YAML Metadata Warning:The pipeline tag "video-object-tracking" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other
Track-Anything: Optimized for Qualcomm Devices
Track-Anything is a video based machine learning model to track an object in a video.
This is based on the implementation of Track-Anything found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.
Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.
Getting Started
There are two ways to deploy this model on your device:
Option 1: Download Pre-Exported Models
Below are pre-exported model assets ready for deployment.
| Runtime | Precision | Chipset | SDK Versions | Download |
|---|---|---|---|---|
| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | Download |
| TFLITE | float | Universal | QAIRT 2.45 | Download |
For more device-specific assets and performance metrics, visit Track-Anything on Qualcomm® AI Hub.
Option 2: Export with Custom Configurations
Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:
- Custom weights (e.g., fine-tuned checkpoints)
- Custom input shapes
- Target device and runtime configurations
This option is ideal if you need to customize the model beyond the default configuration provided here.
See our repository for Track-Anything on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.video_object_tracking
Model Stats:
- Model checkpoint: xmem
- Input resolution: 320x568
- Number of parameters (encode_key_with_shrinkage): 9.72M
- Model size (encode_key_with_shrinkage) (float): 37.1 MB
- Number of parameters (encode_value): 23.3M
- Model size (encode_value) (float): 88.8 MB
- Number of parameters (encode_key_without_shrinkage): 9.71M
- Model size (encode_key_without_shrinkage) (float): 37.1 MB
- Number of parameters (segment): 30.1M
- Model size (segment) (float): 115 MB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| encode_key_with_shrinkage | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.38 ms | 0 - 176 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Snapdragon® 8 Elite Mobile | 2.944 ms | 1 - 165 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Snapdragon® X2 Elite | 2.793 ms | 18 - 18 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Snapdragon® X Elite | 5.585 ms | 19 - 19 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Snapdragon® X Elite | 5.585 ms | 19 - 19 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.68 ms | 10 - 212 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Qualcomm® QCS8550 (Proxy) | 5.141 ms | 0 - 20 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Qualcomm® QCS9075 | 9.634 ms | 10 - 13 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.944 ms | 1 - 165 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.425 ms | 0 - 188 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Snapdragon® 8 Elite Mobile | 3.288 ms | 0 - 180 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4.057 ms | 0 - 215 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 31.246 ms | 3 - 179 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 5.982 ms | 3 - 8 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® SA8775P | 9.456 ms | 3 - 180 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® SA8775P | 9.456 ms | 3 - 180 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® SA8775P | 9.456 ms | 3 - 180 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® QCS9075 | 10.697 ms | 2 - 29 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 11.759 ms | 3 - 196 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® SA7255P | 31.246 ms | 3 - 179 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® SA8295P | 10.278 ms | 3 - 163 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.288 ms | 0 - 180 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.494 ms | 0 - 216 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Snapdragon® 8 Elite Mobile | 4.376 ms | 61 - 254 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Snapdragon® X2 Elite | 3.942 ms | 65 - 65 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Snapdragon® X Elite | 6.908 ms | 66 - 66 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Snapdragon® X Elite | 6.908 ms | 66 - 66 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.047 ms | 64 - 274 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Qualcomm® QCS8550 (Proxy) | 6.871 ms | 58 - 77 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Qualcomm® QCS9075 | 11.441 ms | 61 - 64 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.376 ms | 61 - 254 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.545 ms | 0 - 223 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Snapdragon® 8 Elite Mobile | 4.393 ms | 19 - 205 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.581 ms | 19 - 232 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 33.576 ms | 20 - 204 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.966 ms | 18 - 20 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® SA8775P | 11.675 ms | 20 - 207 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® SA8775P | 11.675 ms | 20 - 207 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® SA8775P | 11.675 ms | 20 - 207 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® QCS9075 | 12.853 ms | 20 - 63 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 14.187 ms | 20 - 220 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® SA7255P | 33.576 ms | 20 - 204 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® SA8295P | 12.592 ms | 20 - 185 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.393 ms | 19 - 205 MB | NPU |
| encode_value | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.639 ms | 11 - 177 MB | NPU |
| encode_value | ONNX | float | Snapdragon® 8 Elite Mobile | 8.284 ms | 8 - 176 MB | NPU |
| encode_value | ONNX | float | Snapdragon® X2 Elite | 6.342 ms | 39 - 39 MB | NPU |
| encode_value | ONNX | float | Snapdragon® X Elite | 12.518 ms | 38 - 38 MB | NPU |
| encode_value | ONNX | float | Snapdragon® X Elite | 12.518 ms | 38 - 38 MB | NPU |
| encode_value | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 9.863 ms | 0 - 204 MB | NPU |
| encode_value | ONNX | float | Qualcomm® QCS8550 (Proxy) | 15.591 ms | 0 - 44 MB | NPU |
| encode_value | ONNX | float | Qualcomm® QCS9075 | 18.566 ms | 6 - 14 MB | NPU |
| encode_value | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.284 ms | 8 - 176 MB | NPU |
| encode_value | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.33 ms | 3 - 202 MB | NPU |
| encode_value | TFLITE | float | Snapdragon® 8 Elite Mobile | 6.829 ms | 2 - 214 MB | NPU |
| encode_value | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 8.266 ms | 3 - 289 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 51.338 ms | 0 - 213 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 11.899 ms | 3 - 5 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® SA8775P | 17.032 ms | 3 - 215 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® SA8775P | 17.032 ms | 3 - 215 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® SA8775P | 17.032 ms | 3 - 215 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® QCS9075 | 19.763 ms | 0 - 55 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 21.329 ms | 3 - 288 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® SA7255P | 51.338 ms | 0 - 213 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® SA8295P | 18.885 ms | 3 - 219 MB | NPU |
| encode_value | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 6.829 ms | 2 - 214 MB | NPU |
| segment | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 10.485 ms | 8 - 222 MB | NPU |
| segment | ONNX | float | Snapdragon® 8 Elite Mobile | 13.638 ms | 5 - 216 MB | NPU |
| segment | ONNX | float | Snapdragon® X2 Elite | 11.809 ms | 38 - 38 MB | NPU |
| segment | ONNX | float | Snapdragon® X Elite | 23.504 ms | 37 - 37 MB | NPU |
| segment | ONNX | float | Snapdragon® X Elite | 23.504 ms | 37 - 37 MB | NPU |
| segment | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 17.531 ms | 0 - 245 MB | NPU |
| segment | ONNX | float | Qualcomm® QCS8550 (Proxy) | 23.248 ms | 0 - 43 MB | NPU |
| segment | ONNX | float | Qualcomm® QCS9075 | 36.384 ms | 21 - 45 MB | NPU |
| segment | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 13.638 ms | 5 - 216 MB | NPU |
| segment | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 11.448 ms | 0 - 194 MB | NPU |
| segment | TFLITE | float | Snapdragon® 8 Elite Mobile | 13.272 ms | 1 - 197 MB | NPU |
| segment | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 17.409 ms | 2 - 289 MB | NPU |
| segment | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 103.489 ms | 2 - 195 MB | NPU |
| segment | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 23.401 ms | 2 - 5 MB | NPU |
| segment | TFLITE | float | Qualcomm® SA8775P | 33.353 ms | 2 - 193 MB | NPU |
| segment | TFLITE | float | Qualcomm® SA8775P | 33.353 ms | 2 - 193 MB | NPU |
| segment | TFLITE | float | Qualcomm® SA8775P | 33.353 ms | 2 - 193 MB | NPU |
| segment | TFLITE | float | Qualcomm® QCS9075 | 38.107 ms | 0 - 83 MB | NPU |
| segment | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 42.635 ms | 2 - 294 MB | NPU |
| segment | TFLITE | float | Qualcomm® SA7255P | 103.489 ms | 2 - 195 MB | NPU |
| segment | TFLITE | float | Qualcomm® SA8295P | 37.703 ms | 0 - 199 MB | NPU |
| segment | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 13.272 ms | 1 - 197 MB | NPU |
License
- The license for the original implementation of Track-Anything can be found here.
References
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.
