mirrors/gstreamer
mirrors/gstreamer
1
1
Fork 0
mirror of https://gitlab.freedesktop.org/gstreamer/gstreamer.git synced 2024-12-26 10:10:32 +00:00
Code Issues 1 Projects Releases Wiki Activity
gstreamer/subprojects/gst-plugins-bad/ext/onnx/meson.build

33 lines
886 B
Meson
Raw Normal View History

onnx: add plugin to apply ONNX neural network models to video This MR provides a transform element that leverage ONNX runtime to run AI inference on a broad range of neural network toolkits, running on either CPU or GPU. ONNX supports 16 different providers at the moment, so with ONNX we immediately get support for Nvidia, AMD, Xilinx and many others. For the first release, this plugin adds a gstonnxobjectdetector element to detect objects in video frames. Meta data generated by the model is attached to the video buffer as a custom GstObjectDetectorMeta meta. Part-of: <https://gitlab.freedesktop.org/gstreamer/gst-plugins-bad/-/merge_requests/1997>
2021-02-23 16:56:53 +00:00
if get_option('onnx').disabled()
subdir_done()
endif
onnx: Update to build against 1.16.1 Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/4916>
2023-10-19 20:16:21 +00:00
onnxrt_dep = dependency('libonnxruntime', version : '>= 1.16.1', required : get_option('onnx'))
onnx: add gstonnxinference element This element refactors functionality from gstonnxinference element, namely separating out the ONNX inference from the subsequent analysis. The new element runs an ONNX model on each video frame, and then attaches a TensorMeta meta with the output tensor data. This tensor data will then be consumed by downstream elements such as gstobjectdetector. At the moment, a provisional TensorMeta is used just in the ONNX plugin, but in future this will upgraded to a GStreamer API for other plugins to consume. Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/4916>
2023-06-26 14:55:53 +00:00
extra_args = []
extra_deps = []
if gstcuda_dep.found()
extra_args += ['-DHAVE_CUDA']
extra_deps += [gstcuda_dep]
endif
onnx: add plugin to apply ONNX neural network models to video This MR provides a transform element that leverage ONNX runtime to run AI inference on a broad range of neural network toolkits, running on either CPU or GPU. ONNX supports 16 different providers at the moment, so with ONNX we immediately get support for Nvidia, AMD, Xilinx and many others. For the first release, this plugin adds a gstonnxobjectdetector element to detect objects in video frames. Meta data generated by the model is attached to the video buffer as a custom GstObjectDetectorMeta meta. Part-of: <https://gitlab.freedesktop.org/gstreamer/gst-plugins-bad/-/merge_requests/1997>
2021-02-23 16:56:53 +00:00
if onnxrt_dep.found()
gstonnx = library('gstonnx',
'gstonnx.c',
onnx: add gstonnxinference element This element refactors functionality from gstonnxinference element, namely separating out the ONNX inference from the subsequent analysis. The new element runs an ONNX model on each video frame, and then attaches a TensorMeta meta with the output tensor data. This tensor data will then be consumed by downstream elements such as gstobjectdetector. At the moment, a provisional TensorMeta is used just in the ONNX plugin, but in future this will upgraded to a GStreamer API for other plugins to consume. Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/4916>
2023-06-26 14:55:53 +00:00
'decoders/gstobjectdetectorutils.cpp',
'decoders/gstssdobjectdetector.cpp',
'gstonnxinference.cpp',
onnx: add plugin to apply ONNX neural network models to video This MR provides a transform element that leverage ONNX runtime to run AI inference on a broad range of neural network toolkits, running on either CPU or GPU. ONNX supports 16 different providers at the moment, so with ONNX we immediately get support for Nvidia, AMD, Xilinx and many others. For the first release, this plugin adds a gstonnxobjectdetector element to detect objects in video frames. Meta data generated by the model is attached to the video buffer as a custom GstObjectDetectorMeta meta. Part-of: <https://gitlab.freedesktop.org/gstreamer/gst-plugins-bad/-/merge_requests/1997>
2021-02-23 16:56:53 +00:00
'gstonnxclient.cpp',
onnx: add gstonnxinference element This element refactors functionality from gstonnxinference element, namely separating out the ONNX inference from the subsequent analysis. The new element runs an ONNX model on each video frame, and then attaches a TensorMeta meta with the output tensor data. This tensor data will then be consumed by downstream elements such as gstobjectdetector. At the moment, a provisional TensorMeta is used just in the ONNX plugin, but in future this will upgraded to a GStreamer API for other plugins to consume. Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/4916>
2023-06-26 14:55:53 +00:00
'tensor/gsttensormeta.c',
c_args : gst_plugins_bad_args + extra_args,
cpp_args : gst_plugins_bad_args + extra_args,
onnx: add plugin to apply ONNX neural network models to video This MR provides a transform element that leverage ONNX runtime to run AI inference on a broad range of neural network toolkits, running on either CPU or GPU. ONNX supports 16 different providers at the moment, so with ONNX we immediately get support for Nvidia, AMD, Xilinx and many others. For the first release, this plugin adds a gstonnxobjectdetector element to detect objects in video frames. Meta data generated by the model is attached to the video buffer as a custom GstObjectDetectorMeta meta. Part-of: <https://gitlab.freedesktop.org/gstreamer/gst-plugins-bad/-/merge_requests/1997>
2021-02-23 16:56:53 +00:00
link_args : noseh_link_args,
onnx: Update to build against 1.16.1 Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/4916>
2023-10-19 20:16:21 +00:00
include_directories : [configinc, libsinc, cuda_stubinc],
onnx: add gstonnxinference element This element refactors functionality from gstonnxinference element, namely separating out the ONNX inference from the subsequent analysis. The new element runs an ONNX model on each video frame, and then attaches a TensorMeta meta with the output tensor data. This tensor data will then be consumed by downstream elements such as gstobjectdetector. At the moment, a provisional TensorMeta is used just in the ONNX plugin, but in future this will upgraded to a GStreamer API for other plugins to consume. Part-of: <https://gitlab.freedesktop.org/gstreamer/gstreamer/-/merge_requests/4916>
2023-06-26 14:55:53 +00:00
dependencies : [gstbase_dep, gstvideo_dep, onnxrt_dep, libm] + extra_deps,
onnx: add plugin to apply ONNX neural network models to video This MR provides a transform element that leverage ONNX runtime to run AI inference on a broad range of neural network toolkits, running on either CPU or GPU. ONNX supports 16 different providers at the moment, so with ONNX we immediately get support for Nvidia, AMD, Xilinx and many others. For the first release, this plugin adds a gstonnxobjectdetector element to detect objects in video frames. Meta data generated by the model is attached to the video buffer as a custom GstObjectDetectorMeta meta. Part-of: <https://gitlab.freedesktop.org/gstreamer/gst-plugins-bad/-/merge_requests/1997>
2021-02-23 16:56:53 +00:00
install : true,
install_dir : plugins_install_dir,
)
plugins += [gstonnx]
endif
Reference in a new issue Copy permalink