Yolo-v3: Optimized for Mobile Deployment

Real-time object detection optimized for mobile and edge

YoloV3 is a machine learning model that predicts bounding boxes and classes of objects in an image.

This model is an implementation of Yolo-v3 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: YoloV3 Tiny
    • Input resolution: 416p (416x416)
    • Number of parameters: 8.85M
    • Model size (float): 24.4 MB
Model Precision Device Chipset Target Runtime Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit Target Model
Yolo-v3 float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) TFLITE 31.893 ms 0 - 70 MB NPU --
Yolo-v3 float QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 22.337 ms 0 - 10 MB NPU --
Yolo-v3 float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) TFLITE 18.08 ms 0 - 86 MB NPU --
Yolo-v3 float QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 12.484 ms 5 - 35 MB NPU --
Yolo-v3 float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) TFLITE 16.645 ms 0 - 7 MB NPU --
Yolo-v3 float QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 8.348 ms 5 - 9 MB NPU --
Yolo-v3 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) TFLITE 17.779 ms 0 - 72 MB NPU --
Yolo-v3 float QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 9.892 ms 1 - 16 MB NPU --
Yolo-v3 float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile TFLITE 16.402 ms 0 - 7 MB NPU --
Yolo-v3 float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 8.419 ms 5 - 12 MB NPU --
Yolo-v3 float Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 13.158 ms 7 - 79 MB NPU --
Yolo-v3 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile TFLITE 10.671 ms 0 - 98 MB NPU --
Yolo-v3 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 6.127 ms 5 - 41 MB NPU --
Yolo-v3 float Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 12.245 ms 16 - 46 MB NPU --
Yolo-v3 float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile TFLITE 8.377 ms 0 - 73 MB NPU --
Yolo-v3 float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 6.417 ms 5 - 34 MB NPU --
Yolo-v3 float Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 10.412 ms 12 - 41 MB NPU --
Yolo-v3 float Snapdragon X Elite CRD Snapdragon® X Elite QNN 8.644 ms 5 - 5 MB NPU --
Yolo-v3 float Snapdragon X Elite CRD Snapdragon® X Elite ONNX 13.808 ms 6 - 6 MB NPU --
Yolo-v3 w8a16 QCS8275 (Proxy) Qualcomm® QCS8275 (Proxy) QNN 14.031 ms 1 - 11 MB NPU --
Yolo-v3 w8a16 QCS8450 (Proxy) Qualcomm® QCS8450 (Proxy) QNN 9.518 ms 2 - 51 MB NPU --
Yolo-v3 w8a16 QCS8550 (Proxy) Qualcomm® QCS8550 (Proxy) QNN 6.465 ms 2 - 5 MB NPU --
Yolo-v3 w8a16 QCS9075 (Proxy) Qualcomm® QCS9075 (Proxy) QNN 6.842 ms 0 - 14 MB NPU --
Yolo-v3 w8a16 RB3 Gen 2 (Proxy) Qualcomm® QCS6490 (Proxy) QNN 20.066 ms 2 - 16 MB NPU --
Yolo-v3 w8a16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile QNN 6.442 ms 2 - 12 MB NPU --
Yolo-v3 w8a16 Samsung Galaxy S23 Snapdragon® 8 Gen 2 Mobile ONNX 11.291 ms 6 - 55 MB NPU --
Yolo-v3 w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile QNN 4.734 ms 2 - 46 MB NPU --
Yolo-v3 w8a16 Samsung Galaxy S24 Snapdragon® 8 Gen 3 Mobile ONNX 8.894 ms 10 - 52 MB NPU --
Yolo-v3 w8a16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile QNN 4.099 ms 2 - 32 MB NPU --
Yolo-v3 w8a16 Snapdragon 8 Elite QRD Snapdragon® 8 Elite Mobile ONNX 11.027 ms 10 - 34 MB NPU --
Yolo-v3 w8a16 Snapdragon X Elite CRD Snapdragon® X Elite QNN 6.958 ms 2 - 2 MB NPU --

License

  • The license for the original implementation of Yolo-v3 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