qtimlesnpe

The QTI's qtimlesnpe GStreamer element exposes Qualcomm Neural Processing SDK capabilities to GStreamer. It can load and execute AI models. It supports preprocessing and post processing functionality. The preprocessing supports downscale, color convert, mean subtraction and padding. The postprocessing supports the most popular model types as classification, detection, and segmentation. The postprocessing result is attached as machine learning metadata (MLMeta) to GST buffer. The QTI's qtimlesnpe GStreamer element support two ways of configuration: config file in JSON format, and GST properties. Each configuration parameter can be set using both ways, but GST properties has higher priority.

Pad templates

sink (input)

Presence – always

Direction – sink

source (output)

Presence – always

Direction – src

Properties

name

The name of the object.

qos

Handle Quality-of-Service events.

config

Path to JSON configuration file. Eg.: /data/misc/camera/mle_snpe_config.json

model

Model file name. Path to model file. Eg.: /data/misc/camera/model.dlc. Filename extension should be .dlc

labels

Labels file name. Path to labels file. Eg.: /data/misc/camera/labels.txt. Filename extension should be .txt

input-format

Set inference input format. Supported formats: 0 - RGB; 1 - BGR; 2 - RGBFloat; 3 - BGRFloat.

postprocessing

Supported Postprocessing: classification; detection; singlessd; segmentation

mean

Channel Mean Subtraction values ('<B, G, R>'). Eg. mean="<128.0,128.0,128.0>"

sigma

Channel divisor values ('<B, G, R>'). Eg. sigma="<128.0,128.0,128.0>"

runtime

SNPE Runtime: 0 - CPU; 1 - DSP

output-layers

Model output layers, comma separated. Should be set if model have more than one output

preprocess-type

Controls pre-processing aspect ration(AR) maintenance.

Possible values: 0-kKeepARCrop, 1-kKeepARPad, 2-kDirectDownscale

confidence-threshold

Confidence threshold value.