-
I have created a WinML extension for OpenVX, to use to WinML functionality from with an OpenVX graph - https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/tree/master/amd_openvx_extensi…
-
Do you consider support Vega M in the future ROCm release? I think there are NUC users besides me want to setup AMD GPU support. Thanks!
-
````
kiriti@simon:~/ISV/trafficVision$ ./main.py --video media/demo.mp4
('Loaded', 'yoloOpenVX')
OK: loaded 22 kernels from libvx_nn.so
OK: OpenVX using GPU device#0 (gfx900) [OpenCL 1.2 ] [SvmCa…
-
we have for v1.1: MIVisionX_WinML-installer.msi
-
In the NNEF Model Zoo, some of the models get input as nhwc while some models get input as nchw format. I assume that models that are converted from tensorflow is in nhwc format. Can you make this uni…
-
Model conversion fails with the latest MIVisionX Master Install
-
[ 0%] Running C++ protocol buffer compiler on proto/caffe.proto
Scanning dependencies of target runcl
Scanning dependencies of target openvx
Scanning dependencies of target nnef2openvx
[ 1%] Bui…
-
OpenVX.lib, vx_opencv.lib, vx_winml.lib files should be installed under $(MIVisionX_ROOT)\bin in order to be linked to certain apps.
-
* RPP and RALI - PR #267 adds the hardcoded paths previously fixed.
* Adds hardcoded include paths
Bug - https://github.com/GPUOpen-ProfessionalCompute-Libraries/MIVisionX/commit/f5eabaa1871e26bc…
-
* MIVisionX/amd_openvx_extensions/amd_nn/CMakeLists.txt
* MIVisionX/apps/cloud_inference/server_app/CMakeLists.txt
needs
````
include_directories(${OpenCL_INCLUDE_DIRS})
````