--- library_name: pytorch license: gpl-3.0 tags: - real_time - android pipeline_tag: object-detection --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolov7/web-assets/model_demo.png) # 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](https://github.com/WongKinYiu/yolov7/). More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/yolov7). ### Model Details - **Model Type:** Object detection - **Model Stats:** - Model checkpoint: YoloV7 Tiny - Input resolution: 640x640 - Number of parameters: 6.39M - Model size: 24.4 MB | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model |---|---|---|---|---|---|---|---|---| | Yolo-v7 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 17.699 ms | 1 - 15 MB | FP16 | NPU | -- | | Yolo-v7 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 8.899 ms | 5 - 16 MB | FP16 | NPU | -- | | Yolo-v7 | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 13.998 ms | 2 - 43 MB | FP16 | NPU | -- | | Yolo-v7 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 12.886 ms | 0 - 39 MB | FP16 | NPU | -- | | Yolo-v7 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 5.774 ms | 5 - 25 MB | FP16 | NPU | -- | | Yolo-v7 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 10.077 ms | 4 - 61 MB | FP16 | NPU | -- | | Yolo-v7 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 10.706 ms | 1 - 31 MB | FP16 | NPU | -- | | Yolo-v7 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 7.03 ms | 5 - 49 MB | FP16 | NPU | -- | | Yolo-v7 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 8.109 ms | 7 - 53 MB | FP16 | NPU | -- | | Yolo-v7 | SA7255P ADP | SA7255P | TFLITE | 109.709 ms | 1 - 24 MB | FP16 | NPU | -- | | Yolo-v7 | SA7255P ADP | SA7255P | QNN | 98.032 ms | 0 - 10 MB | FP16 | NPU | -- | | Yolo-v7 | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 17.837 ms | 1 - 15 MB | FP16 | NPU | -- | | Yolo-v7 | SA8255 (Proxy) | SA8255P Proxy | QNN | 8.907 ms | 5 - 7 MB | FP16 | NPU | -- | | Yolo-v7 | SA8295P ADP | SA8295P | TFLITE | 22.345 ms | 1 - 30 MB | FP16 | NPU | -- | | Yolo-v7 | SA8295P ADP | SA8295P | QNN | 11.756 ms | 0 - 18 MB | FP16 | NPU | -- | | Yolo-v7 | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 17.78 ms | 1 - 12 MB | FP16 | NPU | -- | | Yolo-v7 | SA8650 (Proxy) | SA8650P Proxy | QNN | 8.8 ms | 6 - 8 MB | FP16 | NPU | -- | | Yolo-v7 | SA8775P ADP | SA8775P | TFLITE | 22.152 ms | 0 - 23 MB | FP16 | NPU | -- | | Yolo-v7 | SA8775P ADP | SA8775P | QNN | 12.76 ms | 0 - 10 MB | FP16 | NPU | -- | | Yolo-v7 | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 109.709 ms | 1 - 24 MB | FP16 | NPU | -- | | Yolo-v7 | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 98.032 ms | 0 - 10 MB | FP16 | NPU | -- | | Yolo-v7 | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 17.681 ms | 1 - 10 MB | FP16 | NPU | -- | | Yolo-v7 | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 8.724 ms | 5 - 8 MB | FP16 | NPU | -- | | Yolo-v7 | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 22.152 ms | 0 - 23 MB | FP16 | NPU | -- | | Yolo-v7 | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 12.76 ms | 0 - 10 MB | FP16 | NPU | -- | | Yolo-v7 | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 20.941 ms | 1 - 42 MB | FP16 | NPU | -- | | Yolo-v7 | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 10.764 ms | 5 - 32 MB | FP16 | NPU | -- | | Yolo-v7 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 9.406 ms | 5 - 5 MB | FP16 | NPU | -- | | Yolo-v7 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 13.818 ms | 9 - 9 MB | FP16 | NPU | -- | ## License * The license for the original implementation of Yolo-v7 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: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