Yolo-v5: Optimized for Mobile Deployment

Real-time object detection optimized for mobile and edge

YoloV5 is a machine learning model that predicts bounding boxes and classes of objects in an image.

This model is an implementation of Yolo-v5 found here.

More details on model performance across various devices, can be found here.

Model Details

  • Model Type: Object detection
  • Model Stats:
    • Model checkpoint: YoloV5-M
    • Input resolution: 640x640
    • Number of parameters: 21.2M
    • Model size: 81.1 MB
Model Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Precision Primary Compute Unit Target Model
Yolo-v5 Samsung Galaxy S23 Snapdragon® 8 Gen 2 TFLITE 23.409 ms 6 - 43 MB FP16 NPU --
Yolo-v5 Samsung Galaxy S23 Snapdragon® 8 Gen 2 QNN 19.013 ms 5 - 8 MB FP16 NPU --
Yolo-v5 Samsung Galaxy S23 Snapdragon® 8 Gen 2 ONNX 21.857 ms 0 - 122 MB FP16 NPU --
Yolo-v5 Samsung Galaxy S24 Snapdragon® 8 Gen 3 TFLITE 18.14 ms 5 - 73 MB FP16 NPU --
Yolo-v5 Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 14.239 ms 5 - 25 MB FP16 NPU --
Yolo-v5 Samsung Galaxy S24 Snapdragon® 8 Gen 3 ONNX 16.524 ms 7 - 158 MB FP16 NPU --
Yolo-v5 Snapdragon 8 Elite QRD Snapdragon® 8 Elite TFLITE 16.688 ms 5 - 72 MB FP16 NPU --
Yolo-v5 Snapdragon 8 Elite QRD Snapdragon® 8 Elite QNN 15.112 ms 5 - 150 MB FP16 NPU --
Yolo-v5 Snapdragon 8 Elite QRD Snapdragon® 8 Elite ONNX 13.239 ms 7 - 160 MB FP16 NPU --
Yolo-v5 QCS8275 (Proxy) QCS8275 Proxy TFLITE 370.16 ms 6 - 71 MB FP16 NPU --
Yolo-v5 QCS8275 (Proxy) QCS8275 Proxy QNN 360.947 ms 0 - 7 MB FP16 NPU --
Yolo-v5 QCS8550 (Proxy) QCS8550 Proxy TFLITE 23.532 ms 6 - 37 MB FP16 NPU --
Yolo-v5 QCS8550 (Proxy) QCS8550 Proxy QNN 18.977 ms 5 - 7 MB FP16 NPU --
Yolo-v5 QCS9075 (Proxy) QCS9075 Proxy QNN 28.25 ms 1 - 9 MB FP16 NPU --
Yolo-v5 QCS8450 (Proxy) QCS8450 Proxy TFLITE 34.248 ms 6 - 49 MB FP16 NPU --
Yolo-v5 QCS8450 (Proxy) QCS8450 Proxy QNN 38.932 ms 5 - 60 MB FP16 NPU --
Yolo-v5 Snapdragon X Elite CRD Snapdragon® X Elite QNN 19.003 ms 5 - 5 MB FP16 NPU --
Yolo-v5 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 23.673 ms 40 - 40 MB FP16 NPU --

License

  • The license for the original implementation of Yolo-v5 can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

Usage and Limitations

Model may not be used for or in connection with any of the following applications:

  • Accessing essential private and public services and benefits;
  • Administration of justice and democratic processes;
  • Assessing or recognizing the emotional state of a person;
  • Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
  • Education and vocational training;
  • Employment and workers management;
  • Exploitation of the vulnerabilities of persons resulting in harmful behavior;
  • General purpose social scoring;
  • Law enforcement;
  • Management and operation of critical infrastructure;
  • Migration, asylum and border control management;
  • Predictive policing;
  • Real-time remote biometric identification in public spaces;
  • Recommender systems of social media platforms;
  • Scraping of facial images (from the internet or otherwise); and/or
  • Subliminal manipulation
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The HF Inference API does not support object-detection models for pytorch library.