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: 11.5M
- Model size (float): 43.9 MB
- Model size (w8a16): 16.9 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 | 31.683 ms | 0 - 76 MB | NPU | -- |
| Yolo-v3 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 21.753 ms | 4 - 94 MB | NPU | -- |
| Yolo-v3 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 17.902 ms | 0 - 88 MB | NPU | -- |
| Yolo-v3 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 12.001 ms | 4 - 75 MB | NPU | -- |
| Yolo-v3 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 16.371 ms | 0 - 14 MB | NPU | -- |
| Yolo-v3 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 8.133 ms | 5 - 21 MB | NPU | -- |
| Yolo-v3 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 17.753 ms | 0 - 76 MB | NPU | -- |
| Yolo-v3 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 9.735 ms | 2 - 87 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 16.53 ms | 0 - 12 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 8.129 ms | 5 - 22 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 9.178 ms | 0 - 79 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 10.757 ms | 0 - 99 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 5.872 ms | 5 - 100 MB | NPU | -- |
| Yolo-v3 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 6.757 ms | 5 - 114 MB | NPU | -- |
| Yolo-v3 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 8.081 ms | 0 - 79 MB | NPU | -- |
| Yolo-v3 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 6.046 ms | 5 - 102 MB | NPU | -- |
| Yolo-v3 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 6.684 ms | 5 - 93 MB | NPU | -- |
| Yolo-v3 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 9.061 ms | 0 - 0 MB | NPU | -- |
| Yolo-v3 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 9.226 ms | 21 - 21 MB | NPU | -- |
| Yolo-v3 | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 13.726 ms | 2 - 68 MB | NPU | -- |
| Yolo-v3 | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 8.413 ms | 2 - 92 MB | NPU | -- |
| Yolo-v3 | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 6.258 ms | 2 - 28 MB | NPU | -- |
| Yolo-v3 | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.696 ms | 2 - 69 MB | NPU | -- |
| Yolo-v3 | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 19.487 ms | 2 - 79 MB | NPU | -- |
| Yolo-v3 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 6.278 ms | 2 - 19 MB | NPU | -- |
| Yolo-v3 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 8.787 ms | 0 - 41 MB | NPU | -- |
| Yolo-v3 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 4.545 ms | 2 - 93 MB | NPU | -- |
| Yolo-v3 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.98 ms | 2 - 103 MB | NPU | -- |
| Yolo-v3 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 4.834 ms | 2 - 76 MB | NPU | -- |
| Yolo-v3 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 6.218 ms | 2 - 100 MB | NPU | -- |
| Yolo-v3 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 7.428 ms | 83 - 83 MB | NPU | -- |
| Yolo-v3 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 9.078 ms | 15 - 15 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