ed710eaa1c
Make Inference Engine R3 as a minimal supported version
6 years ago
ca5976e3d4
Fix IE backend considering future changes.
6 years ago
c918ac298c
Fix IE tests
6 years ago
ac262f5b5d
Clone convolution layer weights only for fusion
6 years ago
ff775b2e54
Remove ASSERT_ANY_THROW checks fpr Myriad plugin and FP32 networks
6 years ago
f0ddf302b2
Move Inference Engine to new API
6 years ago
d0504c95f4
Add a text message for Convolution layer's input channels check
6 years ago
0d117312c9
DNN_TARGET_FPGA using Intel's Inference Engine
7 years ago
b5c54e447c
Extra hyperparameters for Intel's Inference Engine layers
7 years ago
dc3406eed9
Fix Pooling and Convolution layers from Intel's Inference Engine
7 years ago
9d02d42afe
dnn(ocl4dnn): don't use getUMat()
...
especially in CPU only processing
7 years ago
24ab751547
Merge pull request #12565 from dkurt:dnn_non_intel_gpu
...
* Remove isIntel check from deep learning layers
* Remove fp16->fp32 fallbacks where it's not necessary
* Fix Kernel::run to prevent localsize > globalsize
7 years ago
43f889ae1f
Merge pull request #12519 from l-bat:l-bat/onnx_parser
...
Support asymmetric padding in pooling layer (#12519 )
* Add Inception_V1 support in ONNX
* Add asymmetric padding in OpenCL and Inference engine
* Refactoring
7 years ago
d486204a0d
Merge pull request #12264 from dkurt:dnn_remove_forward_method
...
* Remove a forward method in dnn::Layer
* Add a test
* Fix tests
* Mark multiple dnn::Layer::finalize methods as deprecated
* Replace back dnn's inputBlobs to vector of pointers
* Remove Layer::forward_fallback from CV_OCL_RUN scopes
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
3e027df583
Enable more deep learning tests using Intel's Inference Engine backend
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
be08730cd6
MVN layer using Intel's Inference Engine backend
7 years ago
cbb1e867e5
More issues found by static analysis
7 years ago
ee743afebe
dnn(ocl): don't use getUMat() for long live objects
7 years ago
019c2f2115
Enable more deep learning tests
7 years ago
b09a4a98d4
opencv: Use cv::AutoBuffer<>::data()
7 years ago
2c291bc2fb
Enable FastNeuralStyle and OpenFace networks with IE backend
7 years ago
1187a7fa34
Merge pull request #11649 from rockzhan:dnn_dw_prelu
...
dnn: Fix output mismatch when forward dnn model contain [depthwise conv(group=1) + bn + prelu] (#11649 )
* this can make sure [depthwise conv(group=1) + bn + prelu] output not shift
* add TEST to show the output mismatch in [DWconv+Prelu]
* fix typo
* change loading image to init cvMat directly
* build runtime model, without loading external model
* remove whitespace
* change way to create a cvmat
* add bias_term, add target output
* fix [dwconv + prelu] value mismatch when no optimizations
* fix Test error when change output channels
* add parametric test
* change num_output to group value
* change conv code and change test back
7 years ago
b781ac7346
Make Intel's Inference Engine backend is default if no preferable backend is specified.
7 years ago
9ae28415ec
fix doc.
7 years ago
2e9e71ab9e
make ocl4dnn available to run on other platform than Intel GPU
7 years ago
895e10c317
dnn: fixed IE support on Windows
7 years ago
3dd916882a
fp16 ocl support for googlenet
...
Signed-off-by: Li Peng <peng.li@intel.com>
7 years ago
c99c3e761e
Fuse multipliers but not convolution layers weights
7 years ago
66ce8cd7ea
Fix bugs found by valgrind
7 years ago
709cf5d038
OpenCL GPU target for Inference Engine deep learning backend
...
Enable FP16 GPU target for DL Inference Engine backend.
7 years ago
1060c0f439
dnn: apply CV_OVERRIDE/CV_FINAL
7 years ago
6c051a55e5
cmake: don't add include <module>/src directory to avoid conflicts
...
during opencv_world builds
7 years ago
0f01b40dd5
Reset OpenCL kernels if batch size changes
7 years ago
4a6d582f2e
dnn: make OpenCL DNN code optional
7 years ago
1b83bc48a1
dnn: make OpenCL DNN code optional
7 years ago
ef937dd676
ocl4dnn: Fix SAME padding mode for convolve
...
Signed-off-by: Wu, Zhiwen <zhiwen.wu@intel.com>
Signed-off-by: Li Peng <peng.li@intel.com>
7 years ago
608968aa83
Deconvolution ocl fix
...
Signed-off-by: Li Peng <peng.li@intel.com>
7 years ago
c524f669c7
Fallback for "SAME" padMode in ocl convolution and pooling
...
It fixes tensorflow ocl testcase of MobileNetSSD and Inception_v2_SSD
Signed-off-by: Li Peng <peng.li@intel.com>
7 years ago
2863f950d6
ReLU6 layer ocl support
...
include relu6 ocl kernel and layer fusion support
Signed-off-by: Li Peng <peng.li@intel.com>
7 years ago
5992c46606
add fallback case for ocl convolution
...
The ocl convolution doesn't support tensorflow padMode well.
Add fallback check if we meet this situation, it could fix the
tensorflow MobileNet SSD failure.
Signed-off-by: Li Peng <peng.li@intel.com>
7 years ago
514e6df460
Refactored deep learning layers fusion
7 years ago
a6baedd02c
Fix deconvolution layer. Add batch norm layer with mean-variance normalization from TensorFlow.
7 years ago
10e1de74d2
Intel Inference Engine deep learning backend ( #10608 )
...
* Intel Inference Engine deep learning backend.
* OpenFace network using Inference Engine backend
7 years ago
e15928b49e
convolution and tanh layer fusion
...
Signed-off-by: Li Peng <peng.li@intel.com>
7 years ago
2124361ff7
ocl support for Deconvolution layer
...
Signed-off-by: Li Peng <peng.li@intel.com>
7 years ago
1f4fdfd599
Untrainable version of Scale layer from Caffe
7 years ago
64a9e92390
Merge pull request #10466 from dkurt:reduce_umat_try_2
...
* UMat blobs are wrapped
* Replace getUMat and getMat at OpenCLBackendWrapper
7 years ago
7d67d60fb1
cmake(opt): AVX512_SKX
7 years ago
Dmitry Kurtaev
Alexander Alekhin
Lubov Batanina
Maksim Shabunin
Alexander Alekhin
rockzhan
Kuang Fangjun
Tomoaki Teshima
Li Peng
Wu Zhiwen