GstInference/Metadatas/GstEmbeddingMeta: Difference between revisions
Maumontero (talk | contribs) No edit summary |
mNo edit summary |
||
Line 6: | Line 6: | ||
{{DISPLAYTITLE:GstInference - <descriptive page name>|noerror}} | {{DISPLAYTITLE:GstInference - <descriptive page name>|noerror}} | ||
--> | --> | ||
{{DISPLAYTITLE:GstInference and GstEmbeddingMeta metadata|noerror}} | |||
This metadata consist on a variable size elements array, that is filed with the embedding produced by the net, like facenet that uses a 128 elements array size. | This metadata consist on a variable size elements array, that is filed with the embedding produced by the net, like facenet that uses a 128 elements array size. | ||
Line 11: | Line 13: | ||
[[File:gst_inference_GstEmbeddingMetaf.png|500px|center|thumb|GstEmbeddingMeta example]] | [[File:gst_inference_GstEmbeddingMetaf.png|500px|center|thumb|GstEmbeddingMeta example]] | ||
=Fields= | ==Fields== | ||
The facenet element and embedding overlay uses similar metadata as the classification plugins. GstEmbeddingMeta consist on the following fields: | The facenet element and embedding overlay uses similar metadata as the classification plugins. GstEmbeddingMeta consist on the following fields: | ||
Line 29: | Line 31: | ||
|} | |} | ||
=Access metadata= | ==Access metadata== | ||
If you want to access this metadata from your custom Gstreamer element instead the process is fairly easy: | If you want to access this metadata from your custom Gstreamer element instead the process is fairly easy: | ||
# Add the [[GstInference/Supported architectures/FaceNet|Facenet]] element to your pipeline | # Add the [[GstInference/Supported architectures/FaceNet|Facenet]] element to your pipeline |
Revision as of 18:56, 31 January 2020
Make sure you also check GstInference's companion project: R2Inference |
GstInference |
---|
Introduction |
Getting started |
Supported architectures |
InceptionV1 InceptionV3 YoloV2 AlexNet |
Supported backends |
Caffe |
Metadata and Signals |
Overlay Elements |
Utils Elements |
Legacy pipelines |
Example pipelines |
Example applications |
Benchmarks |
Model Zoo |
Project Status |
Contact Us |
|
This metadata consist on a variable size elements array, that is filed with the embedding produced by the net, like facenet that uses a 128 elements array size.
Fields
The facenet element and embedding overlay uses similar metadata as the classification plugins. GstEmbeddingMeta consist on the following fields:
field | type | description |
---|---|---|
num_dimensions | gint | The number of labels outputted by the model. This can vary from model to model. Facenet uses 128. |
embedding | gdouble * | The embedding produced by the network |
Access metadata
If you want to access this metadata from your custom Gstreamer element instead the process is fairly easy:
- Add the Facenet element to your pipeline
- Include GstInference metadata header:
#include "gst/r2inference/gstinferencemeta.h"
- Get a GstClassificationMeta object from the buffer:
class_meta = (GstClassificationMeta *) gst_buffer_get_meta (frame->buffer, GST_CLASSIFICATION_META_API_TYPE);
FaceNet also raises a signal containing GstClassificationMeta, for details on how to use this signal please check the example applications section.
In the following section of code, we add the include like in point 2 and safe the GstClassificationMeta in the class_meta variable like in point 3.
#include "gst/r2inference/gstinferencemeta.h" static void get_buffer(GstPadProbeInfo * info) { GstBuffer *buffer; GstDetectionMeta *meta; buffer = gst_pad_probe_info_get_buffer (info); class_meta = (GstClassificationMeta *) gst_buffer_get_meta (buffer, GST_DETECTION_META_API_TYPE); g_print ("Dimension: 0 has embedding %f\n", class_meta->embedding[0]); }