Recherche avancée

Sur d’autres sites (7367)

• dnn/queue : add queue and safe_queue support

  9 novembre 2020, par Xie, Lin

  dnn/queue : add queue and safe_queue support
  Signed-off-by : Xie, Lin <lin.xie@intel.com>
  
  Signed-off-by : Wu Zhiwen <zhiwen.wu@intel.com>
  
  Signed-off-by : Guo, Yejun <yejun.guo@intel.com>
  

  • [DH] libavfilter/dnn/Makefile
  • [DH] libavfilter/dnn/queue.c
  • [DH] libavfilter/dnn/queue.h
  • [DH] libavfilter/dnn/safe_queue.c
  • [DH] libavfilter/dnn/safe_queue.h

• dnn : add openvino as one of dnn backend

  25 mai 2020, par Guo, Yejun

  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>
  

  • [DH] configure
  • [DH] libavfilter/dnn/Makefile
  • [DH] libavfilter/dnn/dnn_backend_openvino.c
  • [DH] libavfilter/dnn/dnn_backend_openvino.h
  • [DH] libavfilter/dnn/dnn_interface.c
  • [DH] libavfilter/dnn_interface.h

• How to distinguish a physical D3D adapter from a virtual adapter used by the Remote Desktop Protocol ?

  31 octobre 2023, par rustak

  I'm currently developing a desktop application(c#/wpf) that decodes video using FFmpeg. I would like to give the user the option to select an adapter for video decoding. I'm using Direct3D method EnumAdapters to list available adapters on current device which works fine. The list of available adapters looks something like this :

  


  Adapter 0
  Description: Intel(R) HD Graphics 630
  Vendor ID:   0x8086
  Device ID:   0x5912
  SubSys ID:   0x86941043
  Revision:    4
  Luid:    46459
  Flags:    None
  Dedicated Video Memory:    128 MB
  Dedicated System Memory:  0 MB
  Shared System Memory:     8092 MB
Adapter 2
  Description: Microsoft Basic Render Driver
  Vendor ID:   0x1414
  Device ID:   0x8C
  SubSys ID:   0x0
  Revision:    0
  Luid:    50158
  Flags:    Software
  Dedicated Video Memory:    0 MB
  Dedicated System Memory:  0 MB
  Shared System Memory:     8092 MB


  


  I have noticed that an additional adapter appears in the list of available adapters when RDP is used. The additional adapter has the same properties as the physical one ; the only difference is in the LUID. The output looks something like this :

  


  Adapter 0
  Description: Intel(R) HD Graphics 630
  Vendor ID:   0x8086
  Device ID:   0x5912
  SubSys ID:   0x86941043
  Revision:    4
  Luid:    46459
  Flags:    None
  Dedicated Video Memory:    128 MB
  Dedicated System Memory:  0 MB
  Shared System Memory:     8092 MB
Adapter 1 // <- additional addapter
  Description: Intel(R) HD Graphics 630 
  Vendor ID:   0x8086
  Device ID:   0x5912
  SubSys ID:   0x86941043
  Revision:    4
  Luid:    1322913970
  Flags:    None
  Dedicated Video Memory:    128 MB
  Dedicated System Memory:  0 MB
  Shared System Memory:     8092 MB
Adapter 2
  Description: Microsoft Basic Render Driver
  Vendor ID:   0x1414
  Device ID:   0x8C
  SubSys ID:   0x0
  Revision:    0
  Luid:    50158
  Flags:    Software
  Dedicated Video Memory:    0 MB
  Dedicated System Memory:  0 MB
  Shared System Memory:     8092 MB


  


  I'm aware that the additional adapter is some kind of virtual adapter used by RDP. I have tried both of them, and it seems that both are suitable for video decoding using FFmpeg.

  


  However, from a UX perspective, it doesn't look or feel right that the combo box contains two adapters with the same name. So my question is : how can I distinguish a physical adapter from a virtual adapter used by the Remote Desktop Protocol ?