--- library_name: pytorch license: other tags: - real_time - android pipeline_tag: object-detection --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolonas/web-assets/model_demo.png) # Yolo-NAS: Optimized for Mobile Deployment ## Real-time object detection optimized for mobile and edge YoloNAS is a machine learning model that predicts bounding boxes and classes of objects in an image. This model is an implementation of Yolo-NAS found [here](https://github.com/Deci-AI/super-gradients). More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/yolonas). ### Model Details - **Model Type:** Object detection - **Model Stats:** - Model checkpoint: YoloNAS Small - Input resolution: 640x640 - Number of parameters: 12.2M - Model size: 46.6 MB | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model |---|---|---|---|---|---|---|---|---| | Yolo-NAS | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 7.9 ms | 0 - 19 MB | FP16 | NPU | -- | | Yolo-NAS | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 8.291 ms | 5 - 7 MB | FP16 | NPU | -- | | Yolo-NAS | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 8.833 ms | 0 - 77 MB | FP16 | NPU | -- | | Yolo-NAS | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 5.345 ms | 0 - 62 MB | FP16 | NPU | -- | | Yolo-NAS | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 5.44 ms | 5 - 23 MB | FP16 | NPU | -- | | Yolo-NAS | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 5.971 ms | 2 - 55 MB | FP16 | NPU | -- | | Yolo-NAS | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 5.431 ms | 0 - 46 MB | FP16 | NPU | -- | | Yolo-NAS | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 5.288 ms | 5 - 31 MB | FP16 | NPU | -- | | Yolo-NAS | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 5.985 ms | 5 - 39 MB | FP16 | NPU | -- | | Yolo-NAS | SA7255P ADP | SA7255P | TFLITE | 220.694 ms | 0 - 43 MB | FP16 | NPU | -- | | Yolo-NAS | SA7255P ADP | SA7255P | QNN | 218.0 ms | 1 - 10 MB | FP16 | NPU | -- | | Yolo-NAS | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 7.877 ms | 0 - 21 MB | FP16 | NPU | -- | | Yolo-NAS | SA8255 (Proxy) | SA8255P Proxy | QNN | 8.341 ms | 5 - 7 MB | FP16 | NPU | -- | | Yolo-NAS | SA8295P ADP | SA8295P | TFLITE | 12.74 ms | 0 - 42 MB | FP16 | NPU | -- | | Yolo-NAS | SA8295P ADP | SA8295P | QNN | 12.799 ms | 0 - 18 MB | FP16 | NPU | -- | | Yolo-NAS | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 7.973 ms | 0 - 20 MB | FP16 | NPU | -- | | Yolo-NAS | SA8650 (Proxy) | SA8650P Proxy | QNN | 8.335 ms | 5 - 7 MB | FP16 | NPU | -- | | Yolo-NAS | SA8775P ADP | SA8775P | TFLITE | 14.238 ms | 0 - 42 MB | FP16 | NPU | -- | | Yolo-NAS | SA8775P ADP | SA8775P | QNN | 14.008 ms | 0 - 10 MB | FP16 | NPU | -- | | Yolo-NAS | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 220.694 ms | 0 - 43 MB | FP16 | NPU | -- | | Yolo-NAS | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 218.0 ms | 1 - 10 MB | FP16 | NPU | -- | | Yolo-NAS | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 7.893 ms | 0 - 19 MB | FP16 | NPU | -- | | Yolo-NAS | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 8.248 ms | 3 - 6 MB | FP16 | NPU | -- | | Yolo-NAS | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 14.238 ms | 0 - 42 MB | FP16 | NPU | -- | | Yolo-NAS | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 14.008 ms | 0 - 10 MB | FP16 | NPU | -- | | Yolo-NAS | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 11.039 ms | 0 - 58 MB | FP16 | NPU | -- | | Yolo-NAS | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 12.474 ms | 5 - 38 MB | FP16 | NPU | -- | | Yolo-NAS | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 8.542 ms | 5 - 5 MB | FP16 | NPU | -- | | Yolo-NAS | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 9.049 ms | 20 - 20 MB | FP16 | NPU | -- | ## License * The license for the original implementation of Yolo-NAS can be found [here](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md#license). * The license for the compiled assets for on-device deployment can be found [here](https://github.com/Deci-AI/super-gradients/blob/master/LICENSE.YOLONAS.md) ## References * [A Next-Generation, Object Detection Foundational Model generated by Deci’s Neural Architecture Search Technology](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md) * [Source Model Implementation](https://github.com/Deci-AI/super-gradients) ## 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:ai-hub-support@qti.qualcomm.com). ## 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