> ## Documentation Index
> Fetch the complete documentation index at: https://imsdkdocs.qualcomm.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Semantic Segmentation

> QIM SDK supported models for Semantic Segmentation

***

<Tabs>
  <Tab title="TFLite Runtime">
    <div style={{overflowX:"auto",borderRadius:"10px",boxShadow:"0 2px 12px rgba(50,83,220,0.10)",overflow:"hidden"}}>
      <table style={{width:"100%",borderCollapse:"collapse",fontSize:"0.85rem",border:"2px solid #3253DC"}}>
        <colgroup>
          <col style={{width:"40px"}} />

          <col style={{width:"220px"}} />

          <col style={{width:"100%"}} />
        </colgroup>

        <thead>
          <tr>
            <th style={{backgroundColor:"#3253DC",color:"#ffffff",border:"1px solid #000000",padding:"10px 8px",textAlign:"center",letterSpacing:"0.05em",width:"40px"}}>No.</th>
            <th style={{backgroundColor:"#3253DC",color:"#ffffff",border:"1px solid #000000",padding:"10px 8px",textAlign:"center",letterSpacing:"0.05em",width:"220px"}}>Model Name</th>
            <th style={{backgroundColor:"#3253DC",color:"#ffffff",border:"1px solid #000000",padding:"10px 8px",textAlign:"center",letterSpacing:"0.05em"}}>Description</th>
          </tr>
        </thead>

        <tbody>
          <tr>
            <td rowSpan={2} style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"center",verticalAlign:"middle",width:"40px"}}>1</td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"left",verticalAlign:"middle",width:"180px"}}><a href="https://aihub.qualcomm.com/iot/models/deeplabv3_plus_mobilenet?searchTerm=DeepLabV3-Plus-MobileNet" target="_blank" style={{color:"#3253DC",fontWeight:600}}>DeepLabV3-Plus-MobileNet</a></td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",color:"#555",fontSize:"0.82rem",verticalAlign:"middle"}}>Atrous separable convolutions with encoder-decoder for segmentation.</td>
          </tr>

          <tr>
            <td colSpan={2} style={{border:"1px solid #e2e8f0",padding:"4px",verticalAlign:"top",width:"100%"}}>
              {/* yaml_id: 11 */}

              <Accordion title="Steps to Run on QIMSDK">
                <Accordion title="🟢 W8A8 — Model Precision">
                  <Steps>
                    <Step title="Download Required Files">
                      | File                                                                                                                                                   | Save as                                 |
                      | ------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------- |
                      | [Model](https://aihub.qualcomm.com/iot/models/deeplabv3_plus_mobilenet?searchTerm=DeepLabV3-Plus-MobileNet)                                            | deeplabv3\_plus\_mobilenet\_w8a8.tflite |
                      | <a href="../labels/dv3-argmax.json" download="dv3-argmax.json">dv3-argmax.json</a>                                                                     | dv3-argmax.json                         |
                      | <a href="https://github.com/qualcomm/sample-apps-for-qualcomm-linux/raw/refs/heads/main/qualcomm-linux/artifacts/videos/demo_samples/">Input video</a> | ai\_demo\_sample.mp4                    |

                      <Note>
                        If any downloaded file is a `.zip` archive, extract it on your host machine before copying:
                        `unzip filename.zip`
                      </Note>
                    </Step>

                    <Step title="Copy Files to Device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Replace $HOME to the appropriate device path before running the commands.
                        # For QLI:    /root
                        # For Ubuntu: /home/ubuntu
                        # Modify this based on your platform and ensure files are copied to the correct location on the device.

                        ssh <user>@<device-ip> "mkdir -p $HOME/{models,labels,media,media/output}"
                        scp deeplabv3_plus_mobilenet_w8a8.tflite   <user>@<device-ip>:$HOME/models/
                        scp dv3-argmax.json                        <user>@<device-ip>:$HOME/labels/
                        scp ai_demo_sample.mp4              <user>@<device-ip>:$HOME/media/
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Connect to device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Run from your host machine — replace <user> and <device-ip>
                        ssh <user>@<device-ip>
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Set Environment Variables">
                      ```bash Qualcomm Linux theme={null}
                      export MODEL_NAME=deeplabv3_plus_mobilenet_w8a8.tflite
                      export LABELS_NAME=dv3-argmax.json
                      export SRC_VIDEO_NAME=ai_demo_sample.mp4
                      ```
                    </Step>

                    <Step title="Run the Pipeline">
                      ```bash theme={null}
                      gst-launch-1.0 -e --gst-debug=2 \
                      filesrc location=$HOME/media/$SRC_VIDEO_NAME ! qtdemux ! h264parse ! \
                      v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! \
                      tee name=t \
                      t. ! queue ! qtivcomposer name=seg_mix sink_1::alpha=0.5 ! queue ! waylandsink fullscreen=true sync=true \
                      t. ! queue ! qtimlvconverter ! queue ! \
                      qtimltflite model=$HOME/models/$MODEL_NAME delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp,log_level=(string)1;" ! queue ! \
                      qtimlpostprocess module=deeplab-argmax labels=$HOME/labels/$LABELS_NAME ! video/x-raw,format=BGRA,width=520,height=520 ! queue ! seg_mix.
                      ```
                    </Step>
                  </Steps>
                </Accordion>
              </Accordion>
            </td>
          </tr>

          <tr>
            <td rowSpan={2} style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"center",verticalAlign:"middle",width:"40px"}}>2</td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"left",verticalAlign:"middle",width:"180px"}}><a href="https://aihub.qualcomm.com/iot/models/fcn_resnet50" target="_blank" style={{color:"#3253DC",fontWeight:600}}>FCN-ResNet50</a></td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",color:"#555",fontSize:"0.82rem",verticalAlign:"middle"}}>Fully convolutional network for dense pixel classification.</td>
          </tr>

          <tr>
            <td colSpan={2} style={{border:"1px solid #e2e8f0",padding:"4px",verticalAlign:"top",width:"100%"}}>
              <Accordion title="Steps to Run on QIMSDK">
                <Accordion title="🟢 W8A8 — Model Precision">
                  <Steps>
                    <Step title="Download Required Files">
                      | File                                                                                                                                                 | Save as                                |
                      | ---------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------- |
                      | [Model](https://aihub.qualcomm.com/iot/models/fcn_resnet50)                                                                                          | fcn\_resnet50\_w8a8.tflite             |
                      | <a href="../labels/dv3-argmax.json" download="dv3-argmax.json">dv3-argmax.json</a>                                                                   | dv3-argmax.json                        |
                      | <a href="/sample-videos/Street_Bridge_1080p_180s_30FPS.MOV" download="Street_Bridge_1080p_180s_30FPS.MOV">Street\_Bridge\_1080p\_180s\_30FPS.MOV</a> | Street\_Bridge\_1080p\_180s\_30FPS.MOV |

                      <Note>
                        If any downloaded file is a `.zip` archive, extract it on your host machine before copying:
                        `unzip filename.zip`
                      </Note>
                    </Step>

                    <Step title="Copy Files to Device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Replace $HOME to the appropriate device path before running the commands.
                        # For QLI:    /root
                        # For Ubuntu: /home/ubuntu
                        # Modify this based on your platform and ensure files are copied to the correct location on the device.

                        ssh <user>@<device-ip> "mkdir -p $HOME/{models,labels,media,media/output}"
                        scp fcn_resnet50_w8a8.tflite                <user>@<device-ip>:$HOME/models/
                        scp dv3-argmax.json                         <user>@<device-ip>:$HOME/labels/
                        scp Street_Bridge_1080p_180s_30FPS.MOV      <user>@<device-ip>:$HOME/media/
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Connect to device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Run from your host machine — replace <user> and <device-ip>
                        ssh <user>@<device-ip>
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Set Environment Variables">
                      ```bash Qualcomm Linux theme={null}
                      export MODEL_NAME=fcn_resnet50_w8a8.tflite
                      export LABELS_NAME=dv3-argmax.json
                      export SRC_VIDEO_NAME=Street_Bridge_1080p_180s_30FPS.MOV
                      ```
                    </Step>

                    <Step title="Run the Pipeline">
                      ```bash theme={null}
                      gst-launch-1.0 -e --gst-debug=2 \
                      filesrc location=$HOME/media/$SRC_VIDEO_NAME ! qtdemux ! h264parse ! \
                      v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! \
                      tee name=t \
                      t. ! queue ! qtivcomposer name=seg_mix sink_1::alpha=0.5 ! queue ! waylandsink fullscreen=true sync=true \
                      t. ! queue ! qtimlvconverter ! queue ! \
                      qtimltflite model=$HOME/models/$MODEL_NAME delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp,log_level=(string)1;" ! queue ! \
                      qtimlpostprocess module=deeplab-argmax labels=$HOME/labels/$LABELS_NAME ! video/x-raw,format=BGRA,width=520,height=520 ! queue ! seg_mix.
                      ```
                    </Step>
                  </Steps>
                </Accordion>
              </Accordion>
            </td>
          </tr>

          <tr>
            <td rowSpan={2} style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"center",verticalAlign:"middle",width:"40px"}}>3</td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"left",verticalAlign:"middle",width:"180px"}}><a href="https://aihub.qualcomm.com/iot/models/ffnet_122ns_lowres" target="_blank" style={{color:"#3253DC",fontWeight:600}}>FFNet-122NS-LowRes</a></td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",color:"#555",fontSize:"0.82rem",verticalAlign:"middle"}}>Fast Fusion Network for real-time semantic segmentation.</td>
          </tr>

          <tr>
            <td colSpan={2} style={{border:"1px solid #e2e8f0",padding:"4px",verticalAlign:"top",width:"100%"}}>
              {/* yaml_id: 14 */}

              <Accordion title="Steps to Run on QIMSDK">
                <Accordion title="🟢 W8A8 — Model Precision">
                  <Steps>
                    <Step title="Download Required Files">
                      | File                                                                                                                                                 | Save as                                |
                      | ---------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------- |
                      | [Model](https://aihub.qualcomm.com/iot/models/ffnet_122ns_lowres)                                                                                    | ffnet\_122ns\_lowres\_w8a8.tflite      |
                      | <a href="../labels/dv3-argmax.json" download="dv3-argmax.json">dv3-argmax.json</a>                                                                   | dv3-argmax.json                        |
                      | <a href="/sample-videos/Street_Bridge_1080p_180s_30FPS.MOV" download="Street_Bridge_1080p_180s_30FPS.MOV">Street\_Bridge\_1080p\_180s\_30FPS.MOV</a> | Street\_Bridge\_1080p\_180s\_30FPS.MOV |

                      <Note>
                        If any downloaded file is a `.zip` archive, extract it on your host machine before copying:
                        `unzip filename.zip`
                      </Note>
                    </Step>

                    <Step title="Copy Files to Device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Replace $HOME to the appropriate device path before running the commands.
                        # For QLI:    /root
                        # For Ubuntu: /home/ubuntu
                        # Modify this based on your platform and ensure files are copied to the correct location on the device.

                        ssh <user>@<device-ip> "mkdir -p $HOME/{models,labels,media,media/output}"
                        scp ffnet_122ns_lowres_w8a8.tflite      <user>@<device-ip>:$HOME/models/
                        scp dv3-argmax.json                     <user>@<device-ip>:$HOME/labels/
                        scp Street_Bridge_1080p_180s_30FPS.MOV  <user>@<device-ip>:$HOME/media/
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Connect to device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Run from your host machine — replace <user> and <device-ip>
                        ssh <user>@<device-ip>
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Set Environment Variables">
                      ```bash Qualcomm Linux theme={null}
                      export MODEL_NAME=ffnet_122ns_lowres_w8a8.tflite
                      export LABELS_NAME=dv3-argmax.json
                      export SRC_VIDEO_NAME=Street_Bridge_1080p_180s_30FPS.MOV
                      ```
                    </Step>

                    <Step title="Run the Pipeline">
                      ```bash theme={null}
                      gst-launch-1.0 -e --gst-debug=2 \
                      filesrc location=$HOME/media/$SRC_VIDEO_NAME ! qtdemux ! h264parse ! \
                      v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! \
                      tee name=t \
                      t. ! queue ! qtivcomposer name=seg_mix sink_1::alpha=0.5 ! queue ! waylandsink fullscreen=true sync=true \
                      t. ! queue ! qtimlvconverter ! queue ! \
                      qtimltflite model=$HOME/models/$MODEL_NAME delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp,log_level=(string)1;" ! queue ! \
                      qtimlpostprocess module=deeplab-argmax labels=$HOME/labels/$LABELS_NAME ! video/x-raw,format=BGRA,width=520,height=520 ! queue ! seg_mix.
                      ```
                    </Step>
                  </Steps>
                </Accordion>
              </Accordion>
            </td>
          </tr>

          <tr>
            <td rowSpan={2} style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"center",verticalAlign:"middle",width:"40px"}}>4</td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"left",verticalAlign:"middle",width:"180px"}}><a href="https://aihub.qualcomm.com/iot/models/ffnet_78s_lowres" target="_blank" style={{color:"#3253DC",fontWeight:600}}>FFNet-78S-LowRes</a></td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",color:"#555",fontSize:"0.82rem",verticalAlign:"middle"}}>Compact FFNet variant balancing speed and accuracy.</td>
          </tr>

          <tr>
            <td colSpan={2} style={{border:"1px solid #e2e8f0",padding:"4px",verticalAlign:"top",width:"100%"}}>
              {/* yaml_id: 16 */}

              <Accordion title="Steps to Run on QIMSDK">
                <Accordion title="🟢 W8A8 — Model Precision">
                  <Steps>
                    <Step title="Download Required Files">
                      | File                                                                                                                                                 | Save as                                |
                      | ---------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------- |
                      | [Model](https://aihub.qualcomm.com/iot/models/ffnet_78s_lowres)                                                                                      | ffnet\_78s\_lowres\_w8a8.tflite        |
                      | <a href="../labels/dv3-argmax.json" download="dv3-argmax.json">dv3-argmax.json</a>                                                                   | dv3-argmax.json                        |
                      | <a href="/sample-videos/Street_Bridge_1080p_180s_30FPS.MOV" download="Street_Bridge_1080p_180s_30FPS.MOV">Street\_Bridge\_1080p\_180s\_30FPS.MOV</a> | Street\_Bridge\_1080p\_180s\_30FPS.MOV |

                      <Note>
                        If any downloaded file is a `.zip` archive, extract it on your host machine before copying:
                        `unzip filename.zip`
                      </Note>
                    </Step>

                    <Step title="Copy Files to Device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Replace $HOME to the appropriate device path before running the commands.
                        # For QLI:    /root
                        # For Ubuntu: /home/ubuntu
                        # Modify this based on your platform and ensure files are copied to the correct location on the device.

                        ssh <user>@<device-ip> "mkdir -p $HOME/{models,labels,media,media/output}"
                        scp ffnet_78s_lowres_w8a8.tflite        <user>@<device-ip>:$HOME/models/
                        scp dv3-argmax.json                     <user>@<device-ip>:$HOME/labels/
                        scp Street_Bridge_1080p_180s_30FPS.MOV  <user>@<device-ip>:$HOME/media/
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Connect to device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Run from your host machine — replace <user> and <device-ip>
                        ssh <user>@<device-ip>
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Set Environment Variables">
                      ```bash Qualcomm Linux theme={null}
                      export MODEL_NAME=ffnet_78s_lowres_w8a8.tflite
                      export LABELS_NAME=dv3-argmax.json
                      export SRC_VIDEO_NAME=Street_Bridge_1080p_180s_30FPS.MOV
                      ```
                    </Step>

                    <Step title="Run the Pipeline">
                      ```bash theme={null}
                      gst-launch-1.0 -e --gst-debug=2 \
                      filesrc location=$HOME/media/$SRC_VIDEO_NAME ! qtdemux ! h264parse ! \
                      v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! \
                      tee name=t \
                      t. ! queue ! qtivcomposer name=seg_mix sink_1::alpha=0.5 ! queue ! waylandsink fullscreen=true sync=true \
                      t. ! queue ! qtimlvconverter ! queue ! \
                      qtimltflite model=$HOME/models/$MODEL_NAME delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp,log_level=(string)1;" ! queue ! \
                      qtimlpostprocess module=deeplab-argmax labels=$HOME/labels/$LABELS_NAME ! video/x-raw,format=BGRA,width=520,height=520 ! queue ! seg_mix.
                      ```
                    </Step>
                  </Steps>
                </Accordion>
              </Accordion>
            </td>
          </tr>

          <tr>
            <td rowSpan={2} style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"center",verticalAlign:"middle",width:"40px"}}>5</td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"left",verticalAlign:"middle",width:"180px"}}><a href="https://aihub.qualcomm.com/iot/models/pidnet?searchTerm=pid" target="_blank" style={{color:"#3253DC",fontWeight:600}}>PidNet</a></td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",color:"#555",fontSize:"0.82rem",verticalAlign:"middle"}}>Parallel information distillation network for real-time segmentation.</td>
          </tr>

          <tr>
            <td colSpan={2} style={{border:"1px solid #e2e8f0",padding:"4px",verticalAlign:"top",width:"100%"}}>
              {/* yaml_id: 18 */}

              <Accordion title="Steps to Run on QIMSDK">
                <Accordion title="🟢 W8A8 — Model Precision">
                  <Steps>
                    <Step title="Download Required Files">
                      | File                                                                                                                                                 | Save as                                |
                      | ---------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------- |
                      | [Model](https://aihub.qualcomm.com/iot/models/pidnet?searchTerm=pid)                                                                                 | pidnet\_w8a8.tflite                    |
                      | <a href="../labels/dv3-argmax.json" download="dv3-argmax.json">dv3-argmax.json</a>                                                                   | dv3-argmax.json                        |
                      | <a href="/sample-videos/Street_Bridge_1080p_180s_30FPS.MOV" download="Street_Bridge_1080p_180s_30FPS.MOV">Street\_Bridge\_1080p\_180s\_30FPS.MOV</a> | Street\_Bridge\_1080p\_180s\_30FPS.MOV |

                      <Note>
                        If any downloaded file is a `.zip` archive, extract it on your host machine before copying:
                        `unzip filename.zip`
                      </Note>
                    </Step>

                    <Step title="Copy Files to Device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Replace $HOME to the appropriate device path before running the commands.
                        # For QLI:    /root
                        # For Ubuntu: /home/ubuntu
                        # Modify this based on your platform and ensure files are copied to the correct location on the device.

                        ssh <user>@<device-ip> "mkdir -p $HOME/{models,labels,media,media/output}"
                        scp pidnet_w8a8.tflite                  <user>@<device-ip>:$HOME/models/
                        scp dv3-argmax.json                     <user>@<device-ip>:$HOME/labels/
                        scp Street_Bridge_1080p_180s_30FPS.MOV  <user>@<device-ip>:$HOME/media/
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Connect to device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Run from your host machine — replace <user> and <device-ip>
                        ssh <user>@<device-ip>
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Set Environment Variables">
                      ```bash Qualcomm Linux theme={null}
                      export MODEL_NAME=pidnet_w8a8.tflite
                      export LABELS_NAME=dv3-argmax.json
                      export SRC_VIDEO_NAME=Street_Bridge_1080p_180s_30FPS.MOV
                      ```
                    </Step>

                    <Step title="Run the Pipeline">
                      ```bash theme={null}
                      gst-launch-1.0 -e --gst-debug=2 \
                      filesrc location=$HOME/media/$SRC_VIDEO_NAME ! qtdemux ! h264parse ! \
                      v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! \
                      tee name=t \
                      t. ! queue ! qtivcomposer name=seg_mix sink_1::alpha=0.5 ! queue ! waylandsink fullscreen=true sync=true \
                      t. ! queue ! qtimlvconverter ! queue ! \
                      qtimltflite model=$HOME/models/$MODEL_NAME delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp,log_level=(string)1;" ! queue ! \
                      qtimlpostprocess module=deeplab-argmax labels=$HOME/labels/$LABELS_NAME ! video/x-raw,format=BGRA,width=520,height=520 ! queue ! seg_mix.
                      ```
                    </Step>
                  </Steps>
                </Accordion>
              </Accordion>
            </td>
          </tr>

          <tr>
            <td rowSpan={2} style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"center",verticalAlign:"middle",width:"40px"}}>6</td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"left",verticalAlign:"middle",width:"180px"}}><a href="https://aihub.qualcomm.com/iot/models/ddrnet23_slim?searchTerm=DDRNet23-Slim" target="_blank" style={{color:"#3253DC",fontWeight:600}}>DDRNet23-Slim</a></td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",color:"#555",fontSize:"0.82rem",verticalAlign:"middle"}}>Dual-resolution discrepancy network (slim) for fast segmentation.</td>
          </tr>

          <tr>
            <td colSpan={2} style={{border:"1px solid #e2e8f0",padding:"4px",verticalAlign:"top",width:"100%"}}>
              {/* yaml_id: 21 */}

              <Accordion title="Steps to Run on QIMSDK">
                <Accordion title="🟢 W8A8 — Model Precision">
                  <Steps>
                    <Step title="Download Required Files">
                      | File                                                                                                                                                 | Save as                                |
                      | ---------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------- |
                      | [Model](https://aihub.qualcomm.com/iot/models/ddrnet23_slim?searchTerm=DDRNet23-Slim)                                                                | ddrnet23\_slim\_w8a8.tflite            |
                      | <a href="../labels/dv3-argmax.json" download="dv3-argmax.json">dv3-argmax.json</a>                                                                   | dv3-argmax.json                        |
                      | <a href="/sample-videos/Street_Bridge_1080p_180s_30FPS.MOV" download="Street_Bridge_1080p_180s_30FPS.MOV">Street\_Bridge\_1080p\_180s\_30FPS.MOV</a> | Street\_Bridge\_1080p\_180s\_30FPS.MOV |

                      <Note>
                        If any downloaded file is a `.zip` archive, extract it on your host machine before copying:
                        `unzip filename.zip`
                      </Note>
                    </Step>

                    <Step title="Copy Files to Device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Replace $HOME to the appropriate device path before running the commands.
                        # For QLI:    /root
                        # For Ubuntu: /home/ubuntu
                        # Modify this based on your platform and ensure files are copied to the correct location on the device.

                        ssh <user>@<device-ip> "mkdir -p $HOME/{models,labels,media,media/output}"
                        scp ddrnet23_slim_w8a8.tflite           <user>@<device-ip>:$HOME/models/
                        scp dv3-argmax.json                     <user>@<device-ip>:$HOME/labels/
                        scp Street_Bridge_1080p_180s_30FPS.MOV  <user>@<device-ip>:$HOME/media/
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Connect to device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Run from your host machine — replace <user> and <device-ip>
                        ssh <user>@<device-ip>
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Set Environment Variables">
                      ```bash Qualcomm Linux theme={null}
                      export MODEL_NAME=ddrnet23_slim_w8a8.tflite
                      export LABELS_NAME=dv3-argmax.json
                      export SRC_VIDEO_NAME=Street_Bridge_1080p_180s_30FPS.MOV
                      ```
                    </Step>

                    <Step title="Run the Pipeline">
                      ```bash theme={null}
                      gst-launch-1.0 -e --gst-debug=2 \
                      filesrc location=$HOME/media/$SRC_VIDEO_NAME ! qtdemux ! h264parse ! \
                      v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! \
                      tee name=t \
                      t. ! queue ! qtivcomposer name=seg_mix sink_1::alpha=0.5 ! queue ! waylandsink fullscreen=true sync=true \
                      t. ! queue ! qtimlvconverter ! queue ! \
                      qtimltflite model=$HOME/models/$MODEL_NAME delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp,log_level=(string)1;" ! queue ! \
                      qtimlpostprocess module=deeplab-argmax labels=$HOME/labels/$LABELS_NAME ! video/x-raw,format=BGRA,width=520,height=520 ! queue ! seg_mix.
                      ```
                    </Step>
                  </Steps>
                </Accordion>
              </Accordion>
            </td>
          </tr>

          <tr>
            <td rowSpan={2} style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"center",verticalAlign:"middle",width:"40px"}}>7</td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"left",verticalAlign:"middle",width:"180px"}}><a href="https://aihub.qualcomm.com/iot/models/ffnet_40s?searchTerm=FFNet-40&chipsets=qualcomm-qcs6490-proxy" target="_blank" style={{color:"#3253DC",fontWeight:600}}>FFNet-40S</a></td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",color:"#555",fontSize:"0.82rem",verticalAlign:"middle"}}>Minimal FFNet for maximum throughput.</td>
          </tr>

          <tr>
            <td colSpan={2} style={{border:"1px solid #e2e8f0",padding:"4px",verticalAlign:"top",width:"100%"}}>
              {/* yaml_id: 23 */}

              <Accordion title="Steps to Run on QIMSDK">
                <Accordion title="🟢 W8A8 — Model Precision">
                  <Steps>
                    <Step title="Download Required Files">
                      | File                                                                                                                                                   | Save as                 |
                      | ------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------- |
                      | [Model](https://aihub.qualcomm.com/iot/models/ffnet_40s?searchTerm=FFNet-40\&chipsets=qualcomm-qcs6490-proxy)                                          | ffnet\_40s\_w8a8.tflite |
                      | <a href="../labels/dv3-argmax.json" download="dv3-argmax.json">dv3-argmax.json</a>                                                                     | dv3-argmax.json         |
                      | <a href="https://github.com/qualcomm/sample-apps-for-qualcomm-linux/raw/refs/heads/main/qualcomm-linux/artifacts/videos/demo_samples/">Input video</a> | ai\_demo\_sample.mp4    |

                      <Note>
                        If any downloaded file is a `.zip` archive, extract it on your host machine before copying:
                        `unzip filename.zip`
                      </Note>
                    </Step>

                    <Step title="Copy Files to Device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Replace $HOME to the appropriate device path before running the commands.
                        # For QLI:    /root
                        # For Ubuntu: /home/ubuntu
                        # Modify this based on your platform and ensure files are copied to the correct location on the device.

                        ssh <user>@<device-ip> "mkdir -p $HOME/{models,labels,media,media/output}"
                        scp ffnet_40s_w8a8.tflite          <user>@<device-ip>:$HOME/models/
                        scp dv3-argmax.json                <user>@<device-ip>:$HOME/labels/
                        scp ai_demo_sample.mp4      <user>@<device-ip>:$HOME/media/
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Connect to device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Run from your host machine — replace <user> and <device-ip>
                        ssh <user>@<device-ip>
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Set Environment Variables">
                      ```bash Qualcomm Linux theme={null}
                      export MODEL_NAME=ffnet_40s_w8a8.tflite
                      export LABELS_NAME=dv3-argmax.json
                      export SRC_VIDEO_NAME=ai_demo_sample.mp4
                      ```
                    </Step>

                    <Step title="Run the Pipeline">
                      ```bash theme={null}
                      gst-launch-1.0 -e --gst-debug=2 \
                      filesrc location=$HOME/media/$SRC_VIDEO_NAME ! qtdemux ! h264parse ! \
                      v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! \
                      tee name=t \
                      t. ! queue ! qtivcomposer name=seg_mix sink_1::alpha=0.5 ! queue ! waylandsink fullscreen=true sync=true \
                      t. ! queue ! qtimlvconverter ! queue ! \
                      qtimltflite model=$HOME/models/$MODEL_NAME delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp,log_level=(string)1;" ! queue ! \
                      qtimlpostprocess module=deeplab-argmax labels=$HOME/labels/$LABELS_NAME ! video/x-raw,format=BGRA,width=520,height=520 ! queue ! seg_mix.
                      ```
                    </Step>
                  </Steps>
                </Accordion>
              </Accordion>
            </td>
          </tr>

          <tr>
            <td rowSpan={2} style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"center",verticalAlign:"middle",width:"40px"}}>8</td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"left",verticalAlign:"middle",width:"180px"}}><a href="https://aihub.qualcomm.com/iot/models/ffnet_54s?searchTerm=FFNet-54&chipsets=qualcomm-qcs6490-proxy" target="_blank" style={{color:"#3253DC",fontWeight:600}}>FFNet-54S</a></td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",color:"#555",fontSize:"0.82rem",verticalAlign:"middle"}}>Small FFNet for low-latency segmentation.</td>
          </tr>

          <tr>
            <td colSpan={2} style={{border:"1px solid #e2e8f0",padding:"4px",verticalAlign:"top",width:"100%"}}>
              {/* yaml_id: 25 */}

              <Accordion title="Steps to Run on QIMSDK">
                <Accordion title="🟢 W8A8 — Model Precision">
                  <Steps>
                    <Step title="Download Required Files">
                      | File                                                                                                                                                   | Save as                 |
                      | ------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------- |
                      | [Model](https://aihub.qualcomm.com/iot/models/ffnet_54s?searchTerm=FFNet-54\&chipsets=qualcomm-qcs6490-proxy)                                          | ffnet\_54s\_w8a8.tflite |
                      | <a href="../labels/dv3-argmax.json" download="dv3-argmax.json">dv3-argmax.json</a>                                                                     | dv3-argmax.json         |
                      | <a href="https://github.com/qualcomm/sample-apps-for-qualcomm-linux/raw/refs/heads/main/qualcomm-linux/artifacts/videos/demo_samples/">Input video</a> | ai\_demo\_sample.mp4    |

                      <Note>
                        If any downloaded file is a `.zip` archive, extract it on your host machine before copying:
                        `unzip filename.zip`
                      </Note>
                    </Step>

                    <Step title="Copy Files to Device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Replace $HOME to the appropriate device path before running the commands.
                        # For QLI:    /root
                        # For Ubuntu: /home/ubuntu
                        # Modify this based on your platform and ensure files are copied to the correct location on the device.

                        ssh <user>@<device-ip> "mkdir -p $HOME/{models,labels,media,media/output}"
                        scp ffnet_54s_w8a8.tflite          <user>@<device-ip>:$HOME/models/
                        scp dv3-argmax.json                <user>@<device-ip>:$HOME/labels/
                        scp ai_demo_sample.mp4      <user>@<device-ip>:$HOME/media/
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Connect to device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Run from your host machine — replace <user> and <device-ip>
                        ssh <user>@<device-ip>
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Set Environment Variables">
                      ```bash Qualcomm Linux theme={null}
                      export MODEL_NAME=ffnet_54s_w8a8.tflite
                      export LABELS_NAME=dv3-argmax.json
                      export SRC_VIDEO_NAME=ai_demo_sample.mp4
                      ```
                    </Step>

                    <Step title="Run the Pipeline">
                      ```bash theme={null}
                      gst-launch-1.0 -e --gst-debug=2 \
                      filesrc location=$HOME/media/$SRC_VIDEO_NAME ! qtdemux ! h264parse ! \
                      v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! \
                      tee name=t \
                      t. ! queue ! qtivcomposer name=seg_mix sink_1::alpha=0.5 ! queue ! waylandsink fullscreen=true sync=true \
                      t. ! queue ! qtimlvconverter ! queue ! \
                      qtimltflite model=$HOME/models/$MODEL_NAME delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp,log_level=(string)1;" ! queue ! \
                      qtimlpostprocess module=deeplab-argmax labels=$HOME/labels/$LABELS_NAME ! video/x-raw,format=BGRA,width=520,height=520 ! queue ! seg_mix.
                      ```
                    </Step>
                  </Steps>
                </Accordion>
              </Accordion>
            </td>
          </tr>

          <tr>
            <td rowSpan={2} style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"center",verticalAlign:"middle",width:"40px"}}>9</td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"left",verticalAlign:"middle",width:"180px"}}><a href="https://aihub.qualcomm.com/iot/models/ffnet_78s?searchTerm=FFNet-78&chipsets=qualcomm-qcs6490-proxy" target="_blank" style={{color:"#3253DC",fontWeight:600}}>FFNet-78S</a></td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",color:"#555",fontSize:"0.82rem",verticalAlign:"middle"}}>Standard-resolution FFNet-78S segmentation model.</td>
          </tr>

          <tr>
            <td colSpan={2} style={{border:"1px solid #e2e8f0",padding:"4px",verticalAlign:"top",width:"100%"}}>
              {/* yaml_id: 27 */}

              <Accordion title="Steps to Run on QIMSDK">
                <Accordion title="🟢 W8A8 — Model Precision">
                  <Steps>
                    <Step title="Download Required Files">
                      | File                                                                                                                                                   | Save as                 |
                      | ------------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------- |
                      | [Model](https://aihub.qualcomm.com/iot/models/ffnet_78s?searchTerm=FFNet-78\&chipsets=qualcomm-qcs6490-proxy)                                          | ffnet\_78s\_w8a8.tflite |
                      | <a href="../labels/dv3-argmax.json" download="dv3-argmax.json">dv3-argmax.json</a>                                                                     | dv3-argmax.json         |
                      | <a href="https://github.com/qualcomm/sample-apps-for-qualcomm-linux/raw/refs/heads/main/qualcomm-linux/artifacts/videos/demo_samples/">Input video</a> | ai\_demo\_sample.mp4    |

                      <Note>
                        If any downloaded file is a `.zip` archive, extract it on your host machine before copying:
                        `unzip filename.zip`
                      </Note>
                    </Step>

                    <Step title="Copy Files to Device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Replace $HOME to the appropriate device path before running the commands.
                        # For QLI:    /root
                        # For Ubuntu: /home/ubuntu
                        # Modify this based on your platform and ensure files are copied to the correct location on the device.

                        ssh <user>@<device-ip> "mkdir -p $HOME/{models,labels,media,media/output}"
                        scp ffnet_78s_w8a8.tflite          <user>@<device-ip>:$HOME/models/
                        scp dv3-argmax.json                <user>@<device-ip>:$HOME/labels/
                        scp ai_demo_sample.mp4      <user>@<device-ip>:$HOME/media/
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Connect to device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Run from your host machine — replace <user> and <device-ip>
                        ssh <user>@<device-ip>
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Set Environment Variables">
                      ```bash Qualcomm Linux theme={null}
                      export MODEL_NAME=ffnet_78s_w8a8.tflite
                      export LABELS_NAME=dv3-argmax.json
                      export SRC_VIDEO_NAME=ai_demo_sample.mp4
                      ```
                    </Step>

                    <Step title="Run the Pipeline">
                      ```bash theme={null}
                      gst-launch-1.0 -e --gst-debug=2 \
                      filesrc location=$HOME/media/$SRC_VIDEO_NAME ! qtdemux ! h264parse ! \
                      v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! \
                      tee name=t \
                      t. ! queue ! qtivcomposer name=seg_mix sink_1::alpha=0.5 ! queue ! waylandsink fullscreen=true sync=true \
                      t. ! queue ! qtimlvconverter ! queue ! \
                      qtimltflite model=$HOME/models/$MODEL_NAME delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp,log_level=(string)1;" ! queue ! \
                      qtimlpostprocess module=deeplab-argmax labels=$HOME/labels/$LABELS_NAME ! video/x-raw,format=BGRA,width=520,height=520 ! queue ! seg_mix.
                      ```
                    </Step>
                  </Steps>
                </Accordion>
              </Accordion>
            </td>
          </tr>

          <tr>
            <td rowSpan={2} style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"center",verticalAlign:"middle",width:"40px"}}>10</td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"left",verticalAlign:"middle",width:"180px"}}><a href="https://aihub.qualcomm.com/iot/models/segformer_base" target="_blank" style={{color:"#3253DC",fontWeight:600}}>Segformer-Base</a></td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",color:"#555",fontSize:"0.82rem",verticalAlign:"middle"}}>Hierarchical transformer with lightweight MLP decoder.</td>
          </tr>

          <tr>
            <td colSpan={2} style={{border:"1px solid #e2e8f0",padding:"4px",verticalAlign:"top",width:"100%"}}>
              {/* yaml_id: 29 */}

              <Accordion title="Steps to Run on QIMSDK">
                <Accordion title="🟢 W8A8 — Model Precision">
                  <Steps>
                    <Step title="Download Required Files">
                      | File                                                                                                                              | Save as                         |
                      | --------------------------------------------------------------------------------------------------------------------------------- | ------------------------------- |
                      | [Model](https://aihub.qualcomm.com/iot/models/segformer_base)                                                                     | segformer\_base\_w8a8.tflite    |
                      | <a href="../labels/segformer.json" download="segformer.json">segformer.json</a>                                                   | segformer.json                  |
                      | <a href="/sample-videos/Driving_1080p_180s_30FPS.MOV" download="Driving_1080p_180s_30FPS.MOV">Driving\_1080p\_180s\_30FPS.MOV</a> | Driving\_1080p\_180s\_30FPS.MOV |

                      <Note>
                        If any downloaded file is a `.zip` archive, extract it on your host machine before copying:
                        `unzip filename.zip`
                      </Note>
                    </Step>

                    <Step title="Copy Files to Device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Replace $HOME to the appropriate device path before running the commands.
                        # For QLI:    /root
                        # For Ubuntu: /home/ubuntu
                        # Modify this based on your platform and ensure files are copied to the correct location on the device.

                        ssh <user>@<device-ip> "mkdir -p $HOME/{models,labels,media,media/output}"
                        scp segformer_base_w8a8.tflite         <user>@<device-ip>:$HOME/models/
                        scp segformer.json                     <user>@<device-ip>:$HOME/labels/
                        scp Driving_1080p_180s_30FPS.MOV       <user>@<device-ip>:$HOME/media/
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Connect to device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Run from your host machine — replace <user> and <device-ip>
                        ssh <user>@<device-ip>
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Set Environment Variables">
                      ```bash Qualcomm Linux theme={null}
                      export MODEL_NAME=segformer_base_w8a8.tflite
                      export LABELS_NAME=segformer.json
                      export SRC_VIDEO_NAME=Driving_1080p_180s_30FPS.MOV
                      ```
                    </Step>

                    <Step title="Run the Pipeline">
                      ```bash theme={null}
                      gst-launch-1.0 -e --gst-debug=2 \
                      filesrc location=$HOME/media/$SRC_VIDEO_NAME ! qtdemux ! h264parse ! \
                      v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! \
                      tee name=t \
                      t. ! queue ! qtivcomposer name=seg_mix sink_1::alpha=0.5 ! queue ! waylandsink fullscreen=true sync=true \
                      t. ! queue ! qtimlvconverter ! queue ! \
                      qtimltflite model=$HOME/models/$MODEL_NAME delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp,log_level=(string)1;" ! queue ! \
                      qtimlpostprocess module=deeplab-argmax labels=$HOME/labels/$LABELS_NAME ! video/x-raw,format=BGRA,width=520,height=520 ! queue ! seg_mix.
                      ```
                    </Step>
                  </Steps>
                </Accordion>
              </Accordion>
            </td>
          </tr>

          <tr>
            <td rowSpan={2} style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"center",verticalAlign:"middle",width:"40px"}}>11</td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"left",verticalAlign:"middle",width:"180px"}}><a href="https://aihub.qualcomm.com/iot/models/sinet" target="_blank" style={{color:"#3253DC",fontWeight:600}}>SINet</a></td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",color:"#555",fontSize:"0.82rem",verticalAlign:"middle"}}>Salient instance network for scene understanding.</td>
          </tr>

          <tr>
            <td colSpan={2} style={{border:"1px solid #e2e8f0",padding:"4px",verticalAlign:"top",width:"100%"}}>
              <Accordion title="Steps to Run on QIMSDK">
                <Accordion title="🟢 W8A8 — Model Precision">
                  <Steps>
                    <Step title="Download Required Files">
                      | File                                                                                                                                                   | Save as              |
                      | ------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------- |
                      | [Model](https://aihub.qualcomm.com/iot/models/sinet)                                                                                                   | sinet\_w8a8.tflite   |
                      | <a href="../labels/dv3-argmax.json" download="dv3-argmax.json">dv3-argmax.json</a>                                                                     | dv3-argmax.json      |
                      | <a href="https://github.com/qualcomm/sample-apps-for-qualcomm-linux/raw/refs/heads/main/qualcomm-linux/artifacts/videos/demo_samples/">Input video</a> | ai\_demo\_sample.mp4 |

                      <Note>
                        If any downloaded file is a `.zip` archive, extract it on your host machine before copying:
                        `unzip filename.zip`
                      </Note>
                    </Step>

                    <Step title="Copy Files to Device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Replace $HOME to the appropriate device path before running the commands.
                        # For QLI:    /root
                        # For Ubuntu: /home/ubuntu
                        # Modify this based on your platform and ensure files are copied to the correct location on the device.

                        ssh <user>@<device-ip> "mkdir -p $HOME/{models,labels,media,media/output}"
                        scp sinet_w8a8.tflite              <user>@<device-ip>:$HOME/models/
                        scp dv3-argmax.json                <user>@<device-ip>:$HOME/labels/
                        scp ai_demo_sample.mp4      <user>@<device-ip>:$HOME/media/
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Connect to device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Run from your host machine — replace <user> and <device-ip>
                        ssh <user>@<device-ip>
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Set Environment Variables">
                      ```bash Qualcomm Linux theme={null}
                      export MODEL_NAME=sinet_w8a8.tflite
                      export LABELS_NAME=dv3-argmax.json
                      export SRC_VIDEO_NAME=ai_demo_sample.mp4
                      ```
                    </Step>

                    <Step title="Run the Pipeline">
                      ```bash theme={null}
                      gst-launch-1.0 -e --gst-debug=2 \
                      filesrc location=$HOME/media/$SRC_VIDEO_NAME ! qtdemux ! h264parse ! \
                      v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! \
                      tee name=t \
                      t. ! queue ! qtivcomposer name=seg_mix sink_1::alpha=0.5 ! queue ! waylandsink fullscreen=true sync=true \
                      t. ! queue ! qtimlvconverter ! queue ! \
                      qtimltflite model=$HOME/models/$MODEL_NAME delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp,log_level=(string)1; ! queue ! \
                      qtimlpostprocess module=deeplab-argmax labels=$HOME/labels/$LABELS_NAME ! video/x-raw,format=BGRA,width=520,height=520 ! queue ! seg_mix.
                      ```
                    </Step>
                  </Steps>
                </Accordion>
              </Accordion>
            </td>
          </tr>

          <tr>
            <td rowSpan={2} style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"center",verticalAlign:"middle",width:"40px"}}>12</td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",textAlign:"left",verticalAlign:"middle",width:"180px"}}><a href="https://aihub.qualcomm.com/iot/models/pspnet" target="_blank" style={{color:"#3253DC",fontWeight:600}}>PSPNet</a></td>
            <td style={{border:"1px solid #e2e8f0",padding:"8px",color:"#555",fontSize:"0.82rem",verticalAlign:"middle"}}>Pyramid pooling module for global scene context aggregation.</td>
          </tr>

          <tr>
            <td colSpan={2} style={{border:"1px solid #e2e8f0",padding:"4px",verticalAlign:"top",width:"100%"}}>
              <Accordion title="Steps to Run on QIMSDK">
                <Accordion title="🟢 W8A8 — Model Precision">
                  <Steps>
                    <Step title="Download Required Files">
                      | File                                                                                                                                                         | Save as                                |
                      | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------- |
                      | [Model](https://aihub.qualcomm.com/iot/models/pspnet)                                                                                                        | pspnet\_w8a8.tflite                    |
                      | <a href="../labels/dv3-argmax.json" download="dv3-argmax.json">dv3-argmax.json</a>                                                                           | dv3-argmax.json                        |
                      | <a href="https://github.com/qualcomm/sample-apps-for-qualcomm-linux/raw/refs/heads/main/artifacts/videos/Street_Bridge_1080p_180s_30FPS.MOV">Input video</a> | Street\_Bridge\_1080p\_180s\_30FPS.MOV |

                      <Note>
                        If any downloaded file is a `.zip` archive, extract it on your host machine before copying:
                        `unzip filename.zip`
                      </Note>
                    </Step>

                    <Step title="Copy Files to Device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Replace $HOME to the appropriate device path before running the commands.
                        # For QLI:    /root
                        # For Ubuntu: /home/ubuntu
                        # Modify this based on your platform and ensure files are copied to the correct location on the device.

                        ssh <user>@<device-ip> "mkdir -p $HOME/{models,labels,media,media/output}"
                        scp pspnet_w8a8.tflite                  <user>@<device-ip>:$HOME/models/
                        scp dv3-argmax.json                     <user>@<device-ip>:$HOME/labels/
                        scp Street_Bridge_1080p_180s_30FPS.MOV  <user>@<device-ip>:$HOME/media/
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Connect to device">
                      <CodeGroup>
                        ```bash SCP (SSH) theme={null}
                        # Run from your host machine — replace <user> and <device-ip>
                        ssh <user>@<device-ip>
                        ```
                      </CodeGroup>
                    </Step>

                    <Step title="Set Environment Variables">
                      ```bash Qualcomm Linux theme={null}
                      export MODEL_NAME=pspnet_w8a8.tflite
                      export LABELS_NAME=dv3-argmax.json
                      export SRC_VIDEO_NAME=Street_Bridge_1080p_180s_30FPS.MOV
                      ```
                    </Step>

                    <Step title="Run the Pipeline">
                      ```bash theme={null}
                      gst-launch-1.0 -e --gst-debug=2 \
                      filesrc location=$HOME/media/$SRC_VIDEO_NAME ! qtdemux ! h264parse ! \
                      v4l2h264dec capture-io-mode=4 output-io-mode=4 ! video/x-raw,format=NV12 ! queue ! \
                      tee name=t \
                      t. ! queue ! qtivcomposer name=seg_mix sink_1::alpha=0.5 ! queue ! waylandsink fullscreen=true sync=true \
                      t. ! queue ! qtimlvconverter ! queue ! \
                      qtimltflite model=$HOME/models/$MODEL_NAME delegate=external external-delegate-path=libQnnTFLiteDelegate.so external-delegate-options="QNNExternalDelegate,backend_type=htp,log_level=(string)1;" ! queue ! \
                      qtimlpostprocess module=deeplab-argmax labels=$HOME/labels/$LABELS_NAME ! video/x-raw,format=BGRA,width=520,height=520 ! queue ! seg_mix.
                      ```
                    </Step>
                  </Steps>
                </Accordion>
              </Accordion>
            </td>
          </tr>
        </tbody>
      </table>
    </div>
  </Tab>
</Tabs>