Hugging Face's logo

qualcomm
/
OSNet

PyTorch
backbone
real_time
android
video-object-tracking
Model card Files
xet
 Community

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

OSNet: Optimized for Qualcomm Devices

OSNet is a compact convolutional architecture for person re-identification. It extracts discriminative embeddings that can be compared with cosine similarity for person matching across camera views.

This is based on the implementation of OSNet 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 2.45, ONNX Runtime 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a8 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download
TFLITE w8a8 Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit OSNet 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 OSNet on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.video_object_tracking

Model Stats:

  • Input resolution: 256x128
  • Model checkpoint: osnet_x1_0_market_256x128_amsgrad_ep150_stp60_lr0.0015_b64_fb10_softmax_labelsmooth_flip.pth
  • Model size (float): 8.69 MB
  • Model size (w8a8): 3.57 MB
  • Number of parameters: 2.68M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
OSNet ONNX float Snapdragon® X2 Elite 0.515 ms 1 - 1 MB NPU
OSNet ONNX float Snapdragon® X Elite 0.928 ms 0 - 0 MB NPU
OSNet ONNX float Snapdragon® 8 Gen 3 Mobile 0.614 ms 0 - 70 MB NPU
OSNet ONNX float Snapdragon® 8 Gen 1 Mobile 1.593 ms 0 - 68 MB NPU
OSNet ONNX float Qualcomm® Dragonwing™ IQ-8275 1.41 ms 0 - 4 MB NPU
OSNet ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.892 ms 0 - 6 MB NPU
OSNet ONNX float Qualcomm® QCS8450 1.593 ms 0 - 68 MB NPU
OSNet ONNX float Qualcomm® Dragonwing™ IQ-9075 1.392 ms 0 - 3 MB NPU
OSNet ONNX float Qualcomm® Dragonwing™ IQ-X7181 0.928 ms 0 - 0 MB NPU
OSNet ONNX float Qualcomm® Dragonwing™ Q-8750 0.487 ms 0 - 50 MB NPU
OSNet ONNX float Snapdragon® 8 Elite Mobile 0.487 ms 0 - 50 MB NPU
OSNet ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.455 ms 0 - 54 MB NPU
OSNet ONNX w8a8 Snapdragon® X2 Elite 0.278 ms 1 - 1 MB NPU
OSNet ONNX w8a8 Snapdragon® X Elite 0.556 ms 0 - 0 MB NPU
OSNet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.38 ms 0 - 75 MB NPU
OSNet ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.704 ms 0 - 75 MB NPU
OSNet ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 1.908 ms 0 - 3 MB NPU
OSNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 0.628 ms 0 - 4 MB NPU
OSNet ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.553 ms 0 - 5 MB NPU
OSNet ONNX w8a8 Qualcomm® QCS8450 0.704 ms 0 - 75 MB NPU
OSNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 0.673 ms 0 - 3 MB NPU
OSNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.556 ms 0 - 0 MB NPU
OSNet ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 2.858 ms 0 - 57 MB NPU
OSNet ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 0.589 ms 0 - 58 MB NPU
OSNet ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.335 ms 0 - 62 MB NPU
OSNet ONNX w8a8 Snapdragon® 8 Elite Mobile 0.335 ms 0 - 62 MB NPU
OSNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.289 ms 0 - 64 MB NPU
OSNet ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 0.589 ms 0 - 58 MB NPU
OSNet QNN_DLC float Snapdragon® X2 Elite 0.666 ms 0 - 0 MB NPU
OSNet QNN_DLC float Snapdragon® X Elite 1.233 ms 0 - 0 MB NPU
OSNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.703 ms 0 - 59 MB NPU
OSNet QNN_DLC float Snapdragon® 8 Gen 1 Mobile 2.02 ms 0 - 62 MB NPU
OSNet QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 1.445 ms 0 - 3 MB NPU
OSNet QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.037 ms 0 - 2 MB NPU
OSNet QNN_DLC float Qualcomm® SA8775P 1.688 ms 0 - 46 MB NPU
OSNet QNN_DLC float Qualcomm® SA8650P 1.688 ms 0 - 46 MB NPU
OSNet QNN_DLC float Qualcomm® SA8255P 1.688 ms 0 - 46 MB NPU
OSNet QNN_DLC float Qualcomm® QCS8450 2.02 ms 0 - 62 MB NPU
OSNet QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.487 ms 0 - 2 MB NPU
OSNet QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.233 ms 0 - 0 MB NPU
OSNet QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.532 ms 0 - 44 MB NPU
OSNet QNN_DLC float Qualcomm® SA7255P 4.556 ms 0 - 43 MB NPU
OSNet QNN_DLC float Qualcomm® SA8295P 2.195 ms 0 - 40 MB NPU
OSNet QNN_DLC float Snapdragon® 8 Elite Mobile 0.532 ms 0 - 44 MB NPU
OSNet QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.434 ms 0 - 46 MB NPU
OSNet QNN_DLC w8a8 Snapdragon® X2 Elite 0.35 ms 0 - 0 MB NPU
OSNet QNN_DLC w8a8 Snapdragon® X Elite 0.657 ms 0 - 0 MB NPU
OSNet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.362 ms 0 - 56 MB NPU
OSNet QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.677 ms 0 - 60 MB NPU
OSNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 1.488 ms 0 - 2 MB NPU
OSNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.595 ms 0 - 3 MB NPU
OSNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.533 ms 0 - 2 MB NPU
OSNet QNN_DLC w8a8 Qualcomm® SA8775P 0.739 ms 0 - 48 MB NPU
OSNet QNN_DLC w8a8 Qualcomm® SA8650P 0.739 ms 0 - 48 MB NPU
OSNet QNN_DLC w8a8 Qualcomm® SA8255P 0.739 ms 0 - 48 MB NPU
OSNet QNN_DLC w8a8 Qualcomm® QCS8450 0.677 ms 0 - 60 MB NPU
OSNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 0.615 ms 2 - 4 MB NPU
OSNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.657 ms 0 - 0 MB NPU
OSNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 2.8 ms 0 - 41 MB NPU
OSNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 0.536 ms 0 - 43 MB NPU
OSNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.287 ms 0 - 43 MB NPU
OSNet QNN_DLC w8a8 Qualcomm® SA8295P 0.995 ms 0 - 43 MB NPU
OSNet QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.287 ms 0 - 43 MB NPU
OSNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.23 ms 0 - 45 MB NPU
OSNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.536 ms 0 - 43 MB NPU
OSNet TFLITE float Snapdragon® 8 Gen 3 Mobile 0.717 ms 0 - 59 MB NPU
OSNet TFLITE float Snapdragon® 8 Gen 1 Mobile 2.035 ms 0 - 62 MB NPU
OSNet TFLITE float Qualcomm® Dragonwing™ IQ-8275 1.466 ms 0 - 8 MB NPU
OSNet TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.108 ms 0 - 2 MB NPU
OSNet TFLITE float Qualcomm® SA8775P 1.755 ms 0 - 49 MB NPU
OSNet TFLITE float Qualcomm® SA8650P 1.755 ms 0 - 49 MB NPU
OSNet TFLITE float Qualcomm® SA8255P 1.755 ms 0 - 49 MB NPU
OSNet TFLITE float Qualcomm® QCS8450 2.035 ms 0 - 62 MB NPU
OSNet TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.566 ms 0 - 7 MB NPU
OSNet TFLITE float Qualcomm® Dragonwing™ Q-8750 0.536 ms 0 - 43 MB NPU
OSNet TFLITE float Qualcomm® SA7255P 4.57 ms 0 - 45 MB NPU
OSNet TFLITE float Qualcomm® SA8295P 2.235 ms 0 - 39 MB NPU
OSNet TFLITE float Snapdragon® 8 Elite Mobile 0.536 ms 0 - 43 MB NPU
OSNet TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.445 ms 0 - 45 MB NPU
OSNet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.312 ms 0 - 55 MB NPU
OSNet TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.588 ms 0 - 59 MB NPU
OSNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 2.282 ms 0 - 12 MB NPU
OSNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.489 ms 0 - 5 MB NPU
OSNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.445 ms 0 - 5 MB NPU
OSNet TFLITE w8a8 Qualcomm® SA8775P 0.675 ms 0 - 44 MB NPU
OSNet TFLITE w8a8 Qualcomm® SA8650P 0.675 ms 0 - 44 MB NPU
OSNet TFLITE w8a8 Qualcomm® SA8255P 0.675 ms 0 - 44 MB NPU
OSNet TFLITE w8a8 Qualcomm® QCS8450 0.588 ms 0 - 59 MB NPU
OSNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 0.534 ms 0 - 5 MB NPU
OSNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 3.494 ms 0 - 40 MB NPU
OSNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 0.912 ms 0 - 42 MB NPU
OSNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.257 ms 0 - 45 MB NPU
OSNet TFLITE w8a8 Qualcomm® SA7255P 1.145 ms 0 - 41 MB NPU
OSNet TFLITE w8a8 Qualcomm® SA8295P 0.922 ms 0 - 40 MB NPU
OSNet TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.257 ms 0 - 45 MB NPU
OSNet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.215 ms 0 - 42 MB NPU
OSNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.912 ms 0 - 42 MB NPU

License

  • The license for the original implementation of OSNet can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/OSNet