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 - 76 MB | NPU | -- |
| Yolo-v3 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 21.993 ms | 1 - 11 MB | NPU | -- |
| Yolo-v3 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 18.063 ms | 0 - 90 MB | NPU | -- |
| Yolo-v3 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 12.038 ms | 5 - 36 MB | NPU | -- |
| Yolo-v3 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 16.571 ms | 0 - 11 MB | NPU | -- |
| Yolo-v3 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 8.213 ms | 5 - 7 MB | NPU | -- |
| Yolo-v3 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 17.661 ms | 0 - 76 MB | NPU | -- |
| Yolo-v3 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 9.65 ms | 1 - 12 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 16.48 ms | 0 - 13 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 8.122 ms | 6 - 24 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 12.774 ms | 4 - 63 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 10.712 ms | 0 - 100 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 5.892 ms | 5 - 59 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 9.83 ms | 11 - 48 MB | NPU | -- |
| Yolo-v3 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 8.077 ms | 0 - 79 MB | NPU | -- |
| Yolo-v3 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 6.041 ms | 5 - 64 MB | NPU | -- |
| Yolo-v3 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 10.376 ms | 11 - 44 MB | NPU | -- |
| Yolo-v3 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 8.381 ms | 5 - 5 MB | NPU | -- |
| Yolo-v3 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 14.343 ms | 7 - 7 MB | NPU | -- |
| Yolo-v3 | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 13.664 ms | 1 - 10 MB | NPU | -- |
| Yolo-v3 | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 8.523 ms | 2 - 50 MB | NPU | -- |
| Yolo-v3 | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 6.272 ms | 2 - 4 MB | NPU | -- |
| Yolo-v3 | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 6.677 ms | 1 - 12 MB | NPU | -- |
| Yolo-v3 | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 19.609 ms | 2 - 15 MB | NPU | -- |
| Yolo-v3 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 6.267 ms | 2 - 12 MB | NPU | -- |
| Yolo-v3 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 12.807 ms | 9 - 68 MB | NPU | -- |
| Yolo-v3 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 4.565 ms | 2 - 48 MB | NPU | -- |
| Yolo-v3 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 9.336 ms | 10 - 53 MB | NPU | -- |
| Yolo-v3 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 4.467 ms | 2 - 33 MB | NPU | -- |
| Yolo-v3 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 9.784 ms | 7 - 34 MB | NPU | -- |
| Yolo-v3 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 6.772 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
- 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.
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
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support