--- 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/yolov5/web-assets/model_demo.png) # Yolo-v5: Optimized for Mobile Deployment ## Real-time object detection optimized for mobile and edge YoloV5 is a machine learning model that predicts bounding boxes and classes of objects in an image. This model is an implementation of Yolo-v5 found [here](https://github.com/ultralytics/yolov5). More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/yolov5). ### Model Details - **Model Type:** Model_use_case.object_detection - **Model Stats:** - Model checkpoint: YoloV5-M - Input resolution: 640x640 - Number of parameters: 21.2M - Model size (float): 81.1 MB - Model size (w8a16): 21.8 MB | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model |---|---|---|---|---|---|---|---|---| | Yolo-v5 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 69.964 ms | 0 - 115 MB | NPU | -- | | Yolo-v5 | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 64.424 ms | 4 - 136 MB | NPU | -- | | Yolo-v5 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 39.135 ms | 1 - 88 MB | NPU | -- | | Yolo-v5 | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 34.534 ms | 5 - 60 MB | NPU | -- | | Yolo-v5 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 21.938 ms | 1 - 19 MB | NPU | -- | | Yolo-v5 | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 20.564 ms | 5 - 36 MB | NPU | -- | | Yolo-v5 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 26.674 ms | 1 - 119 MB | NPU | -- | | Yolo-v5 | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 24.754 ms | 0 - 128 MB | NPU | -- | | Yolo-v5 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 22.313 ms | 1 - 23 MB | NPU | -- | | Yolo-v5 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 20.694 ms | 5 - 42 MB | NPU | -- | | Yolo-v5 | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 23.106 ms | 2 - 111 MB | NPU | -- | | Yolo-v5 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 16.744 ms | 0 - 142 MB | NPU | -- | | Yolo-v5 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 15.396 ms | 5 - 146 MB | NPU | -- | | Yolo-v5 | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 17.563 ms | 4 - 149 MB | NPU | -- | | Yolo-v5 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 13.676 ms | 5 - 134 MB | NPU | -- | | Yolo-v5 | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 16.023 ms | 5 - 139 MB | NPU | -- | | Yolo-v5 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 23.176 ms | 5 - 5 MB | NPU | -- | | Yolo-v5 | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 24.753 ms | 38 - 38 MB | NPU | -- | | Yolo-v5 | w8a16 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 24.684 ms | 2 - 73 MB | NPU | -- | | Yolo-v5 | w8a16 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 16.243 ms | 2 - 85 MB | NPU | -- | | Yolo-v5 | w8a16 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 11.84 ms | 2 - 26 MB | NPU | -- | | Yolo-v5 | w8a16 | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 12.209 ms | 2 - 75 MB | NPU | -- | | Yolo-v5 | w8a16 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 55.451 ms | 2 - 83 MB | NPU | -- | | Yolo-v5 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 11.785 ms | 2 - 25 MB | NPU | -- | | Yolo-v5 | w8a16 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 17.564 ms | 0 - 72 MB | NPU | -- | | Yolo-v5 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 7.89 ms | 2 - 87 MB | NPU | -- | | Yolo-v5 | w8a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 11.914 ms | 1 - 247 MB | NPU | -- | | Yolo-v5 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 6.721 ms | 2 - 102 MB | NPU | -- | | Yolo-v5 | w8a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 8.48 ms | 2 - 206 MB | NPU | -- | | Yolo-v5 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 13.575 ms | 6 - 6 MB | NPU | -- | | Yolo-v5 | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 20.708 ms | 20 - 20 MB | NPU | -- | ## License * The license for the original implementation of Yolo-v5 can be found [here](https://github.com/ultralytics/yolov5?tab=AGPL-3.0-1-ov-file#readme). * The license for the compiled assets for on-device deployment can be found [here](https://github.com/ultralytics/yolov5?tab=AGPL-3.0-1-ov-file#readme) ## References * [Source Model Implementation](https://github.com/ultralytics/yolov5) ## 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