579
edits
GstInference/Benchmarks: Difference between revisions
no edit summary
No edit summary |
No edit summary |
||
| Line 744: | Line 744: | ||
== ONNXRT Benchmarks == | == ONNXRT Benchmarks == | ||
The following was the GStreamer pipeline used to obtain the results: | |||
<source lang="bash"> | |||
model_array=(inceptionv1 inceptionv2 inceptionv3 inceptionv4 tinyyolov2 tinyyolov3) | |||
gst-launch-1.0 \ | |||
filesrc location=$VIDEO_PATH num-buffers=600 ! decodebin ! videoconvert ! \ | |||
perf print-arm-load=true name=inputperf ! tee name=t t. ! videoscale ! queue ! net.sink_model t. ! queue ! net.sink_bypass \ | |||
${model_array[i]} backend=onnxrt name=net \ | |||
model-location="$MODELS_PATH \ | |||
net.src_bypass ! perf print-arm-load=true name=outputperf ! videoconvert ! fakesink sync=false | |||
</source> | |||
=== FPS Measurements === | === FPS Measurements === | ||