Yolo-v7: Optimized for Mobile Deployment
Real-time object detection optimized for mobile and edge
YoloV7 is a machine learning model that predicts bounding boxes and classes of objects in an image.
This model is an implementation of Yolo-v7 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: YoloV7 Tiny
- Input resolution: 640x640
- Number of parameters: 6.24M
- Model size (float): 23.8 MB
- Model size (w8a8): 6.23 MB
- Model size (w8a16): 6.66 MB
| Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model |
|---|---|---|---|---|---|---|---|---|
| Yolo-v7 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 34.815 ms | 1 - 28 MB | NPU | -- |
| Yolo-v7 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 22.796 ms | 0 - 119 MB | NPU | -- |
| Yolo-v7 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 20.598 ms | 1 - 45 MB | NPU | -- |
| Yolo-v7 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 13.777 ms | 5 - 44 MB | NPU | -- |
| Yolo-v7 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 17.337 ms | 1 - 15 MB | NPU | -- |
| Yolo-v7 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 8.761 ms | 5 - 22 MB | NPU | -- |
| Yolo-v7 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 18.764 ms | 1 - 28 MB | NPU | -- |
| Yolo-v7 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 10.511 ms | 1 - 123 MB | NPU | -- |
| Yolo-v7 | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 34.815 ms | 1 - 28 MB | NPU | -- |
| Yolo-v7 | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 22.796 ms | 0 - 119 MB | NPU | -- |
| Yolo-v7 | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 17.744 ms | 1 - 17 MB | NPU | -- |
| Yolo-v7 | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 8.792 ms | 0 - 97 MB | NPU | -- |
| Yolo-v7 | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 22.139 ms | 1 - 32 MB | NPU | -- |
| Yolo-v7 | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 13.626 ms | 2 - 32 MB | NPU | -- |
| Yolo-v7 | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 17.625 ms | 0 - 59 MB | NPU | -- |
| Yolo-v7 | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 8.771 ms | 0 - 78 MB | NPU | -- |
| Yolo-v7 | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 18.764 ms | 1 - 28 MB | NPU | -- |
| Yolo-v7 | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 10.511 ms | 1 - 123 MB | NPU | -- |
| Yolo-v7 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 17.533 ms | 1 - 15 MB | NPU | -- |
| Yolo-v7 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 8.78 ms | 0 - 88 MB | NPU | -- |
| Yolo-v7 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 11.033 ms | 1 - 46 MB | NPU | -- |
| Yolo-v7 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 12.861 ms | 0 - 41 MB | NPU | -- |
| Yolo-v7 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 5.823 ms | 5 - 275 MB | NPU | -- |
| Yolo-v7 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 7.913 ms | 0 - 211 MB | NPU | -- |
| Yolo-v7 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 12.331 ms | 1 - 34 MB | NPU | -- |
| Yolo-v7 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 5.908 ms | 5 - 136 MB | NPU | -- |
| Yolo-v7 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 7.213 ms | 5 - 127 MB | NPU | -- |
| Yolo-v7 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 9.64 ms | 87 - 87 MB | NPU | -- |
| Yolo-v7 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 13.096 ms | 10 - 10 MB | NPU | -- |
| Yolo-v7 | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 17.905 ms | 1 - 34 MB | NPU | -- |
| Yolo-v7 | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 10.617 ms | 2 - 52 MB | NPU | -- |
| Yolo-v7 | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 9.369 ms | 2 - 14 MB | NPU | -- |
| Yolo-v7 | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 10.014 ms | 0 - 34 MB | NPU | -- |
| Yolo-v7 | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 30.109 ms | 2 - 36 MB | NPU | -- |
| Yolo-v7 | w8a16 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 17.905 ms | 1 - 34 MB | NPU | -- |
| Yolo-v7 | w8a16 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 9.326 ms | 2 - 13 MB | NPU | -- |
| Yolo-v7 | w8a16 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 11.731 ms | 1 - 42 MB | NPU | -- |
| Yolo-v7 | w8a16 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 9.406 ms | 2 - 16 MB | NPU | -- |
| Yolo-v7 | w8a16 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 10.014 ms | 0 - 34 MB | NPU | -- |
| Yolo-v7 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 9.333 ms | 2 - 15 MB | NPU | -- |
| Yolo-v7 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 6.464 ms | 1 - 45 MB | NPU | -- |
| Yolo-v7 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 6.179 ms | 2 - 51 MB | NPU | -- |
| Yolo-v7 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 4.64 ms | 3 - 216 MB | NPU | -- |
| Yolo-v7 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 6.303 ms | 2 - 52 MB | NPU | -- |
| Yolo-v7 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 4.012 ms | 1 - 124 MB | NPU | -- |
| Yolo-v7 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 10.201 ms | 14 - 14 MB | NPU | -- |
| Yolo-v7 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 7.044 ms | 5 - 5 MB | NPU | -- |
| Yolo-v7 | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 4.734 ms | 0 - 23 MB | NPU | -- |
| Yolo-v7 | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 4.636 ms | 1 - 28 MB | NPU | -- |
| Yolo-v7 | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 2.731 ms | 0 - 40 MB | NPU | -- |
| Yolo-v7 | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 2.892 ms | 1 - 42 MB | NPU | -- |
| Yolo-v7 | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 2.121 ms | 0 - 6 MB | NPU | -- |
| Yolo-v7 | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 2.083 ms | 1 - 13 MB | NPU | -- |
| Yolo-v7 | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 2.547 ms | 0 - 25 MB | NPU | -- |
| Yolo-v7 | w8a8 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 2.477 ms | 1 - 27 MB | NPU | -- |
| Yolo-v7 | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | TFLITE | 9.69 ms | 0 - 34 MB | NPU | -- |
| Yolo-v7 | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 7.681 ms | 0 - 37 MB | NPU | -- |
| Yolo-v7 | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 59.698 ms | 15 - 60 MB | GPU | -- |
| Yolo-v7 | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 4.734 ms | 0 - 23 MB | NPU | -- |
| Yolo-v7 | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 4.636 ms | 1 - 28 MB | NPU | -- |
| Yolo-v7 | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 2.126 ms | 0 - 31 MB | NPU | -- |
| Yolo-v7 | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 2.084 ms | 1 - 6 MB | NPU | -- |
| Yolo-v7 | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 3.4 ms | 0 - 26 MB | NPU | -- |
| Yolo-v7 | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 3.436 ms | 1 - 33 MB | NPU | -- |
| Yolo-v7 | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 2.118 ms | 0 - 35 MB | NPU | -- |
| Yolo-v7 | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 2.081 ms | 0 - 12 MB | NPU | -- |
| Yolo-v7 | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 2.547 ms | 0 - 25 MB | NPU | -- |
| Yolo-v7 | w8a8 | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 2.477 ms | 1 - 27 MB | NPU | -- |
| Yolo-v7 | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 2.137 ms | 0 - 35 MB | NPU | -- |
| Yolo-v7 | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 2.082 ms | 1 - 12 MB | NPU | -- |
| Yolo-v7 | w8a8 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 3.967 ms | 0 - 53 MB | NPU | -- |
| Yolo-v7 | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 1.425 ms | 0 - 37 MB | NPU | -- |
| Yolo-v7 | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 1.409 ms | 1 - 43 MB | NPU | -- |
| Yolo-v7 | w8a8 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.043 ms | 0 - 255 MB | NPU | -- |
| Yolo-v7 | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 1.372 ms | 0 - 25 MB | NPU | -- |
| Yolo-v7 | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 1.342 ms | 1 - 33 MB | NPU | -- |
| Yolo-v7 | w8a8 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 2.502 ms | 1 - 152 MB | NPU | -- |
| Yolo-v7 | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 2.521 ms | 18 - 18 MB | NPU | -- |
| Yolo-v7 | w8a8 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 4.234 ms | 5 - 5 MB | NPU | -- |
License
- The license for the original implementation of Yolo-v7 can be found here.
- The license for the compiled assets for on-device deployment can be found here
References
- YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
- Source Model Implementation
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