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 2.50, ONNX Runtime 1.30.0 | Download |
| TFLITE | float | Universal | QAIRT 2.50 | 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:
- Input resolution: 320x568
- Model checkpoint: xmem
- Model size (encode_key_with_shrinkage) (float): 37.1 MB
- Model size (encode_key_without_shrinkage) (float): 37.1 MB
- Model size (encode_value) (float): 88.8 MB
- Model size (segment) (float): 115 MB
- Number of parameters (encode_key_with_shrinkage): 9.72M
- Number of parameters (encode_key_without_shrinkage): 9.71M
- Number of parameters (encode_value): 23.3M
- Number of parameters (segment): 30.1M
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 For Galaxy Mobile | 2.395 ms | 1 - 169 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.886 ms | 0 - 158 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Snapdragon® X2 Elite | 2.74 ms | 10 - 10 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.58 ms | 0 - 194 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 8.739 ms | 9 - 185 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 9.425 ms | 8 - 12 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Qualcomm® QCS8450 | 8.739 ms | 9 - 185 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 8.609 ms | 8 - 12 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.196 ms | 18 - 18 MB | NPU |
| encode_key_with_shrinkage | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.886 ms | 0 - 158 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 2.562 ms | 0 - 178 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.288 ms | 0 - 177 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4.142 ms | 3 - 203 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 9.492 ms | 3 - 194 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 9.796 ms | 3 - 31 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.091 ms | 3 - 9 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® SA8650P | 9.452 ms | 3 - 180 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® SA8255P | 9.452 ms | 3 - 180 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® QCS8450 | 9.492 ms | 3 - 194 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 9.537 ms | 2 - 29 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 3.288 ms | 0 - 177 MB | NPU |
| encode_key_with_shrinkage | TFLITE | float | Qualcomm® SA8295P | 9.997 ms | 3 - 158 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.454 ms | 1 - 172 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.407 ms | 54 - 218 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Snapdragon® X2 Elite | 3.817 ms | 79 - 79 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.817 ms | 56 - 250 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 11.101 ms | 50 - 229 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 11.328 ms | 49 - 53 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Qualcomm® QCS8450 | 11.101 ms | 50 - 229 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 10.429 ms | 53 - 56 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 6.5 ms | 80 - 80 MB | NPU |
| encode_key_without_shrinkage | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.407 ms | 54 - 218 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.593 ms | 0 - 187 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.367 ms | 20 - 201 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.395 ms | 18 - 224 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 12.125 ms | 20 - 216 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 11.749 ms | 20 - 65 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.444 ms | 20 - 22 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® SA8650P | 11.663 ms | 20 - 207 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® SA8255P | 11.663 ms | 20 - 207 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® QCS8450 | 12.125 ms | 20 - 216 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 11.308 ms | 20 - 64 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.367 ms | 20 - 201 MB | NPU |
| encode_key_without_shrinkage | TFLITE | float | Qualcomm® SA8295P | 12.431 ms | 20 - 177 MB | NPU |
| encode_value | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 6.527 ms | 6 - 335 MB | NPU |
| encode_value | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.462 ms | 7 - 415 MB | NPU |
| encode_value | ONNX | float | Snapdragon® X2 Elite | 6.295 ms | 20 - 20 MB | NPU |
| encode_value | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 10.125 ms | 0 - 1258 MB | NPU |
| encode_value | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 21.363 ms | 12 - 221 MB | NPU |
| encode_value | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 18.831 ms | 6 - 15 MB | NPU |
| encode_value | ONNX | float | Qualcomm® QCS8450 | 21.363 ms | 12 - 221 MB | NPU |
| encode_value | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 19.44 ms | 6 - 15 MB | NPU |
| encode_value | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 12.329 ms | 39 - 39 MB | NPU |
| encode_value | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 8.462 ms | 7 - 415 MB | NPU |
| encode_value | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 5.075 ms | 3 - 177 MB | NPU |
| encode_value | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 6.408 ms | 1 - 182 MB | NPU |
| encode_value | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 8.175 ms | 2 - 245 MB | NPU |
| encode_value | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 19.559 ms | 3 - 246 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 17.765 ms | 0 - 56 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.633 ms | 3 - 6 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® SA8650P | 16.996 ms | 3 - 215 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® SA8255P | 16.996 ms | 3 - 215 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® QCS8450 | 19.559 ms | 3 - 246 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 16.995 ms | 0 - 55 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 6.408 ms | 1 - 182 MB | NPU |
| encode_value | TFLITE | float | Qualcomm® SA8295P | 18.225 ms | 3 - 178 MB | NPU |
| segment | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 11.254 ms | 7 - 373 MB | NPU |
| segment | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 15.821 ms | 4 - 408 MB | NPU |
| segment | ONNX | float | Snapdragon® X2 Elite | 12.437 ms | 21 - 21 MB | NPU |
| segment | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 18.776 ms | 22 - 397 MB | NPU |
| segment | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 40.5 ms | 2 - 281 MB | NPU |
| segment | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 37.088 ms | 21 - 46 MB | NPU |
| segment | ONNX | float | Qualcomm® QCS8450 | 40.5 ms | 2 - 281 MB | NPU |
| segment | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 35.999 ms | 21 - 46 MB | NPU |
| segment | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 23.183 ms | 38 - 38 MB | NPU |
| segment | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 15.821 ms | 4 - 408 MB | NPU |
| segment | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 9.909 ms | 0 - 182 MB | NPU |
| segment | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 12.865 ms | 0 - 180 MB | NPU |
| segment | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 16.954 ms | 1 - 274 MB | NPU |
| segment | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 38.598 ms | 2 - 277 MB | NPU |
| segment | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 35.598 ms | 0 - 84 MB | NPU |
| segment | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 23.014 ms | 2 - 4 MB | NPU |
| segment | TFLITE | float | Qualcomm® SA8650P | 33.305 ms | 2 - 194 MB | NPU |
| segment | TFLITE | float | Qualcomm® SA8255P | 33.305 ms | 2 - 194 MB | NPU |
| segment | TFLITE | float | Qualcomm® QCS8450 | 38.598 ms | 2 - 277 MB | NPU |
| segment | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 33.91 ms | 0 - 83 MB | NPU |
| segment | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 12.865 ms | 0 - 180 MB | NPU |
| segment | TFLITE | float | Qualcomm® SA8295P | 36.538 ms | 2 - 187 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.
