GstInference GStreamer pipelines for NVIDIA Xavier

GstInference
Introduction
Getting started
Getting the code Building the plugin Quick Starting Guide
Supported architectures
InceptionV1 InceptionV2 InceptionV3 InceptionV4 TinyYoloV2 TinyYoloV3 YoloV2 ResNetV1 MobileNetV2 MobileNetV2 + SSD AlexNet
Supported backends
TensorFlow Tensorflow-Lite Coral from Google Caffe TensorRT ONNXRT ONNXRT ACL ONNXRT OpenVINO
Metadata and Signals
GstClassificationMeta GstInferenceMeta Signals
Overlay Elements
Inference Overlay
Utils Elements
InferenceFilter InferenceCrop InferenceDebug InferenceBin
Legacy pipelines
PC NANO TX2 Xavier IMX8
Example pipelines
Example applications
Classification Detection Hand Pose Recognition
Benchmarks
Model Zoo
Project Status
Releases Roadmap
Contact Us

Problems running the pipelines shown on this page? Please see our GStreamer Debugging guide for help.

Tensorflow

Inceptionv4 inference on image file using Tensorflow

• Get the graph used on this example from this link
• You will need an image file from one of ImageNet classes
• Pipeline

IMAGE_FILE=cat.jpg
MODEL_LOCATION='graph_inceptionv4_tensorflow.pb'
INPUT_LAYER='input'
OUTPUT_LAYER='InceptionV4/Logits/Predictions'
GST_DEBUG=*inceptionv4*:6 gst-launch-1.0 \
multifilesrc location=$IMAGE_FILE ! jpegparse ! nvjpegdec ! 'video/x-raw' ! nvvidconv ! 'video/x-raw(memory:NVMM),format=NV12' ! nvvidconv ! queue ! net.sink_model \
inceptionv4 name=net model-location=$MODEL_LOCATION backend=tensorflow backend::input-layer=$INPUT_LAYER  backend::output-layer=$OUTPUT_LAYER -v

• Output

0:00:27.311799544  8662   0x5574569c00 LOG              inceptionv4 gstinceptionv4.c:199:gst_inceptionv4_preprocess:<net> Preprocess
0:00:27.392320971  8662   0x5574569c00 LOG              inceptionv4 gstinceptionv4.c:231:gst_inceptionv4_postprocess:<net> Postprocess
0:00:27.392530965  8662   0x5574569c00 LOG              inceptionv4 gstinceptionv4.c:252:gst_inceptionv4_postprocess:<net> Highest probability is label 282 : (0.641151)
0:00:27.392753791  8662   0x5574569c00 LOG              inceptionv4 gstinceptionv4.c:199:gst_inceptionv4_preprocess:<net> Preprocess
0:00:27.473382966  8662   0x5574569c00 LOG              inceptionv4 gstinceptionv4.c:231:gst_inceptionv4_postprocess:<net> Postprocess
0:00:27.473550590  8662   0x5574569c00 LOG              inceptionv4 gstinceptionv4.c:252:gst_inceptionv4_postprocess:<net> Highest probability is label 282 : (0.641151)
0:00:27.473744103  8662   0x5574569c00 LOG              inceptionv4 gstinceptionv4.c:199:gst_inceptionv4_preprocess:<net> Preprocess
0:00:27.554464931  8662   0x5574569c00 LOG              inceptionv4 gstinceptionv4.c:231:gst_inceptionv4_postprocess:<net> Postprocess
0:00:27.554651980  8662   0x5574569c00 LOG              inceptionv4 gstinceptionv4.c:252:gst_inceptionv4_postprocess:<net> Highest probability is label 282 : (0.641151)

Inceptionv4 inference on video file using TensorFlow

• Get the graph used on this example from this link
• You will need a video file from one of ImageNet classes
• Pipeline

VIDEO_FILE='cat.mp4'
MODEL_LOCATION='graph_inceptionv4_tensorflow.pb'
INPUT_LAYER='input'
OUTPUT_LAYER='InceptionV4/Logits/Predictions'
GST_DEBUG=inceptionv4:6 gst-launch-1.0 \
filesrc location=$VIDEO_FILE ! qtdemux name=demux ! h264parse ! omxh264dec ! nvvidconv ! queue ! net.sink_model \
inceptionv4 name=net model-location=$MODEL_LOCATION backend=tensorflow backend::input-layer=$INPUT_LAYER  backend::output-layer=$OUTPUT_LAYER

• Output

0:00:26.066035371  8749   0x5561bb6c00 LOG              inceptionv4 gstinceptionv4.c:199:gst_inceptionv4_preprocess:<net> Preprocess
0:00:26.148041538  8749   0x5561bb6c00 LOG              inceptionv4 gstinceptionv4.c:231:gst_inceptionv4_postprocess:<net> Postprocess
0:00:26.148233387  8749   0x5561bb6c00 LOG              inceptionv4 gstinceptionv4.c:252:gst_inceptionv4_postprocess:<net> Highest probability is label 282 : (0.671327)
0:00:26.148416179  8749   0x5561bb6c00 LOG              inceptionv4 gstinceptionv4.c:199:gst_inceptionv4_preprocess:<net> Preprocess
0:00:26.229609892  8749   0x5561bb6c00 LOG              inceptionv4 gstinceptionv4.c:231:gst_inceptionv4_postprocess:<net> Postprocess
0:00:26.229837199  8749   0x5561bb6c00 LOG              inceptionv4 gstinceptionv4.c:252:gst_inceptionv4_postprocess:<net> Highest probability is label 282 : (0.671591)
0:00:26.230285188  8749   0x5561bb6c00 LOG              inceptionv4 gstinceptionv4.c:199:gst_inceptionv4_preprocess:<net> Preprocess
0:00:26.312565831  8749   0x5561bb6c00 LOG              inceptionv4 gstinceptionv4.c:231:gst_inceptionv4_postprocess:<net> Postprocess
0:00:26.312736911  8749   0x5561bb6c00 LOG              inceptionv4 gstinceptionv4.c:252:gst_inceptionv4_postprocess:<net> Highest probability is label 282 : (0.671140)

Inceptionv4 inference on camera stream using TensorFlow

• Get the graph used on this example from this link
• You will need a camera compatible with Nvidia Libargus API or V4l2.

Nvidia Camera

• Pipeline

SENSOR_ID=0
MODEL_LOCATION='graph_inceptionv4_tensorflow.pb'
INPUT_LAYER='input'
OUTPUT_LAYER='InceptionV4/Logits/Predictions'
GST_DEBUG=inceptionv4:6 gst-launch-1.0 \
nvarguscamerasrc sensor-id=$SENSOR_ID ! nvvidconv ! queue ! net.sink_model \
inceptionv4 name=net backend=tensorflow model-location=$MODEL_LOCATION backend::input-layer=$INPUT_LAYER backend::output-layer=$OUTPUT_LAYER

• Output

0:00:18.988267527  9466   0x55ab1bdf70 LOG              inceptionv4 gstinceptionv4.c:199:gst_inceptionv4_preprocess:<net> Preprocess
0:00:19.070172277  9466   0x55ab1bdf70 LOG              inceptionv4 gstinceptionv4.c:231:gst_inceptionv4_postprocess:<net> Postprocess
0:00:19.070390174  9466   0x55ab1bdf70 LOG              inceptionv4 gstinceptionv4.c:252:gst_inceptionv4_postprocess:<net> Highest probability is label 572 : (0.236359)
0:00:19.070572038  9466   0x55ab1bdf70 LOG              inceptionv4 gstinceptionv4.c:199:gst_inceptionv4_preprocess:<net> Preprocess
0:00:19.151636754  9466   0x55ab1bdf70 LOG              inceptionv4 gstinceptionv4.c:231:gst_inceptionv4_postprocess:<net> Postprocess
0:00:19.151839035  9466   0x55ab1bdf70 LOG              inceptionv4 gstinceptionv4.c:252:gst_inceptionv4_postprocess:<net> Highest probability is label 572 : (0.219772)
0:00:19.152054147  9466   0x55ab1bdf70 LOG              inceptionv4 gstinceptionv4.c:199:gst_inceptionv4_preprocess:<net> Preprocess
0:00:19.233439549  9466   0x55ab1bdf70 LOG              inceptionv4 gstinceptionv4.c:231:gst_inceptionv4_postprocess:<net> Postprocess
0:00:19.233609380  9466   0x55ab1bdf70 LOG              inceptionv4 gstinceptionv4.c:252:gst_inceptionv4_postprocess:<net> Highest probability is label 572 : (0.232309)

V4L2

• Pipeline

CAMERA='/dev/video1'
MODEL_LOCATION='graph_inceptionv4_tensorflow.pb'
INPUT_LAYER='input'
OUTPUT_LAYER='InceptionV4/Logits/Predictions'
GST_DEBUG=inceptionv4:6 gst-launch-1.0 \
v4l2src device=$CAMERA ! videoconvert ! videoscale ! queue ! net.sink_model \
inceptionv4 name=net model-location=$MODEL_LOCATION backend=tensorflow backend::input-layer=$INPUT_LAYER  backend::output-layer=$OUTPUT_LAYER

• Output

0:00:26.011511251  9419   0x55be091a80 LOG              inceptionv4 gstinceptionv4.c:199:gst_inceptionv4_preprocess:<net> Preprocess
0:00:26.092995813  9419   0x55be091a80 LOG              inceptionv4 gstinceptionv4.c:231:gst_inceptionv4_postprocess:<net> Postprocess
0:00:26.093545274  9419   0x55be091a80 LOG              inceptionv4 gstinceptionv4.c:252:gst_inceptionv4_postprocess:<net> Highest probability is label 692 : (0.183870)
0:00:26.111398950  9419   0x55be091a80 LOG              inceptionv4 gstinceptionv4.c:199:gst_inceptionv4_preprocess:<net> Preprocess
0:00:26.193210725  9419   0x55be091a80 LOG              inceptionv4 gstinceptionv4.c:231:gst_inceptionv4_postprocess:<net> Postprocess
0:00:26.193724089  9419   0x55be091a80 LOG              inceptionv4 gstinceptionv4.c:252:gst_inceptionv4_postprocess:<net> Highest probability is label 663 : (0.135397)
0:00:26.212316002  9419   0x55be091a80 LOG              inceptionv4 gstinceptionv4.c:199:gst_inceptionv4_preprocess:<net> Preprocess
0:00:26.294116480  9419   0x55be091a80 LOG              inceptionv4 gstinceptionv4.c:231:gst_inceptionv4_postprocess:<net> Postprocess
0:00:26.294284935  9419   0x55be091a80 LOG              inceptionv4 gstinceptionv4.c:252:gst_inceptionv4_postprocess:<net> Highest probability is label 692 : (0.316769)

Inceptionv4 visualization with classification overlay Tensorflow

• Get the graph used on this example from this link
• You will need a camera compatible with Nvidia Libargus API or V4l2.

Nvidia Camera

• Pipeline

SENSOR_ID=0
MODEL_LOCATION='graph_inceptionv4_tensorflow.pb'
INPUT_LAYER='input'
OUTPUT_LAYER='InceptionV4/Logits/Predictions'
LABELS='imagenet_labels.txt'
GST_DEBUG=inceptionv4:6 \
gst-launch-1.0 \
nvarguscamerasrc sensor-id=$SENSOR_ID ! 'video/x-raw(memory:NVMM)' ! tee name=t \
t. ! queue max-size-buffers=1 leaky=downstream ! nvvidconv ! 'video/x-raw,format=(string)RGBA' ! net.sink_model \
t. ! queue max-size-buffers=1 leaky=downstream ! nvvidconv ! 'video/x-raw,format=(string)RGBA' ! net.sink_bypass \
inceptionv4 name=net backend=tensorflow model-location=$MODEL_LOCATION backend::input-layer=$INPUT_LAYER backend::output-layer=$OUTPUT_LAYER \
net.src_bypass ! classificationoverlay labels="$(cat $LABELS)" font-scale=4 thickness=4 ! nvvidconv ! nvoverlaysink sync=false -v

V4L2

• Pipeline

CAMERA='/dev/video1'
MODEL_LOCATION='graph_inceptionv4_tensorflow.pb'
INPUT_LAYER='input'
OUTPUT_LAYER='InceptionV4/Logits/Predictions'
LABELS='imagenet_labels.txt'
gst-launch-1.0 \
v4l2src device=$CAMERA ! "video/x-raw, width=1280, height=720" ! tee name=t \
t. ! videoconvert ! videoscale ! queue ! net.sink_model \
t. ! queue ! net.sink_bypass \
inceptionv4 name=net model-location=$MODEL_LOCATION backend=tensorflow backend::input-layer=$INPUT_LAYER  backend::output-layer=$OUTPUT_LAYER \
net.src_bypass ! videoconvert ! classificationoverlay labels="$(cat $LABELS)" font-scale=4 thickness=4 ! videoconvert ! xvimagesink sync=false

• Output

Example classification overlay output

TinyYolov2 inference on image file using Tensorflow

• Get the graph used on this example from this link
• You will need an image file from one of TinyYOLO classes
• Pipeline

IMAGE_FILE='cat.jpg'
MODEL_LOCATION='graph_tinyyolov2_tensorflow.pb'
INPUT_LAYER='input/Placeholder'
OUTPUT_LAYER='add_8'
GST_DEBUG=*tinyyolov2*:6 gst-launch-1.0 \
multifilesrc location=$IMAGE_FILE ! jpegparse ! nvjpegdec ! 'video/x-raw' ! nvvidconv ! 'video/x-raw(memory:NVMM),format=NV12' ! nvvidconv ! queue ! net.sink_model \
tinyyolov2 name=net model-location=$MODEL_LOCATION backend=tensorflow backend::input-layer=$INPUT_LAYER  backend::output-layer=$OUTPUT_LAYER

• Output

0:00:13.688000146  9079   0x5586b50400 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:13.718464628  9079   0x5586b50400 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:13.718745089  9079   0x5586b50400 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:7, x:25.599654, y:11.992019, width:425.713685, height:450.001330, prob:15.272157]
0:00:13.718885768  9079   0x5586b50400 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:13.749664857  9079   0x5586b50400 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:13.749913956  9079   0x5586b50400 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:7, x:25.599654, y:11.992019, width:425.713685, height:450.001330, prob:15.272157]
0:00:13.750110573  9079   0x5586b50400 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:13.780493932  9079   0x5586b50400 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:13.780683893  9079   0x5586b50400 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:7, x:25.599654, y:11.992019, width:425.713685, height:450.001330, prob:15.272157]

TinyYolov2 inference on video file using Tensorflow

• Get the graph used on this example from this link
• You will need a video file from one of TinyYOLO classes
• Pipeline

VIDEO_FILE='cat.mp4'
MODEL_LOCATION='graph_tinyyolov2_tensorflow.pb'
INPUT_LAYER='input/Placeholder'
OUTPUT_LAYER='add_8'
GST_DEBUG=tinyyolov2:6 gst-launch-1.0 \
filesrc location=$VIDEO_FILE ! qtdemux name=demux ! h264parse ! omxh264dec ! nvvidconv ! queue ! net.sink_model \
tinyyolov2 name=net model-location=$MODEL_LOCATION backend=tensorflow backend::input-layer=$INPUT_LAYER  backend::output-layer=$OUTPUT_LAYER

• Output

0:00:14.381019732  9117   0x557acd2400 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:14.411021505  9117   0x557acd2400 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:14.411177384  9117   0x557acd2400 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:7, x:-44.591707, y:-5.845335, width:442.388362, height:481.775217, prob:14.093070]
0:00:14.411345232  9117   0x557acd2400 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:14.442502898  9117   0x557acd2400 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:14.442725660  9117   0x557acd2400 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:7, x:-44.701888, y:-5.632816, width:442.592144, height:481.298278, prob:14.067967]
0:00:14.442917957  9117   0x557acd2400 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:14.473535727  9117   0x557acd2400 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:14.473714423  9117   0x557acd2400 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:7, x:-44.265085, y:-5.536356, width:441.748600, height:481.168355, prob:14.094460]

TinyYolov2 inference on camera stream using Tensorflow

• Get the graph used on this example from this link
• You will need a camera compatible with Nvidia Libargus API or V4l2.

Nvidia Camera

• Pipeline

SENSOR_ID=0
MODEL_LOCATION='graph_tinyyolov2_tensorflow.pb'
INPUT_LAYER='input/Placeholder'
OUTPUT_LAYER='add_8'
nvarguscamerasrc sensor-id=$SENSOR_ID ! nvvidconv ! 'video/x-raw,format=BGRx' ! queue ! net.sink_model \
tinyyolov2 name=net model-location=$MODEL_LOCATION backend=tensorflow backend::input-layer=$INPUT_LAYER  backend::output-layer=$OUTPUT_LAYER

• Output

0:00:14.000211619 10096   0x559e4a3ad0 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:14.030785264 10096   0x559e4a3ad0 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:14.031252958 10096   0x559e4a3ad0 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:14, x:254.023574, y:0.996667, width:159.442352, height:348.442927, prob:9.038744]
0:00:14.031711884 10096   0x559e4a3ad0 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:14.062577890 10096   0x559e4a3ad0 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:14.062782056 10096   0x559e4a3ad0 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:14, x:256.071149, y:1.104463, width:156.332928, height:348.299846, prob:8.926831]
0:00:14.062944333 10096   0x559e4a3ad0 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:14.093773666 10096   0x559e4a3ad0 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:14.093983657 10096   0x559e4a3ad0 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:14, x:256.927108, y:1.150354, width:156.535506, height:348.715533, prob:8.894010]

V4L2

• Pipeline

CAMERA='/dev/video1'
MODEL_LOCATION='graph_tinyyolov2_tensorflow.pb'
INPUT_LAYER='input/Placeholder'
OUTPUT_LAYER='add_8'
GST_DEBUG=tinyyolov2:6 gst-launch-1.0 \
v4l2src device=$CAMERA ! videoconvert ! videoscale ! queue ! net.sink_model \
tinyyolov2 name=net model-location=$MODEL_LOCATION backend=tensorflow backend::input-layer=$INPUT_LAYER  backend::output-layer=$OUTPUT_LAYER

• Output

0:00:28.565124313 10004   0x557d50b8f0 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:28.595697567 10004   0x557d50b8f0 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:28.595854948 10004   0x557d50b8f0 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:8, x:185.249442, y:65.398277, width:105.441149, height:227.889733, prob:9.066236]
0:00:28.597461562 10004   0x557d50b8f0 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:28.628034112 10004   0x557d50b8f0 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:28.628255335 10004   0x557d50b8f0 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:8, x:186.390381, y:66.198741, width:103.368757, height:226.331411, prob:9.443931]
0:00:28.629607125 10004   0x557d50b8f0 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:28.660004596 10004   0x557d50b8f0 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:28.660173338 10004   0x557d50b8f0 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:8, x:186.278082, y:67.236859, width:103.066607, height:225.127201, prob:8.822085]

TinyYolov2 visualization with detection overlay Tensorflow

• Get the graph used on this example from this link
• You will need a camera compatible with Nvidia Libargus API or V4l2.

Nvidia Camera

• Pipeline

SENSOR_ID=0
MODEL_LOCATION='graph_tinyyolov2_tensorflow.pb'
INPUT_LAYER='input/Placeholder'
OUTPUT_LAYER='add_8'
LABELS='labels.txt'
GST_DEBUG=tinyyolov2:6 \
gst-launch-1.0 \
nvarguscamerasrc sensor-id=$SENSOR_ID ! 'video/x-raw(memory:NVMM)' ! tee name=t \
t. ! queue max-size-buffers=1 leaky=downstream ! nvvidconv ! 'video/x-raw,format=(string)RGBA' ! net.sink_model \
t. ! queue max-size-buffers=1 leaky=downstream ! nvvidconv ! 'video/x-raw,format=(string)RGBA' ! net.sink_bypass \
tinyyolov2 name=net backend=tensorflow model-location=$MODEL_LOCATION backend::input-layer=$INPUT_LAYER backend::output-layer=$OUTPUT_LAYER \
net.src_bypass !  detectionoverlay labels="$(cat $LABELS)" font-scale=4 thickness=4  ! nvvidconv ! nvoverlaysink sync=false -v

V4L2

• Pipeline

CAMERA='/dev/video1'
MODEL_LOCATION='graph_tinyyolov2_tensorflow.pb'
INPUT_LAYER='input/Placeholder'
OUTPUT_LAYER='add_8'
LABELS='labels.txt'
gst-launch-1.0 \
v4l2src device=$CAMERA ! "video/x-raw, width=1280, height=720" ! tee name=t \
t. ! videoconvert ! videoscale ! queue ! net.sink_model \
t. ! queue ! net.sink_bypass \
tinyyolov2 name=net model-location=$MODEL_LOCATION backend=tensorflow backend::input-layer=$INPUT_LAYER backend::output-layer=$OUTPUT_LAYER \
net.src_bypass ! videoconvert ! detectionoverlay labels="$(cat $LABELS)" font-scale=1 thickness=2 ! videoconvert ! xvimagesink sync=false

• Output

Example detection overlay output

FaceNet visualization with embedding overlay Tensorflow

• Get the graph used on this example from this link
• You will need a camera compatible with Nvidia Libargus API or V4l2.
• LABELS and EMBEDDINGS files are in $PATH_TO_GST_INFERENCE_ROOT_DIR/tests/examples/embedding/embeddings.

Nvidia Camera

• Pipeline

SENSOR_ID=0
MODEL_LOCATION='graph_facenetv1_tensorflow.pb'
INPUT_LAYER='input'
OUTPUT_LAYER='output'
LABELS='$PATH_TO_GST_INFERENCE_ROOT_DIR/tests/examples/embedding/embeddings/labels.txt'
EMBEDDINGS='$PATH_TO_GST_INFERENCE_ROOT_DIR/tests/examples/embedding/embeddings/embeddings.txt'
gst-launch-1.0 \
nvarguscamerasrc sensor-id=$SENSOR_ID ! 'video/x-raw(memory:NVMM)' ! nvvidconv ! 'video/x-raw,format=BGRx,width=(int)1280,height=(int)720' ! videoconvert ! tee name=t \
t. ! queue ! videoscale ! queue ! net.sink_model \
t. ! queue ! net.sink_bypass \
facenetv1 name=net model-location=$MODEL_LOCATION backend=tensorflow backend::input-layer=$INPUT_LAYER backend::output-layer=$OUTPUT_LAYER \
net.src_bypass ! videoconvert ! embeddingoverlay labels="$(cat $LABELS)" embeddings="$(cat $EMBEDDINGS)" font-scale=4 thickness=4 ! videoconvert ! xvimagesink sync=false

V4L2

• Pipeline

CAMERA='/dev/video1'
MODEL_LOCATION='graph_facenetv1_tensorflow.pb'
INPUT_LAYER='input'
OUTPUT_LAYER='output'
LABELS='$PATH_TO_GST_INFERENCE_ROOT_DIR/tests/examples/embedding/embeddings/labels.txt'
EMBEDDINGS='$PATH_TO_GST_INFERENCE_ROOT_DIR/tests/examples/embedding/embeddings/embeddings.txt'
gst-launch-1.0 \
v4l2src device=$CAMERA ! "video/x-raw, width=1280, height=720" ! tee name=t \
t. ! videoconvert ! videoscale ! queue ! net.sink_model \
t. ! queue ! net.sink_bypass \
facenetv1 name=net model-location=$MODEL_LOCATION backend=tensorflow backend::input-layer=$INPUT_LAYER backend::output-layer=$OUTPUT_LAYER \
net.src_bypass ! videoconvert ! embeddingoverlay labels="$(cat $LABELS)" embeddings="$(cat $EMBEDDINGS)" font-scale=4 thickness=4 ! videoconvert ! xvimagesink sync=false

• Output

Example detection overlay output

TensorFlow-Lite

Inceptionv4 inference on image file using TensorFlow-Lite

• Get the graph used on this example from this link
• You will need an image file from one of ImageNet classes
• Pipeline

IMAGE_FILE='cat.jpg'
MODEL_LOCATION='graph_inceptionv4.tflite'
LABELS='labels.txt'
GST_DEBUG=inceptionv4:6 gst-launch-1.0 \
multifilesrc location=$IMAGE_FILE ! jpegparse ! nvjpegdec ! 'video/x-raw' ! nvvidconv ! 'video/x-raw(memory:NVMM),format=NV12' ! nvvidconv ! queue ! net.sink_model \
inceptionv4 name=net model-location=$MODEL_LOCATION backend=tflite labels="$(cat $LABELS)"

• Output

0:02:22.005527960 30355       0x5accf0 LOG              inceptionv4 gstinceptionv4.c:200:gst_inceptionv4_preprocess:<net> Preprocess
0:02:22.168796723 30355       0x5accf0 LOG              inceptionv4 gstinceptionv4.c:232:gst_inceptionv4_postprocess:<net> Postprocess
0:02:22.168947603 30355       0x5accf0 LOG              inceptionv4 gstinceptionv4.c:253:gst_inceptionv4_postprocess:<net> Highest probability is label 282 : (0.627314)
0:02:22.169237202 30355       0x5accf0 LOG              inceptionv4 gstinceptionv4.c:200:gst_inceptionv4_preprocess:<net> Preprocess
0:02:22.339393463 30355       0x5accf0 LOG              inceptionv4 gstinceptionv4.c:232:gst_inceptionv4_postprocess:<net> Postprocess
0:02:22.339496918 30355       0x5accf0 LOG              inceptionv4 gstinceptionv4.c:253:gst_inceptionv4_postprocess:<net> Highest probability is label 282 : (0.627314)
0:02:22.339701878 30355       0x5accf0 LOG              inceptionv4 gstinceptionv4.c:200:gst_inceptionv4_preprocess:<net> Preprocess
0:02:22.507804674 30355       0x5accf0 LOG              inceptionv4 gstinceptionv4.c:232:gst_inceptionv4_postprocess:<net> Postprocess
0:02:22.507950081 30355       0x5accf0 LOG              inceptionv4 gstinceptionv4.c:253:gst_inceptionv4_postprocess:<net> Highest probability is label 282 : (0.627314)
0:02:22.508232128 30355       0x5accf0 LOG              inceptionv4 gstinceptionv4.c:200:gst_inceptionv4_preprocess:<net> Preprocess
0:02:22.678740356 30355       0x5accf0 LOG              inceptionv4 gstinceptionv4.c:232:gst_inceptionv4_postprocess:<net> Postprocess
0:02:22.678892356 30355       0x5accf0 LOG              inceptionv4 gstinceptionv4.c:253:gst_inceptionv4_postprocess:<net> Highest probability is label 282 : (0.627314)

Inceptionv4 inference on video file using TensorFlow-Lite

• Get the graph used on this example from this link
• You will need a video file from one of ImageNet classes
• Pipeline

VIDEO_FILE='cat.mp4'
MODEL_LOCATION='graph_inceptionv4.tflite'
LABELS='labels.txt'
GST_DEBUG=inceptionv4:6 gst-launch-1.0 \
filesrc location=$VIDEO_FILE ! qtdemux name=demux ! h264parse ! omxh264dec ! nvvidconv ! queue ! net.sink_model \
inceptionv4 name=net model-location=$MODEL_LOCATION backend=tflite labels="$(cat $LABELS)"

• Output

0:00:11.728307018 30399       0x5ad000 LOG              inceptionv4 gstinceptionv4.c:200:gst_inceptionv4_preprocess:<net> Preprocess
0:00:11.892030154 30399       0x5ad000 LOG              inceptionv4 gstinceptionv4.c:232:gst_inceptionv4_postprocess:<net> Postprocess
0:00:11.892258185 30399       0x5ad000 LOG              inceptionv4 gstinceptionv4.c:253:gst_inceptionv4_postprocess:<net> Highest probability is label 282 : (0.686857)
0:00:11.892556808 30399       0x5ad000 LOG              inceptionv4 gstinceptionv4.c:200:gst_inceptionv4_preprocess:<net> Preprocess
0:00:12.065318539 30399       0x5ad000 LOG              inceptionv4 gstinceptionv4.c:232:gst_inceptionv4_postprocess:<net> Postprocess
0:00:12.065467786 30399       0x5ad000 LOG              inceptionv4 gstinceptionv4.c:253:gst_inceptionv4_postprocess:<net> Highest probability is label 282 : (0.673300)
0:00:12.065759849 30399       0x5ad000 LOG              inceptionv4 gstinceptionv4.c:200:gst_inceptionv4_preprocess:<net> Preprocess
0:00:12.247159695 30399       0x5ad000 LOG              inceptionv4 gstinceptionv4.c:232:gst_inceptionv4_postprocess:<net> Postprocess
0:00:12.247309295 30399       0x5ad000 LOG              inceptionv4 gstinceptionv4.c:253:gst_inceptionv4_postprocess:<net> Highest probability is label 282 : (0.669102)
0:00:12.247612718 30399       0x5ad000 LOG              inceptionv4 gstinceptionv4.c:200:gst_inceptionv4_preprocess:<net> Preprocess
0:00:12.419172436 30399       0x5ad000 LOG              inceptionv4 gstinceptionv4.c:232:gst_inceptionv4_postprocess:<net> Postprocess
0:00:12.419321396 30399       0x5ad000 LOG              inceptionv4 gstinceptionv4.c:253:gst_inceptionv4_postprocess:<net> Highest probability is label 282 : (0.667991)

Inceptionv4 inference on camera stream using TensorFlow-Lite

• Get the graph used on this example from this link
• You will need a camera compatible with Nvidia Libargus API or V4l2.

Nvidia Camera

• Pipeline

SENSOR_ID=0
MODEL_LOCATION='graph_inceptionv4.tflite'
LABELS='labels.txt'
GST_DEBUG=inceptionv4:6 gst-launch-1.0 \
nvcamerasrc sensor-id=$SENSOR_ID ! nvvidconv ! queue ! net.sink_model \
inceptionv4 name=net backend=tflite model-location=$MODEL_LOCATION labels="$(cat $LABELS)"

V4L2

• Pipeline

CAMERA='/dev/video0'
MODEL_LOCATION='graph_inceptionv4.tflite'
LABELS='labels.txt'
GST_DEBUG=inceptionv4:6 gst-launch-1.0 \
v4l2src device=$CAMERA ! videoconvert ! videoscale ! queue ! net.sink_model \
inceptionv4 name=net model-location=$MODEL_LOCATION backend=tflite labels="$(cat $LABELS)"

• Output

0:00:12.199657219  4675      0x10ee590 LOG              inceptionv4 gstinceptionv4.c:200:gst_inceptionv4_preprocess:<net> Preprocess
0:00:12.365172092  4675      0x10ee590 LOG              inceptionv4 gstinceptionv4.c:232:gst_inceptionv4_postprocess:<net> Postprocess
0:00:12.365271548  4675      0x10ee590 LOG              inceptionv4 gstinceptionv4.c:253:gst_inceptionv4_postprocess:<net> Highest probability is label 774 : (0.196048)
0:00:12.365421435  4675      0x10ee590 LOG              inceptionv4 gstinceptionv4.c:200:gst_inceptionv4_preprocess:<net> Preprocess
0:00:12.530604726  4675      0x10ee590 LOG              inceptionv4 gstinceptionv4.c:232:gst_inceptionv4_postprocess:<net> Postprocess
0:00:12.530700501  4675      0x10ee590 LOG              inceptionv4 gstinceptionv4.c:253:gst_inceptionv4_postprocess:<net> Highest probability is label 774 : (0.179406)
0:00:12.530848565  4675      0x10ee590 LOG              inceptionv4 gstinceptionv4.c:200:gst_inceptionv4_preprocess:<net> Preprocess
0:00:12.697053611  4675      0x10ee590 LOG              inceptionv4 gstinceptionv4.c:232:gst_inceptionv4_postprocess:<net> Postprocess
0:00:12.697147818  4675      0x10ee590 LOG              inceptionv4 gstinceptionv4.c:253:gst_inceptionv4_postprocess:<net> Highest probability is label 774 : (0.144033)
0:00:12.697295530  4675      0x10ee590 LOG              inceptionv4 gstinceptionv4.c:200:gst_inceptionv4_preprocess:<net> Preprocess
0:00:12.862007878  4675      0x10ee590 LOG              inceptionv4 gstinceptionv4.c:232:gst_inceptionv4_postprocess:<net> Postprocess
0:00:12.862104134  4675      0x10ee590 LOG              inceptionv4 gstinceptionv4.c:253:gst_inceptionv4_postprocess:<net> Highest probability is label 774 : (0.157707)
0:00:12.862252645  4675      0x10ee590 LOG              inceptionv4 gstinceptionv4.c:200:gst_inceptionv4_preprocess:<net> Preprocess
0:00:13.027090881  4675      0x10ee590 LOG              inceptionv4 gstinceptionv4.c:232:gst_inceptionv4_postprocess:<net> Postprocess
0:00:13.027190273  4675      0x10ee590 LOG              inceptionv4 gstinceptionv4.c:253:gst_inceptionv4_postprocess:<net> Highest probability is label 774 : (0.142998)

Inceptionv4 visualization with classification overlay TensorFlow-Lite

• Get the graph used on this example from this link
• You will need a camera compatible with Nvidia Libargus API or V4l2.

Nvidia Camera

• Pipeline

SENSOR_ID=0
MODEL_LOCATION='graph_inceptionv4.tflite'
LABELS='labels.txt'
gst-launch-1.0 \
nvcamerasrc sensor-id=$SENSOR_ID ! 'video/x-raw(memory:NVMM)' ! tee name=t \
t. ! queue max-size-buffers=1 leaky=downstream ! nvvidconv ! 'video/x-raw,format=(string)RGBA' ! net.sink_model \
t. ! queue max-size-buffers=1 leaky=downstream ! nvvidconv ! 'video/x-raw,format=(string)RGBA' ! net.sink_bypass \
inceptionv4 name=net backend=tflite model-location=$MODEL_LOCATION labels="(cat $LABELS)" \
net.src_bypass ! classificationoverlay labels="$(cat $LABELS)" font-scale=4 thickness=4 ! nvvidconv ! nvoverlaysink sync=false -v

V4L2

• Pipeline

CAMERA='/dev/video1'
MODEL_LOCATION='graph_inceptionv4.tflite'
LABELS='labels.txt'
gst-launch-1.0 \
v4l2src device=$CAMERA ! "video/x-raw, width=1280, height=720" ! tee name=t \
t. ! videoconvert ! videoscale ! queue ! net.sink_model \
t. ! queue ! net.sink_bypass \
inceptionv4 name=net backend=tflite model-location=$MODEL_LOCATION labels="(cat $LABELS)" \
net.src_bypass ! videoconvert ! classificationoverlay labels="$(cat $LABELS)" font-scale=4 thickness=4 ! videoconvert ! xvimagesink sync=false

• Output

Example classification overlay output

TinyYolov2 inference on image file using TensorFlow-Lite

• Get the graph used on this example from this link
• You will need an image file from one of TinyYOLO classes
• Pipeline

IMAGE_FILE='cat.jpg'
MODEL_LOCATION='graph_tinyyolov2.tflite'
LABELS='labels.txt'
GST_DEBUG=tinyyolov2:6 gst-launch-1.0 \
multifilesrc location=$IMAGE_FILE ! jpegparse ! nvjpegdec ! 'video/x-raw' ! nvvidconv ! 'video/x-raw(memory:NVMM),format=NV12' ! nvvidconv ! queue ! net.sink_model \
tinyyolov2 name=net backend=tflite model-location=$MODEL_LOCATION labels="(cat $LABELS)"

• Output

0:00:07.137677204 30513       0x5accf0 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:07.266928985 30513       0x5accf0 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:07.267080761 30513       0x5accf0 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:7, x:25.820670, y:11.977936, width:425.495203, height:450.224357, prob:15.204609]
0:00:07.267382968 30513       0x5accf0 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:07.394225925 30513       0x5accf0 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:07.394431653 30513       0x5accf0 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:7, x:25.820670, y:11.977936, width:425.495203, height:450.224357, prob:15.204609]
0:00:07.394858915 30513       0x5accf0 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:07.527547133 30513       0x5accf0 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:07.527753020 30513       0x5accf0 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:7, x:25.820670, y:11.977936, width:425.495203, height:450.224357, prob:15.204609]
0:00:07.528080219 30513       0x5accf0 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:07.662473455 30513       0x5accf0 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:07.662769998 30513       0x5accf0 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:7, x:25.820670, y:11.977936, width:425.495203, height:450.224357, prob:15.204609]

TinyYolov2 inference on video file using TensorFlow-Lite

• Get the graph used on this example from this link
• You will need a video file from one of TinyYOLO classes
• Pipeline

VIDEO_FILE='cat.mp4'
MODEL_LOCATION='graph_tinyyolov2.tflite'
LABELS='labels.txt'
GST_DEBUG=tinyyolov2:6 gst-launch-1.0 \
filesrc location=$VIDEO_FILE ! qtdemux name=demux ! h264parse ! omxh264dec ! nvvidconv ! queue ! net.sink_model \
tinyyolov2 name=net backend=tflite model-location=$MODEL_LOCATION labels="(cat $LABELS)"

• Output

0:00:07.245722660 30545       0x5ad000 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:07.360377432 30545       0x5ad000 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:07.360586455 30545       0x5ad000 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:7, x:-46.105452, y:-9.139365, width:445.139551, height:487.967720, prob:14.592537]
0:00:07.360859318 30545       0x5ad000 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:07.489190714 30545       0x5ad000 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:07.489382873 30545       0x5ad000 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:7, x:-46.140270, y:-9.193503, width:445.228762, height:488.028163, prob:14.596972]
0:00:07.489736216 30545       0x5ad000 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:07.629190069 30545       0x5ad000 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:07.629379733 30545       0x5ad000 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:7, x:-46.281640, y:-9.164348, width:445.512899, height:487.908826, prob:14.596945]
0:00:07.629717876 30545       0x5ad000 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:07.761072493 30545       0x5ad000 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:07.761271244 30545       0x5ad000 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:7, x:-46.338202, y:-9.202273, width:445.624841, height:487.954952, prob:14.592540]

TinyYolov2 inference on camera stream using TensorFlow-Lite

• Get the graph used on this example from this link
• You will need a camera compatible with Nvidia Libargus API or V4l2.

Nvidia Camera

• Pipeline

SENSOR_ID=0
MODEL_LOCATION='graph_tinyyolov2.tflite'
LABELS='labels.txt'
GST_DEBUG=tinyyolov2:6 gst-launch-1.0 \
nvarguscamerasrc sensor-id=$SENSOR_ID ! nvvidconv ! 'video/x-raw,format=BGRx' ! queue ! net.sink_model \
tinyyolov2 name=net backend=tflite model-location=$MODEL_LOCATION labels="(cat $LABELS)"

V4L2

• Pipeline

CAMERA='/dev/video1'
MODEL_LOCATION='graph_tinyyolov2.tflite'
LABELS='labels.txt'
GST_DEBUG=tinyyolov2:6 gst-launch-1.0 \
v4l2src device=$CAMERA ! videoconvert ! videoscale ! queue ! net.sink_model \
tinyyolov2 name=net model-location=$MODEL_LOCATION backend=tflite labels="$(cat $LABELS)"

• Output

0:00:39.754924355  5030      0x10ee590 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:39.876816786  5030      0x10ee590 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:39.876914225  5030      0x10ee590 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:4, x:147.260736, y:116.184709, width:134.389472, height:245.113627, prob:8.375733]
0:00:39.877085489  5030      0x10ee590 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:39.999699614  5030      0x10ee590 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:39.999799198  5030      0x10ee590 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:4, x:146.957935, y:117.902112, width:134.883825, height:242.143126, prob:7.982772]
0:00:39.999962206  5030      0x10ee590 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:40.118613969  5030      0x10ee590 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:40.118712017  5030      0x10ee590 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:4, x:147.147349, y:116.562615, width:134.469630, height:244.181931, prob:8.139100]
0:00:40.118882641  5030      0x10ee590 LOG               tinyyolov2 gsttinyyolov2.c:479:gst_tinyyolov2_preprocess:<net> Preprocess
0:00:40.264861052  5030      0x10ee590 LOG               tinyyolov2 gsttinyyolov2.c:501:gst_tinyyolov2_postprocess:<net> Postprocess
0:00:40.264964828  5030      0x10ee590 LOG               tinyyolov2 gsttinyyolov2.c:384:print_top_predictions:<net> Box: [class:4, x:146.618516, y:117.162739, width:135.454029, height:243.785573, prob:8.112847]

TinyYolov2 visualization with detection overlay TensorFlow-Lite

• Get the graph used on this example from this link
• You will need a camera compatible with Nvidia Libargus API or V4l2.

Nvidia Camera

• Pipeline

SENSOR_ID=0
MODEL_LOCATION='graph_tinyyolov2.tflite'
LABELS='labels.txt'
GST_DEBUG=tinyyolov2:6 \
gst-launch-1.0 \
nvcamerasrc sensor-id=$SENSOR_ID ! 'video/x-raw(memory:NVMM)' ! tee name=t \
t. ! queue max-size-buffers=1 leaky=downstream ! nvvidconv ! 'video/x-raw,format=(string)RGBA' ! net.sink_model \
t. ! queue max-size-buffers=1 leaky=downstream ! nvvidconv ! 'video/x-raw,format=(string)RGBA' ! net.sink_bypass \
tinyyolov2 name=net backend=tflite model-location=$MODEL_LOCATION labels="(cat $LABELS)" \
net.src_bypass !  detectionoverlay labels="$(cat $LABELS)" font-scale=4 thickness=4  ! nvvidconv ! nvoverlaysink sync=false -v

V4L2

• Pipeline

CAMERA='/dev/video1'
MODEL_LOCATION='graph_tinyyolov2.tflite'
LABELS='labels.txt'
gst-launch-1.0 \
v4l2src device=$CAMERA ! "video/x-raw, width=1280, height=720" ! tee name=t \
t. ! videoconvert ! videoscale ! queue ! net.sink_model \
t. ! queue ! net.sink_bypass \
tinyyolov2 name=net backend=tflite model-location=$MODEL_LOCATION labels="(cat $LABELS)" \
net.src_bypass ! videoconvert ! detectionoverlay labels="$(cat $LABELS)" font-scale=1 thickness=2 ! videoconvert ! xvimagesink sync=false

• Output

Example detection overlay output