Alexander Alekhin
|
ee90a6cbde
|
dnn(test): update error tolerance for RCNN/RFCN tests
|
7 years ago |
Tomoaki Teshima
|
a40354d16f
|
use correct name for NVIDIA
* remove NVidia and Nvidia
* replace Cuda with CUDA
* keep the letters for API
|
7 years ago |
Dmitry Kurtaev
|
b92c3182ab
|
Blank and L2-normalization layers from Intel's Inference Engine
|
7 years ago |
Dmitry Kurtaev
|
512632e574
|
Parse repeated values of ConvolutionParameter
|
7 years ago |
Dmitry Kurtaev
|
4ef6c91583
|
Fix multiple inputs for models from Intel's Model Optimizer
|
7 years ago |
Dmitry Kurtaev
|
1ba72ca0d3
|
Fuse tf.nn.l2_normalize layer
|
7 years ago |
Dmitry Kurtaev
|
709cf5d038
|
OpenCL GPU target for Inference Engine deep learning backend
Enable FP16 GPU target for DL Inference Engine backend.
|
7 years ago |
Vladislav Sovrasov
|
0d9c63744e
|
Add CPU default extensions loading in IE dnn backend (#11252)
* Add CPU default extensions loading in IE dnn backend
* Load cpu_extensions for the future Intel's Inference Engine
|
7 years ago |
Dmitry Kurtaev
|
ef1aaf12c9
|
Fix Proposal deep learning layer
|
7 years ago |
Dmitry Kurtaev
|
8d8f3bca6f
|
Update links to OpenCV's face detection network
|
7 years ago |
Dmitry Kurtaev
|
818a91f4f7
|
Update Torch testdata
|
7 years ago |
Dmitry Kurtaev
|
598039c0ed
|
Fix embedded Torch's nn.ConcatTable
|
7 years ago |
Alexander Alekhin
|
6c8014e7d1
|
cmake: disable checks for protobuf generated files
|
7 years ago |
Alexander Alekhin
|
1060c0f439
|
dnn: apply CV_OVERRIDE/CV_FINAL
|
7 years ago |
Dmitry Kurtaev
|
e039fc3a63
|
Replace protobuf's ReleaseLast to RemoveLast to deallocate memory.
Change an order of PriorBox layer operations.
|
7 years ago |
Dmitry Kurtaev
|
2f3a9ba1d4
|
Update OpenCVDetectInferenceEngine.cmake
|
7 years ago |
Dmitry Kurtaev
|
7972f47ed4
|
Load networks from intermediate representation of Intel's Deep learning deployment toolkit.
|
7 years ago |
Dmitry Kurtaev
|
e8fe6ee4e3
|
Fix prior box generation in case of squared proposals.
Fix batch norm in training phase.
|
7 years ago |
Alexander Alekhin
|
6c051a55e5
|
cmake: don't add include <module>/src directory to avoid conflicts
during opencv_world builds
|
7 years ago |
Dmitry Kurtaev
|
069f9add80
|
Fix an issue https://github.com/opencv/opencv/issues/11102
|
7 years ago |
Dmitry Kurtaev
|
538fd42363
|
Add test for Scalar arguments at CommandLineParser
|
7 years ago |
Dmitry Kurtaev
|
ab20d2a3fc
|
Update assertions in batch norm layer
|
7 years ago |
Dmitry Kurtaev
|
69a8f110b6
|
Fuse subgraphs from Keras
|
7 years ago |
Dmitry Kurtaev
|
9457bf10ab
|
Fuse batch normalization and flatten TensorFlow subgraphs in runtime
|
7 years ago |
Dmitry Kurtaev
|
0f01b40dd5
|
Reset OpenCL kernels if batch size changes
|
7 years ago |
Dmitry Kurtaev
|
0a61ebdd66
|
Replace DNNTarget and DNNBackend in tests
|
7 years ago |
Dmitry Kurtaev
|
e1c3237532
|
Parametric OpenCL deep learning tests
|
7 years ago |
Dmitry Kurtaev
|
f2440ceae6
|
Update tutorials. A new cv::dnn::readNet function
|
7 years ago |
Dmitry Kurtaev
|
e8d94ea87c
|
Unite deep learning object detection samples
|
7 years ago |
Alexander Alekhin
|
e79be78ef4
|
dnn(workaround): switch to CPU target if compiled without OpenCL
|
7 years ago |
Alexander Alekhin
|
4a6d582f2e
|
dnn: make OpenCL DNN code optional
|
7 years ago |
Alexander Alekhin
|
a9ebc61f2a
|
dnn(workaround): switch to CPU target if compiled without OpenCL
|
7 years ago |
Alexander Alekhin
|
1b83bc48a1
|
dnn: make OpenCL DNN code optional
|
7 years ago |
Alexander Alekhin
|
a838a97092
|
dnn: fix precomp.hpp usage
|
7 years ago |
Wu Zhiwen
|
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 |
Maksim Shabunin
|
0f1e193193
|
Fixed two issues found by static analysis
|
7 years ago |
Maksim Shabunin
|
7c855aa3e1
|
Fixed two issues found by static analysis
|
7 years ago |
Alexander Alekhin
|
4a74408eee
|
experimental version++
|
7 years ago |
Li Peng
|
608968aa83
|
Deconvolution ocl fix
Signed-off-by: Li Peng <peng.li@intel.com>
|
7 years ago |
Li, Peng
|
5caf6244a3
|
Merge pull request #10922 from pengli:dnn
* ave pooling ocl fix
support the padded area control in ave pooling
Signed-off-by: Li Peng <peng.li@intel.com>
* warning fix: ununitialized field
|
7 years ago |
Maksim Shabunin
|
92e9d4ec3a
|
Fixed several issues detected by static analysis
|
7 years ago |
Li Peng
|
e7d35d51fa
|
Fix for opencv face detector ocl test
Signed-off-by: Li Peng <peng.li@intel.com>
|
7 years ago |
Li Peng
|
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 |
Dmitry Kurtaev
|
eab556e1e0
|
OpenCV face detection network in TensorFlow
|
7 years ago |
Li Peng
|
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 |
Dmitry Kurtaev
|
8b4871a28d
|
Use only absolute prior boxes explicit sizes. Remove scales attributes. (#10874)
* Use only absolute prior boxes explicit sizes. Remove scales attributes.
* Simplified PriorBox layer forward pass
|
7 years ago |
Dmitry Kurtaev
|
34ba32ff27
|
Fix DNN flatten test
|
7 years ago |
Alexander Alekhin
|
c020a7bb67
|
build: portable integer types
|
7 years ago |
Dmitry Kurtaev
|
f8d0d6365e
|
Add a flag to manage average pooling with padding
|
7 years ago |
Dmitry Kurtaev
|
a66b5e2c13
|
Add const getInputsInfo
|
7 years ago |