# Classification

Source: [https://docs.qualcomm.com/doc/80-70015-50/topic/gst-ai-classification.html](https://docs.qualcomm.com/doc/80-70015-50/topic/gst-ai-classification.html)

The **gst-ai-classification** application enables you to identify the subject in
        an image. The use cases use either the Qualcomm Neural Processing SDK runtime or TensorFlow
        Lite (TFLite) runtime.

The figure shows the pipeline, which receives a video stream from a camera, file source,
            or Real-Time Streaming Protocol (RTSP), performs preprocessing, runs inference on the AI
            hardware, and displays the results on the screen.

For information on the plugins used for classification, see [Pipeline flow](https://docs.qualcomm.com/doc/80-70015-50/topic/gst-ai-classification.html#gst-ai-classification__section_j5t_2jq_nbc).

Figure : gst-ai-classification pipeline
            
            ![](data:image/jpeg;base64,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)

## Prerequisites

- To run the application, push the model and label files to the device. For
                    information on downloading the models, see the following:
    - [Download model and label files for Qualcomm Neural Processing SDK](https://docs.qualcomm.com/doc/80-70015-50/topic/ai-ml-sample-applications.html#ai-ml-sample-applications__section_chl_dgz_scc)
    - [Download model and label files for TFLite from AI Hub](https://docs.qualcomm.com/doc/80-70015-50/topic/ai-ml-sample-applications.html#ai-ml-sample-applications__section_fsl_lgz_scc)

    The application supports both the Qualcomm Neural Processing SDK and
                        TFLite models.
- To access your host device, enable SSH. For instructions, see [Use SSH](https://docs.qualcomm.com/bundle/publicresource/topics/80-70015-254/how_to.html#use-ssh).
- Enter the SSH shell and run the use cases:

        ssh root@<ip-addr of the target device>Copy to clipboard
- Enable the
                    display:

        export XDG_RUNTIME_DIR=/dev/socket/weston && export WAYLAND_DISPLAY=wayland-1Copy to clipboard
- Push the files from the host
                    machine:

        scp <filename> root@<IP address of target device>:/opt/Copy to clipboard

## Use cases

Note: For QCS9075, the camera use cases are not supported. Use
                    file or RTSP as input sources.

To run the application, use the following syntax:

    gst-ai-classification --ml-framework= <OPTION>Copy to clipboard

The following list provides the commands to run the application for various use
                cases:

Note: The commands provide the default model and label paths. If
                you have a different folder structure, replace the default paths in the command-line
                parameters.

- Run using Qualcomm Neural Processing SDK
                    runtime:

        gst-ai-classification --ml-framework=1 --model=/opt/inceptionv3.dlc --labels=/opt/classification.labelsCopy to clipboard
- Run using TFLite
                    runtime:

        gst-ai-classification --ml-framework=2 --model=/opt/inception_v3_quantized.tflite  --labels=/opt/classification.labelsCopy to clipboard
- Run using the secondary camera, Qualcomm Neural Processing SDK model, custom
                    model, and label path in command-line
                    parameters.

        gst-ai-classification -c 1 --ml-framework=1 --model=/opt/inceptionv3.dlc -- labels=/opt/classification.labelsCopy to clipboard
- Run using the file source, TFLite model, and GPU runtime. 
    Push the
                            video.mp4 file to the opt
                        folder before executing the
                    command:

        gst-ai-classification -s /opt/video.mp4 --ml-framework=2 --use_gpu --model=/opt/inception_v3_quantized.tflite --labels=/opt/classification.labelsCopy to clipboard
- Run using the RTSP stream input, TFLite model, CPU runtime, custom constants,
                    and custom threshold
                    value:

        gst-ai-classification --rtsp-ip-port=rtsp://<ip-address>/30fps.mkv --ml-framework=2 --constants="Mobilenet,q-offsets=<33.0>,q-scales=<0.18740029633045197>;" --threshold=50 --use_cpu --model=/opt/inception_v3_quantized.tflite --labels=/opt/classification.labelsCopy to clipboard

Display the available help options:

    gst-ai-classification --helpCopy to clipboard

To stop the use case, press CTRL + C.

## Expected output

The classified object is displayed on the local display.

Figure : Expected output for gst-ai-classification application
                
                ![](data:image/png;base64,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)

## Pipeline flow

The table lists the plugins used in the object classification pipeline:| Plugin | Description |
| --- | --- |
| Camera source:[qtiqmmfsrc](https://docs.qualcomm.com/doc/80-70015-50/topic/qtiqmmfsrc.html) | <ul class="ul" id="gst-ai-classification__ul_zyl_gj1_mcc"><br>                                    <li class="li">Captures the live stream from camera.</li><br><br>                                    <li class="li">Uses tee to split the stream for inferencing.</li><br><br>                                </ul> |
| File source: filesrc | <ul class="ul" id="gst-ai-classification__ul_z1z_x4f_w1c"><br>                                    <li class="li">Captures the video stream using filesrc, followed by<br>                                        qtdemux, which demultiplexes the stream.</li><br><br>                                    <li class="li">Uses tee to split the stream for inferencing.</li><br><br>                                </ul> |
| RTSP source: rtspsrc | <ul class="ul" id="gst-ai-classification__ul_vsj_2r4_tbc"><br>                                    <li class="li">Captures the RTSP stream using rtspsrc, followed by<br>                                        rtph264depay for video extraction.</li><br><br>                                    <li class="li">Uses tee to split the stream for inferencing.</li><br><br>                                </ul> |
| h264parse | Parses the H.264 video. |
| [v4l2h264dec](https://docs.qualcomm.com/doc/80-70015-50/topic/v4l2h264dec.html) | Decodes the video. |
| [qtimlvconverter](https://docs.qualcomm.com/doc/80-70015-50/topic/qtimlvconverter.html) | <ol class="ol" id="gst-ai-classification__ol_j34_ddg_q1c"><br>                                    <li class="li">Receives the video stream on its sink pad.</li><br><br>                                    <li class="li">Performs the following preprocessing on the stream data.<br>                                        This preprocessing is done when the model expects<br>                                        floating-point values as input.<ol class="ol" type="a" id="gst-ai-classification__ol_m5z_cpr_lbc"><br>                                            <li class="li">Color conversion</li><br><br>                                            <li class="li">Scaling (up or down)</li><br><br>                                            <li class="li">Normalization</li><br><br>                                        </ol><br></li><br><br>                                    <li class="li">Converts the preprocessed video stream to a tensor stream on<br>                                        its source pad. </li><br><br>                                </ol><br><br>                                <br>The tensor stream is used for inferencing in the later stages of<br>                                    the pipeline. |
| [qtimlsnpe](https://docs.qualcomm.com/doc/80-70015-50/topic/qtimlsnpe.html) and [qtimltflite](https://docs.qualcomm.com/doc/80-70015-50/topic/qtimltflite.html) | **qtimlsnpe**: Acts as the ML inferencing plugin, which is<br>                                    used with the Qualcomm Neural Processing SDK runtime. It uses<br>                                    the Inceptionv3 model for classification.<br><br><br>                                <br>**qtimltflite**: Acts as an alternative option to qtimlsnpe.<br>                                    It runs on the TFLite runtime and uses the quantized version of<br>                                    Inceptionv3 TFLite model for classification.<br><ol class="ol" id="gst-ai-classification__ol_l2x_zjq_nbc"><br>                                    <li class="li"><br>                                        <p class="p">The application runs on the external delegate to run the<br>                                            model using the Qualcomm<sup class="ph sup">®</sup> Hexagon™ Tensor<br>                                            Processor.</p><br><br>                                    </li><br><br>                                    <li class="li">After the inference runtime receives the tensor stream on<br>                                        its sink pad, it runs the inference.</li><br><br>                                    <li class="li">Produces a tensor stream with the inference results on its<br>                                        source pad.</li><br><br>                                </ol> |
| [qtimlvclassification](https://docs.qualcomm.com/doc/80-70015-50/topic/qtimlvclassification.html) | Handles inference results from any classification model.<ol class="ol" id="gst-ai-classification__ol_ol3_dky_kbc"><br>                                    <li class="li">Applies a threshold to the chosen number of results. For<br>                                        quantized model, add Softmax and Constants (q-offsets and<br>                                        q-scales).</li><br><br>                                    <li class="li">Loads the MobileNet postprocessing module. </li><br><br>                                    <li class="li">Produces results as video frames with classification<br>                                        labels.</li><br><br>                                    <li class="li">Sends these processed results to the sink pad of<br>                                        qtivcomposer.</li><br><br>                                </ol> |
| [qtivcomposer](https://docs.qualcomm.com/doc/80-70015-50/topic/qtivcomposer.html) | <ol class="ol" id="gst-ai-classification__ol_dmb_2vr_lbc"><br>                                    <li class="li">Composes frames with contents from its sink pads.</li><br><br>                                    <li class="li">Pushes the GStreamer buffers containing these composed<br>                                        frames to its source pad.</li><br><br>                                </ol> |
| [Waylandsink](https://docs.qualcomm.com/doc/80-70015-50/topic/waylandsink.html) | <ol class="ol" id="gst-ai-classification__ol_kjr_fvr_lbc"><br>                                    <li class="li">Waylandsink submits the video stream received on its sink<br>                                        pad to Weston.</li><br><br>                                    <li class="li">Weston renders the video stream on a local display.</li><br><br>                                </ol> |

## Known issues

The text overlay of the classification object is small.

**Parent Topic:** [AI/ML sample applications](https://docs.qualcomm.com/doc/80-70015-50/topic/ai-ml-sample-applications.html)

Last Published: Oct 27, 2025

[Previous Topic
AI/ML sample applications](https://docs.qualcomm.com/bundle/publicresource/80-70015-50/topics/ai-ml-sample-applications.md) [Next Topic
Object detection](https://docs.qualcomm.com/bundle/publicresource/80-70015-50/topics/gst-ai-object-detection.md)