20,290
edits
GstInference/Example pipelines/NANO: Difference between revisions
GstInference/Example pipelines/NANO (view source)
Revision as of 15:29, 18 January 2020
, 18 January 2020no edit summary
(Center image and update tinyYolo Image) |
mNo edit summary |
||
| Line 94: | Line 94: | ||
*Output | *Output | ||
[[File:Inceptionv2 barber.png|center|thumb|inceptionv2_barberchair]] | [[File:Inceptionv2 barber.png|center|thumb|inceptionv2_barberchair]] | ||
== InceptionV1 == | |||
===RTSP Camera stream=== | |||
* Get the graph used on this example from [https://shop.ridgerun.com/products/inceptionv1-for-tensorflow this link] | |||
* You will need a v4l2 compatible camera | |||
'''Server Pipeline''' which runs on the host PC | |||
<syntaxhighlight lang=bash> | |||
gst-launch-1.0 -e v4l2src device=/dev/video0 ! video/x-raw, format=YUY2, width=640, height=480, framerate=30/1 ! videoconvert ! video/x-raw, format=I420, width=640, height=480, framerate=30/1 ! queue ! x265enc option-string="keyint=30:min-keyint=30:repeat-headers=1" ! video/x-h265, width=640, height=480, mapping=/stream1 ! queue ! rtspsink service=5000 | |||
</syntaxhighlight> | |||
'''Client Pipeline''' which runs on the NANO board | |||
<syntaxhighlight lang=bash> | |||
CAMERA='/dev/video0' | |||
MODEL_LOCATION='graph_inceptionv1_tensorflow.pb' | |||
INPUT_LAYER='input' | |||
OUTPUT_LAYER='InceptionV1/Logits/Predictions/Reshape_1' | |||
GST_DEBUG=inceptionv1:6 gst-launch-1.0 -e rtspsrc location="rtsp://<server_ip_address>:5000/stream1" ! queue ! rtph265depay ! queue ! h265parse ! queue ! omxh265dec ! queue ! nvvidconv ! queue ! net.sink_model inceptionv1 name=net model-location=$MODEL_LOCATION backend=tensorflow backend::input-layer=$INPUT_LAYER backend::output-layer=$OUTPUT_LAYER | |||
</syntaxhighlight> | |||
* Output | |||
<syntaxhighlight lang=bash> | |||
</syntaxhighlight> | |||
==TinyYoloV2== | ==TinyYoloV2== | ||