Skip to main content
No.Model NameDescription
1ResNeXt101Wide residual network with grouped convolutions for high accuracy.
1

Download Required Files

FileSave as
Modelresnext101_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp resnext101_float.tflite             <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=resnext101_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 31.0}" ! text/x-raw ! queue ! class_mux.
1

Download Required Files

FileSave as
Modelresnext101_w8a8.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp resnext101_w8a8.tflite                <user>@<device-ip>:$HOME/models/
scp mobilenet.json                        <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4      <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=resnext101_w8a8.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! 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=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 35.0}" ! text/x-raw ! queue ! class_mux.
2VITVision Transformer applying self-attention on image patches.
1

Download Required Files

FileSave as
Modelvit_w8a8.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp vit_w8a8.tflite                    <user>@<device-ip>:$HOME/models/
scp mobilenet.json                     <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4   <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=vit_w8a8.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! 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=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 35.0}" ! text/x-raw ! queue ! class_mux.
3EfficientViT-b2-clsMemory-efficient vision transformer (B2 classification).
1

Download Required Files

FileSave as
Modelefficientvit_b2_cls_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp efficientvit_b2_cls_float.tflite   <user>@<device-ip>:$HOME/models/
scp mobilenet.json                     <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4   <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=efficientvit_b2_cls_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
4EfficientViT-l2-clsLarger memory-efficient vision transformer (L2 classification).
1

Download Required Files

FileSave as
Modelefficientvit_l2_cls_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp efficientvit_l2_cls_float.tflite   <user>@<device-ip>:$HOME/models/
scp mobilenet.json                     <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4   <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=efficientvit_l2_cls_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
5EfficientNet-B0Balanced accuracy/efficiency via compound scaling (B0 base).
1

Download Required Files

FileSave as
Modelefficientnet_b0_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp efficientnet_b0_float.tflite      <user>@<device-ip>:$HOME/models/
scp mobilenet.json                    <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4  <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=efficientnet_b0_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
6ConvNext-BasePure CNN architecture inspired by ViT design principles (Base).
1

Download Required Files

FileSave as
Modelconvnext_base_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp convnext_base_float.tflite         <user>@<device-ip>:$HOME/models/
scp mobilenet.json                     <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4   <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=convnext_base_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
7ConvNext-TinyCompact ConvNeXt variant for efficient classification.
1

Download Required Files

FileSave as
Modelconvnext_tiny_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp convnext_tiny_float.tflite        <user>@<device-ip>:$HOME/models/
scp mobilenet.json                    <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4  <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=convnext_tiny_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
8EfficientNet-V2-sFaster training EfficientNet V2 small variant.
1

Download Required Files

FileSave as
Modelefficientnet_v2_s_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp efficientnet_v2_s_float.tflite     <user>@<device-ip>:$HOME/models/
scp mobilenet.json                     <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4   <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=efficientnet_v2_s_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
9BeitBERT pre-training for image transformers.
1

Download Required Files

FileSave as
Modelbeit_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp beit_float.tflite                  <user>@<device-ip>:$HOME/models/
scp mobilenet.json                     <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4   <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=beit_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
10MNASNet05Neural architecture search model for mobile efficiency.
1

Download Required Files

FileSave as
Modelmnasnet05_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp mnasnet05_float.tflite              <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=mnasnet05_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
11DenseNet-121Densely connected CNN with feature reuse across layers.
1

Download Required Files

FileSave as
Modeldensenet_121_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp densenet_121_float.tflite           <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=densenet_121_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
12GoogLeNetInception-based deep CNN for efficient classification.
1

Download Required Files

FileSave as
Modelgooglenet_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp googlenet_float.tflite              <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=googlenet_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
1

Download Required Files

FileSave as
Modelgooglenet_w8a8.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp googlenet_w8a8.tflite               <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=googlenet_w8a8.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! 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=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
13Resnet101Deep residual network with 101 layers.
1

Download Required Files

FileSave as
Modelresnet101_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp resnet101_float.tflite                 <user>@<device-ip>:$HOME/models/
scp mobilenet.json                         <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4       <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=resnet101_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
1

Download Required Files

FileSave as
Modelresnet101_w8a8.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp resnet101_w8a8.tflite               <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=resnet101_w8a8.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! 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=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
14Resnet50Classic 50-layer residual network for image classification.
1

Download Required Files

FileSave as
Modelresnet50_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp resnet50_float.tflite               <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=resnet50_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
1

Download Required Files

FileSave as
Modelresnet50_w8a8.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp resnet50_w8a8.tflite                <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=resnet50_w8a8.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! 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=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
15Inception-v3Multi-scale feature extraction with factorized convolutions.
1

Download Required Files

FileSave as
Modelinception_v3_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp inception_v3_float.tflite           <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=inception_v3_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
1

Download Required Files

FileSave as
Modelinception_v3_w8a8.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp inception_v3_w8a8.tflite            <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=inception_v3_w8a8.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! 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=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
16MobileNet-v2Inverted residual blocks for mobile image classification.
1

Download Required Files

FileSave as
Modelmobilenet_v2_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp mobilenet_v2_float.tflite           <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=mobilenet_v2_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
1

Download Required Files

FileSave as
Modelmobilenet_v2_w8a8.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp mobilenet_v2_w8a8.tflite            <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=mobilenet_v2_w8a8.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! 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=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
17MobileNet-v3-LargeOptimized mobile CNN with SE modules (Large variant).
1

Download Required Files

FileSave as
Modelmobilenet_v3_large_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp mobilenet_v3_large_float.tflite     <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=mobilenet_v3_large_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
18RegNetRegularized network design with quantized widths and depths.
1

Download Required Files

FileSave as
Modelregnet_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp regnet_float.tflite                 <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=regnet_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
1

Download Required Files

FileSave as
Modelregnet_w8a8.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp regnet_w8a8.tflite                  <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=regnet_w8a8.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! 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=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
19ResNet18Lightweight 18-layer residual network.
1

Download Required Files

FileSave as
Modelresnet18_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp resnet18_float.tflite               <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=resnet18_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
1

Download Required Files

FileSave as
Modelresnet18_w8a8.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp resnet18_w8a8.tflite                <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=resnet18_w8a8.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! 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=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
20ResNeXt50Compact grouped-convolution ResNet variant.
1

Download Required Files

FileSave as
Modelresnext50_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp resnext50_float.tflite              <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=resnext50_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
1

Download Required Files

FileSave as
Modelresnext50_w8a8.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp resnext50_w8a8.tflite               <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=resnext50_w8a8.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! 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=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
21Shufflenet-v2Channel-split shuffle network for efficient mobile inference.
1

Download Required Files

FileSave as
Modelshufflenet_v2_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp shufflenet_v2_float.tflite          <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=shufflenet_v2_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
1

Download Required Files

FileSave as
Modelshufflenet_v2_w8a8.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp shufflenet_v2_w8a8.tflite           <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=shufflenet_v2_w8a8.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! 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=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
22SqueezeNet-1.1AlexNet-level accuracy at 50x fewer parameters.
1

Download Required Files

FileSave as
Modelsqueezenet_1_1_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp squeezenet_1_1_float.tflite         <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=squeezenet_1_1_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
1

Download Required Files

FileSave as
Modelsqueezenet_1_1_w8a8.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp squeezenet_1_1_w8a8.tflite          <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=squeezenet_1_1_w8a8.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! 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=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
23WideResNet50Wide residual network with increased channel width.
1

Download Required Files

FileSave as
Modelwideresnet50_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp wideresnet50_float.tflite           <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=wideresnet50_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
1

Download Required Files

FileSave as
Modelwideresnet50_w8a8.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp wideresnet50_w8a8.tflite            <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=wideresnet50_w8a8.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! 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=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
24EfficientNet-B4Higher-capacity EfficientNet for improved accuracy.
1

Download Required Files

FileSave as
Modelefficientnet_b4_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp efficientnet_b4_float.tflite        <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=efficientnet_b4_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
25DLA-102-XDeep layer aggregation for hierarchical feature fusion.
1

Download Required Files

FileSave as
Modeldla_102_x_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp dla_102_x_float.tflite              <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=dla_102_x_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
1

Download Required Files

FileSave as
Modeldla_102_x_w8a8.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp dla_102_x_w8a8.tflite               <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=dla_102_x_w8a8.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! 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=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
26MobileNet-v3-SmallUltra-compact mobile CNN (Small variant).
1

Download Required Files

FileSave as
Modelmobilenet_v3_small_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp mobilenet_v3_small_float.tflite                 <user>@<device-ip>:$HOME/models/
scp mobilenet.json                                  <user>@<device-ip>:$HOME/models/
scp ai_demo_sample.mp4                <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=mobilenet_v3_small_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
27EfficientFormerUltra-fast transformer-style ViT for edge deployment.
1

Download Required Files

FileSave as
Modelefficientformer_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp efficientformer_float.tflite        <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/models/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=efficientformer_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
28GPUNetGPU-optimized network via neural architecture search.
1

Download Required Files

FileSave as
Modelgpunet_float.tflite
mobilenet.jsonmobilenet.json
Input videoai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp gpunet_float.tflite                     <user>@<device-ip>:$HOME/models/
scp mobilenet.json                          <user>@<device-ip>:$HOME/models/
scp ai_demo_sample.mp4        <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=gpunet_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
29Sequencer2D2D LSTM-based alternative to attention for image classification.
1

Download Required Files

FileSave as
Modelsequencer2d_float.tflite
mobilenet.jsonmobilenet.json
ai_demo_sample.mp4ai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp sequencer2d_float.tflite                    <user>@<device-ip>:$HOME/models/
scp mobilenet.json                              <user>@<device-ip>:$HOME/models/
scp ai_demo_sample.mp4            <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=sequencer2d_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
30LeViTHybrid convolutional-attention ViT optimized for fast inference.
1

Download Required Files

FileSave as
Modellevit_float.tflite
mobilenet.jsonmobilenet.json
Input videoai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp levit_float.tflite                 <user>@<device-ip>:$HOME/models/
scp mobilenet.json                     <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4   <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=levit_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! 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=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.
31Mobile-VITLightweight hybrid CNN-Transformer for mobile devices.
1

Download Required Files

FileSave as
Modelmobile_vit_float.tflite
mobilenet.jsonmobilenet.json
Input videoai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp mobile_vit_float.tflite             <user>@<device-ip>:$HOME/models/
scp mobilenet.json                      <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4    <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=mobile_vit_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=true \
t. ! queue ! qtimlvconverter ! queue ! \
qtimltflite model=$HOME/models/$MODEL_NAME delegate=gpu ! queue ! \
qtimlpostprocess module=mobilenet labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 70.0}" ! text/x-raw ! queue ! class_mux.
32NASNetNeural architecture search network for mobile devices.
1

Download Required Files

FileSave as
Modelnasnet_float.tflite
mobilenet.jsonmobilenet.json
Input videoai_demo_sample.mp4
If any downloaded file is a .zip archive, extract it on your host machine before copying: unzip filename.zip
2

Copy Files to Device

# 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 $HOME/{models,labels,media,media/output}"
scp nasnet_float.tflite                   <user>@<device-ip>:$HOME/models/
scp mobilenet.json                        <user>@<device-ip>:$HOME/labels/
scp ai_demo_sample.mp4      <user>@<device-ip>:$HOME/media/
3

Connect to device

# Run from your host machine — replace <user> and <device-ip>
ssh <user>@<device-ip>
4

Set Environment Variables

Qualcomm Linux
export MODEL_NAME=nasnet_float.tflite
export LABELS_NAME=mobilenet.json
export SRC_VIDEO_NAME=ai_demo_sample.mp4
5

Run the Pipeline

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 ! qtimetamux name=class_mux ! qtivoverlay ! waylandsink fullscreen=true sync=false \
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=mobilenet-softmax labels=$HOME/labels/$LABELS_NAME settings="{\"confidence\": 51.0}" ! text/x-raw ! queue ! class_mux.