514f4193db
Merge pull request #10959 from alalek:cmake_ocl4dnn
2018-03-07 10:26:14 +00:00
fe97dc67dc
Merge pull request #10962 from alalek:dnn_precomp_hpp
2018-03-02 11:38:16 +00:00
97c1f09961
Merge pull request #10955 from pengli:dnn
2018-03-02 11:35:59 +00:00
a9ebc61f2a
dnn(workaround): switch to CPU target if compiled without OpenCL
2018-03-01 12:12:40 +03:00
1b83bc48a1
dnn: make OpenCL DNN code optional
2018-03-01 12:12:40 +03:00
a838a97092
dnn: fix precomp.hpp usage
2018-02-28 17:06:26 +03:00
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 >
2018-02-28 21:02:41 +08:00
7c855aa3e1
Fixed two issues found by static analysis
2018-02-26 00:16:02 +03:00
608968aa83
Deconvolution ocl fix
...
Signed-off-by: Li Peng <peng.li@intel.com >
2018-02-23 18:31:30 +08:00
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
2018-02-22 21:01:12 +03:00
92e9d4ec3a
Fixed several issues detected by static analysis
2018-02-22 17:11:33 +03:00
5e0f95b948
Merge pull request #9708 from dkurt:tf_face_detector
2018-02-22 12:04:26 +00:00
e7d35d51fa
Fix for opencv face detector ocl test
...
Signed-off-by: Li Peng <peng.li@intel.com >
2018-02-22 23:37:54 +08:00
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 >
2018-02-22 21:17:59 +08:00
eab556e1e0
OpenCV face detection network in TensorFlow
2018-02-21 19:58:24 +03:00
53305d4a7e
Merge pull request #10891 from pengli:dnn
2018-02-20 08:59:07 +00:00
2863f950d6
ReLU6 layer ocl support
...
include relu6 ocl kernel and layer fusion support
Signed-off-by: Li Peng <peng.li@intel.com >
2018-02-20 15:11:09 +08:00
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
2018-02-19 17:25:18 +03:00
0e4eed0ba1
Merge pull request #10867 from dkurt:dnn_fix_ave_pooling_area
2018-02-16 11:17:32 +00:00
c020a7bb67
build: portable integer types
2018-02-15 23:43:02 +03:00
f8d0d6365e
Add a flag to manage average pooling with padding
2018-02-14 16:56:31 +03:00
cff79609c8
Merge pull request #10854 from pengli:dnn
2018-02-14 12:49:53 +00:00
ef70b0baa4
Merge pull request #10865 from dkurt:dnn_inf_engine_getInputsInfo
2018-02-14 12:25:18 +00:00
a66b5e2c13
Add const getInputsInfo
2018-02-14 14:17:44 +03:00
6dfd7e3da2
Merge pull request #10850 from dkurt:dnn_tf_deconv_tests
2018-02-14 10:35:14 +00:00
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 >
2018-02-14 00:04:38 +08:00
00d2f34888
ocl fix for detection_output and prior_box layer
...
Signed-off-by: Li Peng <peng.li@intel.com >
2018-02-13 23:09:14 +08:00
514e6df460
Refactored deep learning layers fusion
2018-02-13 14:35:58 +03:00
a6baedd02c
Fix deconvolution layer. Add batch norm layer with mean-variance normalization from TensorFlow.
2018-02-13 11:00:27 +03:00
66f3c1ae79
Merge pull request #10843 from luzpaz:misc-modules-typos
2018-02-12 13:47:12 +00:00
1ad814a191
fix faster_rcnn sample crashed at PoolingInvoker on Windows7(x64). ( #10724 )
...
* fix faster_rcnn sample crashed at PoolingInvoker operator() of pooling_layer.
* find_odj onmouse bug about find matched point status.
* reverted AutoBuffer back to std::vector
2018-02-12 16:07:56 +03:00
5718d09e39
Misc. modules/ typos
...
Found via `codespell`
2018-02-12 07:09:43 -05:00
b67523550f
dnn : Added an imagesFromBlob method to the dnn module ( #10607 )
...
* Added the imagesFromBlob method to the dnn module.
* Rewritten imagesFromBlob based on first dkurt comments
* Updated code with getPlane()
* Modify comment of imagesFromBlob() in dnn module
* modified comments, removed useless assertions & added OutputArrayOfArray
* replaced tabs with whitespaces & put vectorOfChannels instantiation outside the loop
* Changed pre-commit.sample to pre-commit in .git/hooks/
* Added a test for imagesFromBlob in test_misc.cpp (dnn)
* Changed nbOfImages, robustified test with cv::randu, modified assertion
2018-02-12 14:51:07 +03:00
7fe97376c2
MobileNet-SSD from TensorFlow 1.3 and Inception-V2-SSD using Inference Engine backend
2018-02-09 13:45:45 +03:00
ed94136548
OpenCV face detection network using Inference Engine backend
2018-02-06 17:53:24 +03:00
398ebbac98
Merge pull request #10795 from pengli:dnn
2018-02-06 10:04:29 +00:00
c43498c6ad
check vector emptiness before access it
...
Signed-off-by: Li Peng <peng.li@intel.com >
2018-02-06 22:59:51 +08:00
389fa5d38e
slice layer ocl update
...
Signed-off-by: Li Peng <peng.li@intel.com >
2018-02-06 22:59:47 +08:00
10e1de74d2
Intel Inference Engine deep learning backend ( #10608 )
...
* Intel Inference Engine deep learning backend.
* OpenFace network using Inference Engine backend
2018-02-06 11:57:35 +03:00
e56d6054aa
Do not build protobuf without dnn ( #10689 )
...
* Do not build protobuf if dnn is disabled
* Added BUILD_LIST cmake option to the cache
* Moved protobuf to the top level
* Fixed static build
* Fixed world build
* fixup! Fixed world build
2018-02-01 16:30:23 +03:00
713ec7be45
Merge pull request #10746 from dkurt:dnn_batch_norm_from_nvidia_caffe
2018-02-01 13:22:09 +00:00
42569cfd61
Merge pull request #10748 from dkurt:fix_dnn_slice_layer
2018-02-01 13:21:17 +00:00
9d25bd583f
Merge pull request #10754 from dkurt:dnn_ocl_gemv_min_globalsize
2018-02-01 12:39:27 +00:00
65a6674c6e
ocl4dnnGEMV in case of row_size < 4
2018-02-01 14:06:47 +03:00
9698b93d10
Merge pull request #10717 from pengli:dnn
2018-02-01 10:49:54 +00:00
6aec71d7ee
mvn layer ocl update
...
it fuse ocl kernels to reduce kernel enqueue
Signed-off-by: Li Peng <peng.li@intel.com >
2018-02-01 17:48:12 +08:00
83b16ab7b7
fix extra spaces in build option
...
Signed-off-by: Li Peng <peng.li@intel.com >
2018-02-01 17:46:11 +08:00
54c81cbde4
eltwise layer SUM op update
...
Signed-off-by: Li Peng <peng.li@intel.com >
2018-02-01 17:46:06 +08:00
184862582c
Fix slice layer from TensorFlow
2018-01-31 19:12:37 +03:00
a75840d19c
Merge pull request #10468 from fenrus75:avx512-2
...
* Add a 512 bit codepath to the AVX512 fastConv function
this patch adds a 512 wide codepath to the fastConv() function for
AVX512 use.
The basic idea is to process the first N * 16 elements of the vector
with avx512, and then run the rest of the vector using the traditional
AVX2 codepath.
* dnn: use unaligned AVX512 load (OpenCV aligns data on 32-byte boundary)
* dnn: change "vecsize" condition for AVX512
* dnn: fix indentation
2018-01-31 16:34:12 +03:00
Alexander Alekhin
Alexander Alekhin
Wu Zhiwen
Maksim Shabunin
Li Peng
Vadim Pisarevsky
Dmitry Kurtaev
Sui Libin
luz.paz
Rémi Ratajczak
Arjan van de Ven