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 | 32.04 ms | 0 - 69 MB | NPU | -- |
| Yolo-v3 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 22.141 ms | 4 - 13 MB | NPU | -- |
| Yolo-v3 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 17.861 ms | 0 - 87 MB | NPU | -- |
| Yolo-v3 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 12.751 ms | 5 - 36 MB | NPU | -- |
| Yolo-v3 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 16.573 ms | 0 - 7 MB | NPU | -- |
| Yolo-v3 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 8.35 ms | 5 - 7 MB | NPU | -- |
| Yolo-v3 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 17.878 ms | 0 - 72 MB | NPU | -- |
| Yolo-v3 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 9.893 ms | 1 - 16 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 16.29 ms | 0 - 8 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 8.392 ms | 5 - 13 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 12.715 ms | 6 - 72 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 10.644 ms | 0 - 91 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 6.103 ms | 5 - 39 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 9.401 ms | 12 - 47 MB | NPU | -- |
| Yolo-v3 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 8.381 ms | 0 - 73 MB | NPU | -- |
| Yolo-v3 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 6.412 ms | 5 - 35 MB | NPU | -- |
| Yolo-v3 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 11.415 ms | 13 - 41 MB | NPU | -- |
| Yolo-v3 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 8.609 ms | 5 - 5 MB | NPU | -- |
| Yolo-v3 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 14.6 ms | 6 - 6 MB | NPU | -- |
| Yolo-v3 | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN | 14.044 ms | 2 - 12 MB | NPU | -- |
| Yolo-v3 | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN | 9.515 ms | 2 - 48 MB | NPU | -- |
| Yolo-v3 | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN | 6.459 ms | 2 - 5 MB | NPU | -- |
| Yolo-v3 | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN | 6.871 ms | 2 - 16 MB | NPU | -- |
| Yolo-v3 | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN | 20.517 ms | 2 - 14 MB | NPU | -- |
| Yolo-v3 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN | 6.448 ms | 2 - 12 MB | NPU | -- |
| Yolo-v3 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 10.932 ms | 6 - 49 MB | NPU | -- |
| Yolo-v3 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN | 4.733 ms | 2 - 49 MB | NPU | -- |
| Yolo-v3 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 8.901 ms | 10 - 53 MB | NPU | -- |
| Yolo-v3 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 4.099 ms | 2 - 30 MB | NPU | -- |
| Yolo-v3 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 11.279 ms | 14 - 37 MB | NPU | -- |
| Yolo-v3 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 6.959 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