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: Model_use_case.object_detection
  • Model Stats:
    • Model checkpoint: YoloV5-M
    • Input resolution: 640x640
    • Number of parameters: 21.2M
    • Model size: 81.1 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
Yolo-v5 float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 72.237 ms 6 - 80 MB NPU --
Yolo-v5 float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 67.981 ms 1 - 11 MB NPU --
Yolo-v5 float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 34.752 ms 6 - 85 MB NPU --
Yolo-v5 float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 36.689 ms 5 - 58 MB NPU --
Yolo-v5 float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 22.909 ms 1 - 33 MB NPU --
Yolo-v5 float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 20.59 ms 5 - 14 MB NPU --
Yolo-v5 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 28.768 ms 6 - 81 MB NPU --
Yolo-v5 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 26.83 ms 3 - 16 MB NPU --
Yolo-v5 float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 22.965 ms 6 - 38 MB NPU --
Yolo-v5 float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 20.664 ms 5 - 38 MB NPU --
Yolo-v5 float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 23.117 ms 2 - 132 MB NPU --
Yolo-v5 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 17.537 ms 4 - 102 MB NPU --
Yolo-v5 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 16.097 ms 5 - 128 MB NPU --
Yolo-v5 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 18.075 ms 3 - 139 MB NPU --
Yolo-v5 float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 16.197 ms 5 - 82 MB NPU --
Yolo-v5 float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 13.158 ms 5 - 127 MB NPU --
Yolo-v5 float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 16.483 ms 7 - 133 MB NPU --
Yolo-v5 float Snapdragon X Elite CRD Snapdragon® X Elite QNN 21.104 ms 5 - 5 MB NPU --
Yolo-v5 float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 25.84 ms 39 - 39 MB NPU --
Yolo-v5 w8a16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 25.413 ms 0 - 10 MB NPU --
Yolo-v5 w8a16 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 17.219 ms 2 - 85 MB NPU --
Yolo-v5 w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 12.515 ms 2 - 5 MB NPU --
Yolo-v5 w8a16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 12.829 ms 2 - 16 MB NPU --
Yolo-v5 w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN 55.56 ms 2 - 14 MB NPU --
Yolo-v5 w8a16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 12.485 ms 2 - 27 MB NPU --
Yolo-v5 w8a16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 18.84 ms 1 - 69 MB NPU --
Yolo-v5 w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 8.295 ms 2 - 80 MB NPU --
Yolo-v5 w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 13.29 ms 0 - 171 MB NPU --
Yolo-v5 w8a16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 7.295 ms 2 - 73 MB NPU --
Yolo-v5 w8a16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 9.545 ms 2 - 161 MB NPU --
Yolo-v5 w8a16 Snapdragon X Elite CRD Snapdragon® X Elite QNN 13.351 ms 2 - 2 MB NPU --
Yolo-v5 w8a16 Snapdragon X Elite CRD Snapdragon® X Elite ONNX 22.063 ms 20 - 20 MB 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 isn't deployed by any Inference Provider. 🙋 Ask for provider support