README.md

---
library_name: pytorch
license: gpl-3.0
tags:
- real_time
- quantized
- android
pipeline_tag: object-detection

---

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolov7_quantized/web-assets/model_demo.png)

# Yolo-v7-Quantized: Optimized for Mobile Deployment
## Quantized 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 post-training quantized to int8 using samples from the COCO dataset.

This model is an implementation of Yolo-v7-Quantized found [here](https://github.com/WongKinYiu/yolov7/).


 More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/yolov7_quantized).

### Model Details

- **Model Type:** Object detection
- **Model Stats:**
  - Model checkpoint: YoloV7 Tiny
  - Input resolution: 640x640
  - Number of parameters: 6.24M
  - Model size: 6.23 MB

| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|---|---|---|---|---|---|---|---|---|
| Yolo-v7-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 4.484 ms | 0 - 11 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 4.37 ms | 1 - 4 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 6.269 ms | 0 - 53 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 2.899 ms | 0 - 47 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 2.89 ms | 1 - 21 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 4.355 ms | 1 - 103 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 2.995 ms | 0 - 40 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 3.783 ms | 1 - 55 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 4.381 ms | 0 - 99 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | SA7255P ADP | SA7255P | TFLITE | 19.602 ms | 0 - 31 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | SA7255P ADP | SA7255P | QNN | 19.873 ms | 1 - 8 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 4.481 ms | 0 - 11 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 4.369 ms | 1 - 4 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | SA8295P ADP | SA8295P | TFLITE | 6.158 ms | 0 - 34 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | SA8295P ADP | SA8295P | QNN | 6.459 ms | 1 - 12 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 4.448 ms | 0 - 11 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 4.377 ms | 1 - 4 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | SA8775P ADP | SA8775P | TFLITE | 6.216 ms | 0 - 31 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | SA8775P ADP | SA8775P | QNN | 6.181 ms | 1 - 8 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 11.976 ms | 0 - 54 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 14.865 ms | 1 - 13 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 60.283 ms | 15 - 55 MB | INT8 | GPU | -- |
| Yolo-v7-Quantized | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 19.602 ms | 0 - 31 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 19.873 ms | 1 - 8 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 4.501 ms | 0 - 11 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 4.418 ms | 1 - 3 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 6.216 ms | 0 - 31 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 6.181 ms | 1 - 8 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 5.083 ms | 0 - 44 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 5.623 ms | 1 - 62 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 4.869 ms | 1 - 1 MB | INT8 | NPU | -- |
| Yolo-v7-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.008 ms | 8 - 8 MB | INT8 | NPU | -- |




## License
* The license for the original implementation of Yolo-v7-Quantized can be found
  [here](https://github.com/WongKinYiu/yolov7/blob/main/LICENSE.md).
* The license for the compiled assets for on-device deployment can be found [here](https://github.com/WongKinYiu/yolov7/blob/main/LICENSE.md)



## References
* [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://arxiv.org/abs/2207.02696)
* [Source Model Implementation](https://github.com/WongKinYiu/yolov7/)



## Community
* Join [our AI Hub Slack community](https://qualcomm-ai-hub.slack.com/join/shared_invite/zt-2d5zsmas3-Sj0Q9TzslueCjS31eXG2UA#/shared-invite/email) to collaborate, post questions and learn more about on-device AI.
* For questions or feedback please [reach out to us](mailto:[email protected]).

## 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