Difference between revisions of "GstInference/Supported backends/Coral from Google"
m |
|||
| (6 intermediate revisions by 2 users not shown) | |||
| Line 1: | Line 1: | ||
<noinclude> | <noinclude> | ||
| − | {{GstInference/Head|previous=Supported backends/Tensorflow-Lite|next=Supported_backends/TensorRT| | + | {{GstInference/Head|previous=Supported backends/Tensorflow-Lite|next=Supported_backends/TensorRT|metakeywords=GstInference backends,Tensorflow,Google,Jetson-TX2,Jetson-TX1,Xavier,Nvidia,Deep Neural Networks,DNN,DNN Model,Neural Compute API}} |
</noinclude> | </noinclude> | ||
<!-- If you want a custom title for the page, un-comment and edit this line: | <!-- If you want a custom title for the page, un-comment and edit this line: | ||
| Line 6: | Line 6: | ||
--> | --> | ||
| − | {{DISPLAYTITLE:GstInference and | + | {{DISPLAYTITLE:GstInference and Coral backend|noerror}} |
| − | The [https://cloud.google.com/edge-tpu ''' | + | The [https://cloud.google.com/edge-tpu '''Edge TPU'''] is an ASIC designed by Google to provide high-performance machine learning applications that are running on embedded devices. The EdgeTPU library extends the TensorFlow Lite framework. For more information about the Edge TPU hardware go to the [[Google_Coral|Coral dev board]] page. |
| − | To use the | + | To use the Edge TPU backend on Gst-Inference be sure to run the R2Inference configure with the flag <code> -Denable-coral=true</code>. Then, use the property <code> backend=coral</code> on the Gst-Inference plugins. GstInference depends on the C++ API of Tensorflow-Lite. |
==Installation== | ==Installation== | ||
| Line 20: | Line 20: | ||
== Enabling the backend == | == Enabling the backend == | ||
| − | To enable Tensorflow-Lite as a backend for GstInference you need to install R2Inference with TensorFlow-Lite, which is a dependency, and EdgeTPU support. To do this, use the option -- | + | To enable Tensorflow-Lite as a backend for GstInference you need to install R2Inference with TensorFlow-Lite, which is a dependency, and EdgeTPU support. To do this, use the option <code> -Denable-coral=true</code> while following this [[R2Inference/Getting_started/Building_the_library|wiki]] |
==Properties== | ==Properties== | ||
| Line 31: | Line 31: | ||
</syntaxhighlight> | </syntaxhighlight> | ||
| − | For example to change the backend to use Tensorflow-Lite | + | For example to change the backend to use Tensorflow-Lite you need to run the pipeline like this: |
<syntaxhighlight lang="bash"> | <syntaxhighlight lang="bash"> | ||
gst-launch-1.0 \ | gst-launch-1.0 \ | ||
| − | mobilenetv2 name=net model-location=mobilenet_v2_1.0_224_quant_edgetpu.tflite backend= | + | mobilenetv2 name=net model-location=mobilenet_v2_1.0_224_quant_edgetpu.tflite backend=coral \ |
filesrc location=video_stream.mp4 ! decodebin ! videoconvert ! videoscale ! queue ! tee name=t \ | filesrc location=video_stream.mp4 ! decodebin ! videoconvert ! videoscale ! queue ! tee name=t \ | ||
t. ! queue ! videoconvert ! videoscale ! net.sink_model \ | t. ! queue ! videoconvert ! videoscale ! net.sink_model \ | ||
Latest revision as of 14:26, 27 February 2023
 | Make sure you also check GstInference's companion project: R2Inference |
The Edge TPU is an ASIC designed by Google to provide high-performance machine learning applications that are running on embedded devices. The EdgeTPU library extends the TensorFlow Lite framework. For more information about the Edge TPU hardware go to the Coral dev board page.
To use the Edge TPU backend on Gst-Inference be sure to run the R2Inference configure with the flag -Denable-coral=true. Then, use the property backend=coral on the Gst-Inference plugins. GstInference depends on the C++ API of Tensorflow-Lite.
Installation
GstInference depends on the C++ API of Tensorflow-Lite. For installation steps, follow the steps in R2Inference/Building the library section.
TensorFlow Python API and utilities can be installed with python pip, but it is not needed by GstInference.
Enabling the backend
To enable Tensorflow-Lite as a backend for GstInference you need to install R2Inference with TensorFlow-Lite, which is a dependency, and EdgeTPU support. To do this, use the option -Denable-coral=true while following this wiki
Properties
TensorFlow Lite API Reference has full documentation of the Tensorflow-Lite C++ API. Gst-Inference uses only the C++ API of Tensorflow-Lite and R2Inference takes care of devices and loading the models.
The following syntax is used to change backend options on Gst-Inference plugins:
backend::<property>
For example to change the backend to use Tensorflow-Lite you need to run the pipeline like this:
gst-launch-1.0 \
mobilenetv2 name=net model-location=mobilenet_v2_1.0_224_quant_edgetpu.tflite backend=coral \
filesrc location=video_stream.mp4 ! decodebin ! videoconvert ! videoscale ! queue ! tee name=t \
t. ! queue ! videoconvert ! videoscale ! net.sink_model \
t. ! queue ! videoconvert ! net.sink_bypass \
net.src_model ! fakesink
To learn more about the EdgeTPU C++ API, please check the Tensorflow-Lite API section on the R2Inference subwiki.
Tools
The TensorFlow Python API installation includes a tool named Tensorboard, that can be used to visualize a model. If you want some examples and a more complete description please check the Tools section on the R2Inference wiki.
