There are various use cases available, click one each hyperlink to find out more details:
to build run:
make build-gst
run one gst dlstreamer pipeline and use the default object detection only (yolov5s.sh)
make run-gst
run three gst dlstreamer pipelines and use the default object detection only (yolov5s.sh)
PIPELINE_COUNT=3 make run-gst
run two gst dlstreamer pipelines and use the object detection with classification (yolov5s_effnetb0.sh)
PIPELINE_SCRIPT=yolov5s_effnetb0.sh PIPELINE_COUNT=2 make run-gst
shutdown Docker containers
make down-gst
clean up the output results
make clean-results
to build run:
make build-grpc_python
run one grpc_python pipeline and use the default model (instance-segmentation-security-1040)
make run-grpc_python
show the supported MODEL_NAME for grpc_python
make list-grpc-python-model-names
run three grpc_python pipelines and use yolov5s model
PIPELINE_COUNT=3 MODEL_NAME=yolov5s make run-grpc_python
shutdown Docker containers
make down-grpc_python
clean up the output results
make clean-results
There are three different pipelines for gst_capi use cases: capi_yolov5, capi_yolov5_ensemble, and capi_face_detection.
to build all capis run:
make build-all-capis
to build one at a time run:
for capi_yolov5
make build-capi_yolov5
for capi_yolov5_ensemble
make build-capi_yolov5_ensemble
for capi_face_detection
make build-capi_face_detection
run one capi_yolov5 pipeline
make run-capi_yolov5
shutdown capi_yolov5
make down-capi_yolov5
run one capi_yolov5_ensemble pipeline
make run-capi_yolov5_ensemble
shutdown capi_yolov5_ensemble
make down-capi_yolov5_ensemble
run one capi_face_detection pipeline
make run-capi_face_detection
shutdown capi_face_detection
make down-capi_face_detection
run two capi_yolov5_ensemble pipelines
PIPELINE_COUNT=2 make run-capi_yolov5_ensemble
shutdown Docker containers
make down-capi_yolov5
make down-capi_yolov5_ensemble
make down-capi_face_detection
clean up the output results
make clean-results
There are three different pipelines for demos use case: classification, instance_segmentation, and object_detection.
to build run:
make build-demos
run one classification pipeline
make run-demo-classification
run one instance segmentation pipeline
make run-demo-instance-segmentation
run two object detection pipelines
PIPELINE_COUNT=2 make run-demo-object-detection
shutdown classification pipeline Docker container
make down-demo-classification
shutdown all Docker containers
make down-demos-all
clean up the output results
make clean-results
to build run:
make build-grpc-go
run one grpc_go pipeline
make run-grpc-go
run two grpc_go pipelines
PIPELINE_COUNT=2 make run-grpc-go
shutdown Docker containers
make down-grpc-go
clean up the output results
make clean-results
GStreamer is an open source framework licensed under LGPL. See https://gstreamer.freedesktop.org/documentation/frequently-asked-questions/licensing.html?gi-language=c. You are solely responsible for determining if your use of Gstreamer requires any additional licenses. Intel is not responsible for obtaining any such licenses, nor liable for any licensing fees due, in connection with your use of Gstreamer.
Certain third-party software or hardware identified in this document only may be used upon securing a license directly from the third-party software or hardware owner. The identification of non-Intel software, tools, or services in this document does not constitute a sponsorship, endorsement, or warranty by Intel.
To the extent that any data, datasets or models are referenced by Intel or accessed using tools or code on this site such data, datasets and models are provided by the third party indicated as the source of such content. Intel does not create the data, datasets, or models, provide a license to any third-party data, datasets, or models referenced, and does not warrant their accuracy or quality. By accessing such data, dataset(s) or model(s) you agree to the terms associated with that content and that your use complies with the applicable license.
Intel expressly disclaims the accuracy, adequacy, or completeness of any data, datasets or models, and is not liable for any errors, omissions, or defects in such content, or for any reliance thereon. Intel also expressly disclaims any warranty of non-infringement with respect to such data, dataset(s), or model(s). Intel is not liable for any liability or damages relating to your use of such data, datasets or models.