel's Inference Engine backend
7 years ago
a56b221559
core: cv::Range() ostream write operator
...
remove from DNN module headers
7 years ago
449696f1e5
Enable reshape-as-shape layer from TensorFlow
7 years ago
be08730cd6
MVN layer using Intel's Inference Engine backend
7 years ago
4fb086d6c3
MobileNet-SSD v1 from TensorFlow with shared convolution weights
7 years ago
8e034053af
Faster-RCNN from TensorFlow on CPU with Intel's Inference Engine backend
7 years ago
7cf52de47e
dnn: modified IE search, R2 compatibility fixed
7 years ago
ed0e79cb61
Add missing parameter to DetectionOutput layer from Intel's Inference Engine
7 years ago
fb1f12021b
Fixed build with latest IE version
7 years ago
b597c87bed
dnn(ocl): avoid memory access violation
7 years ago
9eb79926df
Allow a different input order for Mul+Maximum.
...
Squashed : ReLU operand order tests.
7 years ago
faa6c4e1e1
Faster-RCNN anf RFCN models on CPU using Intel's Inference Engine backend.
...
Enable Torch layers tests with Intel's Inference Engine backend.
7 years ago
dd8701c1a0
dnn(test): skip checks only for unstable tests
...
but execute tested functions in Layer_Test_Halide/Convolution.Accuracy
7 years ago
74cf48b5d7
dnn(test): use Backend/Target enums
...
instead of 'int'
7 years ago
45b5b3c13a
dnn: check layer output for NaN/Inf
7 years ago
cbb1e867e5
More issues found by static analysis
7 years ago
4283309daa
dnn: update tests for OpenVINO models
7 years ago
28e08ae0bd
Add a sample which tests OpenVINO models
7 years ago
e0603bb45f
Fixed several issues found by static analysis tools
7 years ago
ee743afebe
dnn(ocl): don't use getUMat() for long live objects
7 years ago
a4060e15a4
dnn, IE backend: updated to match new interface
7 years ago
c213a3823e
Run entire SSDs from TensorFlow using Intel's Inference Engine
7 years ago
070393dfda
uint8 inputs for deep learning networks
7 years ago
1da46fe6fb
Fixed issues found by static analysis (mostly DBZ)
7 years ago
f0cadaa6e3
enable concat layer fuse for OCL target
...
Signed-off-by: Li Peng <peng.li@intel.com>
7 years ago
Dmitry Kurtaev
Alexander Alekhin
Wu Zhiwen
Jakub Golinowski
Alexander Alekhin
berak
Maksim Shabunin
Suleyman TURKMEN
Triplesalt
Li Peng