61
edits
(Add main pipelines examples for the nano) |
m (Change titles and and previous and next section) |
||
Line 1: | Line 1: | ||
<noinclude> | |||
{{GstInference/Head|previous=Example pipelines/PC|next=Example pipelines/TX2|keywords=GstInference}} | |||
</noinclude> | |||
<!-- If you want a custom title for the page, un-comment and edit this line: | |||
{{DISPLAYTITLE:GstInference - <descriptive page name>|noerror}} | |||
--> | |||
= Tensorflow = | = Tensorflow = | ||
Line 8: | Line 13: | ||
* Use the following pipelines as examples for different scenarios. | * Use the following pipelines as examples for different scenarios. | ||
=== | ===Inceptionv4 inference on image file using Tensorflow=== | ||
<syntaxhighlight lang=bash> | <syntaxhighlight lang=bash> | ||
Line 30: | Line 35: | ||
</syntaxhighlight> | </syntaxhighlight> | ||
=== | ===Inceptionv4 inference on video file using TensorFlow=== | ||
<syntaxhighlight lang=bash> | <syntaxhighlight lang=bash> | ||
Line 51: | Line 56: | ||
</syntaxhighlight> | </syntaxhighlight> | ||
=== | ===Inceptionv4 inference on camera stream using TensorFlow=== | ||
<syntaxhighlight lang=bash> | <syntaxhighlight lang=bash> | ||
CAMERA='/dev/video0' | CAMERA='/dev/video0' | ||
Line 72: | Line 77: | ||
==TinyYOLOV2== | ==TinyYOLOV2== | ||
=== | * Get the graph used on this example from [https://shop.ridgerun.com/products/tinyyolov2-for-tensorflow this link] | ||
* You will need an image file from one of TinyYOLO classes | |||
===TinyYolov2 inference on image file using Tensorflow=== | |||
<syntaxhighlight lang=bash> | <syntaxhighlight lang=bash> | ||
IMAGE_FILE='cat.jpg' | IMAGE_FILE='cat.jpg' | ||
Line 89: | Line 97: | ||
</syntaxhighlight> | </syntaxhighlight> | ||
=== | ===TinyYolov2 inference on video file using Tensorflow=== | ||
<syntaxhighlight lang=bash> | <syntaxhighlight lang=bash> | ||
VIDEO_FILE='cat.mp4' | VIDEO_FILE='cat.mp4' | ||
Line 107: | Line 115: | ||
</syntaxhighlight> | </syntaxhighlight> | ||
=== | ===TinyYolov2 inference on camera stream using Tensorflow=== | ||
* Get the graph used on this example from [https://shop.ridgerun.com/products/facenetv1-for-tensorflow 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. | |||
<syntaxhighlight lang=bash> | <syntaxhighlight lang=bash> | ||
CAMERA='/dev/video0' | CAMERA='/dev/video0' |
edits