Wu Zhiwen
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>
6 years ago
Dmitry Kurtaev
4062ef5fcb
Fix lifetime of networks which are loaded from Model Optimizer IRs
6 years ago
Dmitry Kurtaev
3e027df583
Enable more deep learning tests using Intel's Inference Engine backend
6 years ago
Alexander Alekhin
7f73b105ca
core: std::string more changes
6 years ago
berak
21f3987d53
python: add support for NMSBoxes
6 years ago
Dmitry Kurtaev
472b71ecef
Merge pull request #12243 from dkurt:dnn_tf_mask_rcnn
...
* Support Mask-RCNN from TensorFlow
* Fix a sample
6 years ago
Alexander Alekhin
096366738b
dnn(build): fix CV_Assert() usage
6 years ago
Alexander Alekhin
f25450791b
dnn(test): mark unstable OpenCL tests
6 years ago
Maksim Shabunin
808c89adc1
Fixed windows build with InferenceEngine
6 years ago
Suleyman TURKMEN
c61bc3a0cb
Update documentation and samples
6 years ago
Alexander Alekhin
d2e08a524e
core: repair CV_Assert() messages
...
Multi-argument CV_Assert() is accessible via CV_Assert_N() (with malformed messages).
6 years ago
Maksim Shabunin
eff0f9d3f8
Fixed windows build with InferenceEngine
6 years ago
Alexander Alekhin
8b197c58e6
openvino: use 2018R3 defines
6 years ago
Alexander Alekhin
781721ca50
experimental version++
6 years ago
Dmitry Kurtaev
f056c0f137
UINT8 face detection network using Intel's Inference Engine backend
6 years ago
Alexander Alekhin
a56b221559
core: cv::Range() ostream write operator
...
remove from DNN module headers
6 years ago
Dmitry Kurtaev
449696f1e5
Enable reshape-as-shape layer from TensorFlow
6 years ago
Dmitry Kurtaev
be08730cd6
MVN layer using Intel's Inference Engine backend
6 years ago
Dmitry Kurtaev
4fb086d6c3
MobileNet-SSD v1 from TensorFlow with shared convolution weights
6 years ago
Dmitry Kurtaev
8e034053af
Faster-RCNN from TensorFlow on CPU with Intel's Inference Engine backend
6 years ago
Maksim Shabunin
7cf52de47e
dnn: modified IE search, R2 compatibility fixed
6 years ago
Dmitry Kurtaev
ed0e79cb61
Add missing parameter to DetectionOutput layer from Intel's Inference Engine
6 years ago
Maksim Shabunin
fb1f12021b
Fixed build with latest IE version
6 years ago
Alexander Alekhin
b597c87bed
dnn(ocl): avoid memory access violation
6 years ago
Triplesalt
9eb79926df
Allow a different input order for Mul+Maximum.
...
Squashed : ReLU operand order tests.
6 years ago
Dmitry Kurtaev
faa6c4e1e1
Faster-RCNN anf RFCN models on CPU using Intel's Inference Engine backend.
...
Enable Torch layers tests with Intel's Inference Engine backend.
6 years ago
Alexander Alekhin
dd8701c1a0
dnn(test): skip checks only for unstable tests
...
but execute tested functions in Layer_Test_Halide/Convolution.Accuracy
6 years ago
Alexander Alekhin
74cf48b5d7
dnn(test): use Backend/Target enums
...
instead of 'int'
6 years ago
Alexander Alekhin
45b5b3c13a
dnn: check layer output for NaN/Inf
6 years ago
Maksim Shabunin
cbb1e867e5
More issues found by static analysis
6 years ago
Alexander Alekhin
4283309daa
dnn: update tests for OpenVINO models
6 years ago
Dmitry Kurtaev
28e08ae0bd
Add a sample which tests OpenVINO models
6 years ago
Maksim Shabunin
e0603bb45f
Fixed several issues found by static analysis tools
6 years ago
Alexander Alekhin
ee743afebe
dnn(ocl): don't use getUMat() for long live objects
6 years ago
Maksim Shabunin
a4060e15a4
dnn, IE backend: updated to match new interface
6 years ago
Dmitry Kurtaev
c213a3823e
Run entire SSDs from TensorFlow using Intel's Inference Engine
6 years ago
Dmitry Kurtaev
070393dfda
uint8 inputs for deep learning networks
6 years ago
Maksim Shabunin
1da46fe6fb
Fixed issues found by static analysis (mostly DBZ)
6 years ago
Li Peng
f0cadaa6e3
enable concat layer fuse for OCL target
...
Signed-off-by: Li Peng <peng.li@intel.com>
6 years ago
Dmitry Kurtaev
6eb8faea85
Enable TensorFlow networks tests for different backends and targets
6 years ago
Dmitry Kurtaev
de6f0a537d
Fix fully-connected layer in case of number of rows less than 4
6 years ago
Dmitry Kurtaev
dcc1beb1f8
Clip kernel for OpenCL PriorBox layer
6 years ago
Alexander Alekhin
2508f7f971
dnn(ocl): fix wrong usage of stalled .getMat() pointers
...
Temporary object lifetime must be greater than pointer usage.
6 years ago
Dmitry Kurtaev
8b5f061dae
Replace std::vector<char> to std::vector<uchar> for Java bindings of dnn importers
6 years ago
Li Peng
4c5a86828a
Fix gemmlike convolution input reading
...
use vload3 for half3 or float3 input vector reading,
also check read position to see if it exceed input width
Signed-off-by: Li Peng <peng.li@intel.com>
6 years ago
berak
a7b502f04a
dnn: preserve name, type strings for ShuffleLayer
6 years ago
Alexander Alekhin
452fa3011c
dnn(test): drop CV_ENUM for DNNBackend / DNNTarget
6 years ago
Dmitry Kurtaev
d57e5406f0
Add readNet* functions which parse models from byte arrays
6 years ago
Alexander Alekhin
b6255ab9e7
dnn(ocl4dnn): fix args for 'max_pool_forward' kernel
7 years ago
Alexander Alekhin
e2b5d11290
dnn: allow to use external protobuf
...
"custom layers" feature will not work properly in these builds.
7 years ago