# qtimlpostprocess The qtimlpostprocess is a customizable plugin that provides a library interface to postprocess the tensor output of the inference plugins. The postprocessing library is solely responsible to parse the tensor and generate a list of predicted output modes. The plugin manages the module execution, output generation (ML metadata or image mask), batching, ML staging, and other related tasks. settings.json (optional) yolov8.label label.json {“confidence”, 65,“nms-threshold”, 0.5} unlabeledpersonbicyclecarmotorcycleairplanebustraintruckboattraffic lightfire hydrantstreet signstop signparking meterbenchbirdcatdoghorse {”id”, 1, “color”, “0x00FF00FF”, “label”, “unlabeled” },{”id”, 2, “color”, “0x00FF00FF”, “label”, “person” },{”id”, 3, “color”, “0x00FF00FF”, “label”, “bicycle” },{”id”, 4, “color”, “0x00FF00FF”, “label”, “car” },{”id”, 5, “color”, “0x00FF00FF”, “label”, “motorcycle” },{”id”, 6, “color”, “0x00FF00FF”, “label”, “airplane” },{”id”, 7, “color”, “0x00FF00FF”, “label”, “bus” },{”id”, 8, “color”, “0x00FF00FF”, “label”, “train” },{”id”, 9, “color”, “0x00FF00FF”, “label”, “truck” },{”id”, 10, “color”, “0x00FF00FF”, “label”, “boat” },{”id”, 11, “color”, “0x00FF00FF”, “label”, “traffic light” },{”id”, 12, “color”, “0x00FF00FF”, “label”, “fire hydrant” },{”id”, 13, “color”, “0x00FF00FF”, “label”, “street sign” },{”id”, 14, “color”, “0x00FF00FF”, “label”, “stop sign” },{”id”, 15, “color”, “0x00FF00FF”, “label”, “parking meter” },{”id”, 16, “color”, “0x00FF00FF”, “label”, “bench” },{”id”, 17, “color”, “0x00FF00FF”, “label”, “bird” },{”id”, 18, “color”, “0x00FF00FF”, “label”, “cat” },{”id”, 19, “color”, “0x00FF00FF”, “label”, “dog” },{”id”, 20, “color”, “0x00FF00FF”, “label”, “horse” } Post procesing plugin Labels parser Input padneural-network/tensors Output padvideo/x-rawaudio/x-raw The output of thepostprocess dependsfrom the module selected. OR File path only File path orJSON string Maxresults Module(name) Post procesing module JSONsettings Labelfile Labelslookup table Detect format JSON parser Predefinedcolors Comunityparser dlopen of the module GetCaps Configure Predictions **Figure : GstBuffer workflow with qtimlpostprocess** ## Inheritance chain [GObject](https://docs.gtk.org/gobject/) → [GstObject](https://gstreamer.freedesktop.org/documentation/gstreamer/gstobject.html?gi-language=c) → [GstElement](https://gstreamer.freedesktop.org/documentation/gstreamer/gstelement.html?gi-language=c) → [GstBaseTransform](https://gstreamer.freedesktop.org/documentation/base/gstbasetransform.html?gi-language=c) →GstMLPostProcess The following tables provide information on pad templates and element properties of qtimlpostprocess. For use cases, see the segmentation use cases in [LiteRT use cases](https://docs.qualcomm.com/doc/80-80021-50/topic/tensorflow-lite-use-cases.html) and [Qualcomm Neural Processing SDK use cases](https://docs.qualcomm.com/doc/80-80021-50/topic/qualcomm-neural-processing-sdk-use-cases.html). ## Pad configuration | Pad Name | Capabilities | Capabilities | Capabilities | | --- | --- | --- | --- | | SINK template: 'sink'

| neural-network/tensors | – | – | |
SRC template: 'src'

| video/x-raw | format: | { (string)BGRA, (string)RGBA, (string)ARGB, (string)ABGR, (string)RGBx, (string)BGRx, (string)xRGB, (string)xBGR, (string)RGB, (string)BGR, (string)BGR16 } | |
SRC template: 'src'

| text/x-raw | format: | { (string)utf8 } | | | | | | ## Element configuration Table : Element properties for qtimlpostprocess | Property | Description | | --- | --- | | labels | The filename of the labels.

| | module | Module name that's used for processing the tensors.

| | name | The name of the object.

| | parent | The parent of the object.

| | qos | Handle Quality-of-Service events.

| | results | Number of results to display

| | settings | Settings used by the chosen module to postprocess the output. Applicable only for some modules.

| Last Published: Mar 26, 2026 [Previous Topic qtimlqnn](https://docs.qualcomm.com/bundle/publicresource/80-80021-50/topics/qtimlqnn.md) [Next Topic qtimlaclassification](https://docs.qualcomm.com/bundle/publicresource/80-80021-50/topics/qtimlaclassification.md) Source: [https://docs.qualcomm.com/doc/80-80021-50/topic/qtimlpostprocess.html](https://docs.qualcomm.com/doc/80-80021-50/topic/qtimlpostprocess.html)