dnn: add openvino as one of dnn backend

OpenVINO is a Deep Learning Deployment Toolkit at
https://github.com/openvinotoolkit/openvino, it supports CPU, GPU
and heterogeneous plugins to accelerate deep learning inferencing.

Please refer to https://github.com/openvinotoolkit/openvino/blob/master/build-instruction.md
to build openvino (c library is built at the same time). Please add
option -DENABLE_MKL_DNN=ON for cmake to enable CPU path. The header
files and libraries are installed to /usr/local/deployment_tools/inference_engine/
with default options on my system.

To build FFmpeg with openvion, take my system as an example, run with:
$ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/deployment_tools/inference_engine/lib/intel64/:/usr/local/deployment_tools/inference_engine/external/tbb/lib/
$ ../ffmpeg/configure --enable-libopenvino --extra-cflags=-I/usr/local/deployment_tools/inference_engine/include/ --extra-ldflags=-L/usr/local/deployment_tools/inference_engine/lib/intel64
$ make

Here are the features provided by OpenVINO inference engine:
- support more DNN model formats
It supports TensorFlow, Caffe, ONNX, MXNet and Kaldi by converting them
into OpenVINO format with a python script. And torth model
can be first converted into ONNX and then to OpenVINO format.

see the script at https://github.com/openvinotoolkit/openvino/tree/master/model-optimizer/mo.py
which also does some optimization at model level.

- optimize at inference stage
It optimizes for X86 CPUs with SSE, AVX etc.

It also optimizes based on OpenCL for Intel GPUs.
(only Intel GPU supported becuase Intel OpenCL extension is used for optimization)

Signed-off-by: Guo, Yejun <yejun.guo@intel.com>
Signed-off-by: Pedro Arthur <bygrandao@gmail.com>

1 files changed, 5 insertions, 1 deletions

diff --git a/configure b/configure
index 7495f35faa..cbaddaade9 100755
--- a/configure
+++ b/configure
@@ -253,6 +253,8 @@ External library support:
   --enable-libopenh264     enable H.264 encoding via OpenH264 [no]
   --enable-libopenjpeg     enable JPEG 2000 de/encoding via OpenJPEG [no]
   --enable-libopenmpt      enable decoding tracked files via libopenmpt [no]
+  --enable-libopenvino     enable OpenVINO as a DNN module backend
+                           for DNN based filters like dnn_processing [no]
   --enable-libopus         enable Opus de/encoding via libopus [no]
   --enable-libpulse        enable Pulseaudio input via libpulse [no]
   --enable-librabbitmq     enable RabbitMQ library [no]
@@ -1790,6 +1792,7 @@ EXTERNAL_LIBRARY_LIST="
     libopenh264
     libopenjpeg
     libopenmpt
+    libopenvino
     libopus
     libpulse
     librabbitmq
@@ -2620,7 +2623,7 @@ cbs_mpeg2_select="cbs"
 cbs_vp9_select="cbs"
 dct_select="rdft"
 dirac_parse_select="golomb"
-dnn_suggest="libtensorflow"
+dnn_suggest="libtensorflow libopenvino"
 error_resilience_select="me_cmp"
 faandct_deps="faan"
 faandct_select="fdctdsp"
@@ -6350,6 +6353,7 @@ enabled libopenh264       && require_pkg_config libopenh264 openh264 wels/codec_
 enabled libopenjpeg       && { check_pkg_config libopenjpeg "libopenjp2 >= 2.1.0" openjpeg.h opj_version ||
                                { require_pkg_config libopenjpeg "libopenjp2 >= 2.1.0" openjpeg.h opj_version -DOPJ_STATIC && add_cppflags -DOPJ_STATIC; } }
 enabled libopenmpt        && require_pkg_config libopenmpt "libopenmpt >= 0.2.6557" libopenmpt/libopenmpt.h openmpt_module_create -lstdc++ && append libopenmpt_extralibs "-lstdc++"
+enabled libopenvino       && require libopenvino c_api/ie_c_api.h ie_c_api_version -linference_engine_c_api
 enabled libopus           && {
     enabled libopus_decoder && {
         require_pkg_config libopus opus opus_multistream.h opus_multistream_decoder_create