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 Mobile Deployment
High-performance interactive tracking and segmentation in videos
Track-Anything is a video based machine learning model to track an object in a video.
This model is an implementation of Track-Anything found here.
This repository provides scripts to run Track-Anything on Qualcomm® devices. More details on model performance across various devices, can be found here.
Model Details
- Model Type: Model_use_case.video_object_tracking
- Model Stats:
- Model checkpoint: xmem
- Input resolution: 320x568
- Number of parameters (TrackAnythingEncodeKeyWithShrinkage): 9.72M
- Model size (TrackAnythingEncodeKeyWithShrinkage) (float): 37.1 MB
- Number of parameters (TrackAnythingEncodeValue): 23.3M
- Model size (TrackAnythingEncodeValue) (float): 88.8 MB
- Number of parameters (TrackAnythingEncodeKeyWithoutShrinkage): 9.71M
- Model size (TrackAnythingEncodeKeyWithoutShrinkage) (float): 37.1 MB
- Number of parameters (TrackAnythingSegment): 30.1M
- Model size (TrackAnythingSegment) (float): 115 MB
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model |
|---|---|---|---|---|---|---|---|---|
| TrackAnythingEncodeKeyWithShrinkage | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 33.829 ms | 3 - 45 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithShrinkage | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 9.582 ms | 3 - 48 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithShrinkage | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 6.957 ms | 3 - 17 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithShrinkage | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 5.453 ms | 1 - 50 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingEncodeKeyWithShrinkage | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 11.16 ms | 3 - 45 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithShrinkage | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 33.829 ms | 3 - 45 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithShrinkage | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 6.946 ms | 3 - 16 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithShrinkage | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 11.495 ms | 3 - 45 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithShrinkage | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 6.967 ms | 3 - 16 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithShrinkage | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 11.16 ms | 3 - 45 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithShrinkage | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 4.635 ms | 0 - 54 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithShrinkage | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.881 ms | 0 - 44 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingEncodeKeyWithShrinkage | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 3.756 ms | 0 - 48 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithShrinkage | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 3.134 ms | 0 - 37 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingEncodeKeyWithShrinkage | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 3.234 ms | 0 - 46 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithShrinkage | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 2.548 ms | 2 - 41 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingEncodeKeyWithShrinkage | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 5.529 ms | 19 - 19 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingEncodeValue | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 52.848 ms | 3 - 54 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeValue | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 17.899 ms | 3 - 92 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeValue | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 12.699 ms | 3 - 22 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeValue | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 15.779 ms | 0 - 105 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingEncodeValue | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 80.268 ms | 3 - 54 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeValue | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 52.848 ms | 3 - 54 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeValue | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 12.725 ms | 3 - 17 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeValue | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 20.158 ms | 3 - 47 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeValue | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 12.734 ms | 3 - 18 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeValue | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 80.268 ms | 3 - 54 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeValue | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 8.784 ms | 50 - 147 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeValue | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 10.02 ms | 14 - 63 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingEncodeValue | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 7.026 ms | 2 - 55 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeValue | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 8.422 ms | 8 - 46 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingEncodeValue | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 5.918 ms | 2 - 64 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeValue | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 6.478 ms | 13 - 49 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingEncodeValue | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 12.281 ms | 39 - 39 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingEncodeKeyWithoutShrinkage | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 35.671 ms | 20 - 63 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithoutShrinkage | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 11.309 ms | 20 - 70 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithoutShrinkage | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 8.276 ms | 20 - 35 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithoutShrinkage | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 7.08 ms | 45 - 96 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingEncodeKeyWithoutShrinkage | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 12.713 ms | 20 - 62 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithoutShrinkage | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 35.671 ms | 20 - 63 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithoutShrinkage | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 8.299 ms | 20 - 35 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithoutShrinkage | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 13.36 ms | 20 - 64 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithoutShrinkage | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 8.164 ms | 20 - 32 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithoutShrinkage | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 12.713 ms | 20 - 62 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithoutShrinkage | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.661 ms | 18 - 69 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithoutShrinkage | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.191 ms | 63 - 107 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingEncodeKeyWithoutShrinkage | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 4.602 ms | 19 - 66 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithoutShrinkage | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 4.603 ms | 60 - 128 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingEncodeKeyWithoutShrinkage | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 3.818 ms | 0 - 46 MB | NPU | Track-Anything.tflite |
| TrackAnythingEncodeKeyWithoutShrinkage | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 3.758 ms | 2 - 76 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingEncodeKeyWithoutShrinkage | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 6.869 ms | 66 - 66 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingSegment | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 113.201 ms | 1 - 82 MB | NPU | Track-Anything.tflite |
| TrackAnythingSegment | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 38.3 ms | 1 - 138 MB | NPU | Track-Anything.tflite |
| TrackAnythingSegment | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 28.979 ms | 2 - 24 MB | NPU | Track-Anything.tflite |
| TrackAnythingSegment | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 23.803 ms | 0 - 53 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingSegment | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 38.644 ms | 2 - 80 MB | NPU | Track-Anything.tflite |
| TrackAnythingSegment | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 113.201 ms | 1 - 82 MB | NPU | Track-Anything.tflite |
| TrackAnythingSegment | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 29.069 ms | 2 - 22 MB | NPU | Track-Anything.tflite |
| TrackAnythingSegment | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 41.848 ms | 1 - 81 MB | NPU | Track-Anything.tflite |
| TrackAnythingSegment | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 29.044 ms | 2 - 20 MB | NPU | Track-Anything.tflite |
| TrackAnythingSegment | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 38.644 ms | 2 - 80 MB | NPU | Track-Anything.tflite |
| TrackAnythingSegment | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 21.516 ms | 1 - 133 MB | NPU | Track-Anything.tflite |
| TrackAnythingSegment | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 17.914 ms | 24 - 83 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingSegment | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 17.729 ms | 0 - 66 MB | NPU | Track-Anything.tflite |
| TrackAnythingSegment | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 14.002 ms | 7 - 76 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingSegment | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 14.47 ms | 0 - 90 MB | NPU | Track-Anything.tflite |
| TrackAnythingSegment | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | ONNX | 10.822 ms | 25 - 92 MB | NPU | Track-Anything.onnx.zip |
| TrackAnythingSegment | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 23.717 ms | 38 - 38 MB | NPU | Track-Anything.onnx.zip |
Installation
Install the package via pip:
# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
pip install "qai-hub-models[track-anything]" git+https://github.com/ChaoningZhang/MobileSAM@34bbbfd --use-pep517
Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
Sign-in to Qualcomm® AI Hub Workbench with your
Qualcomm® ID. Once signed in navigate to Account -> Settings -> API Token.
With this API token, you can configure your client to run models on the cloud hosted devices.
qai-hub configure --api_token API_TOKEN
Navigate to docs for more information.
Demo off target
The package contains a simple end-to-end demo that downloads pre-trained weights and runs this model on a sample input.
python -m qai_hub_models.models.track_anything.demo
The above demo runs a reference implementation of pre-processing, model inference, and post processing.
NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).
%run -m qai_hub_models.models.track_anything.demo
Run model on a cloud-hosted device
In addition to the demo, you can also run the model on a cloud-hosted Qualcomm® device. This script does the following:
- Performance check on-device on a cloud-hosted device
- Downloads compiled assets that can be deployed on-device for Android.
- Accuracy check between PyTorch and on-device outputs.
python -m qai_hub_models.models.track_anything.export
How does this work?
This export script leverages Qualcomm® AI Hub to optimize, validate, and deploy this model on-device. Lets go through each step below in detail:
Step 1: Compile model for on-device deployment
To compile a PyTorch model for on-device deployment, we first trace the model
in memory using the jit.trace and then call the submit_compile_job API.
import torch
import qai_hub as hub
from qai_hub_models.models.track_anything import Model
# Load the model
torch_model = Model.from_pretrained()
# Device
device = hub.Device("Samsung Galaxy S25")
# Trace model
input_shape = torch_model.get_input_spec()
sample_inputs = torch_model.sample_inputs()
pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
# Compile model on a specific device
compile_job = hub.submit_compile_job(
model=pt_model,
device=device,
input_specs=torch_model.get_input_spec(),
)
# Get target model to run on-device
target_model = compile_job.get_target_model()
Step 2: Performance profiling on cloud-hosted device
After compiling models from step 1. Models can be profiled model on-device using the
target_model. Note that this scripts runs the model on a device automatically
provisioned in the cloud. Once the job is submitted, you can navigate to a
provided job URL to view a variety of on-device performance metrics.
profile_job = hub.submit_profile_job(
model=target_model,
device=device,
)
Step 3: Verify on-device accuracy
To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device.
input_data = torch_model.sample_inputs()
inference_job = hub.submit_inference_job(
model=target_model,
device=device,
inputs=input_data,
)
on_device_output = inference_job.download_output_data()
With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output.
Note: This on-device profiling and inference requires access to Qualcomm® AI Hub Workbench. Sign up for access.
Run demo on a cloud-hosted device
You can also run the demo on-device.
python -m qai_hub_models.models.track_anything.demo --eval-mode on-device
NOTE: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above).
%run -m qai_hub_models.models.track_anything.demo -- --eval-mode on-device
Deploying compiled model to Android
The models can be deployed using multiple runtimes:
TensorFlow Lite (
.tfliteexport): This tutorial provides a guide to deploy the .tflite model in an Android application.QNN (
.soexport ): This sample app provides instructions on how to use the.soshared library in an Android application.
View on Qualcomm® AI Hub
Get more details on Track-Anything's performance across various devices here. Explore all available models on Qualcomm® AI Hub
License
- The license for the original implementation of Track-Anything can be found here.
- The license for the compiled assets for on-device deployment 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.
- Downloads last month
- 76
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support