Yolo-v7: Optimized for Qualcomm Devices

YoloV7 is a machine learning model that predicts bounding boxes and classes of objects in an image.

This is based on the implementation of Yolo-v7 found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

Due to licensing restrictions, we cannot distribute pre-exported model assets for this model. Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

  • Custom weights (e.g., fine-tuned checkpoints)
  • Custom input shapes
  • Target device and runtime configurations

See our repository for Yolo-v7 on GitHub for usage instructions.

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Yolo-v7 ONNX float Snapdragon® 8 Elite Gen 5 Mobile 4.233 ms 6 - 182 MB NPU
Yolo-v7 ONNX float Snapdragon® X2 Elite 4.066 ms 8 - 8 MB NPU
Yolo-v7 ONNX float Snapdragon® X Elite 11.437 ms 8 - 8 MB NPU
Yolo-v7 ONNX float Snapdragon® 8 Gen 3 Mobile 8.304 ms 6 - 191 MB NPU
Yolo-v7 ONNX float Qualcomm® QCS8550 (Proxy) 11.51 ms 0 - 11 MB NPU
Yolo-v7 ONNX float Qualcomm® QCS9075 11.205 ms 5 - 7 MB NPU
Yolo-v7 ONNX float Snapdragon® 8 Elite For Galaxy Mobile 5.036 ms 3 - 169 MB NPU
Yolo-v7 ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.791 ms 0 - 193 MB NPU
Yolo-v7 ONNX w8a16 Snapdragon® X2 Elite 2.069 ms 5 - 5 MB NPU
Yolo-v7 ONNX w8a16 Snapdragon® X Elite 4.874 ms 4 - 4 MB NPU
Yolo-v7 ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 2.854 ms 0 - 210 MB NPU
Yolo-v7 ONNX w8a16 Qualcomm® QCS6490 430.124 ms 84 - 87 MB CPU
Yolo-v7 ONNX w8a16 Qualcomm® QCS8550 (Proxy) 4.415 ms 0 - 7 MB NPU
Yolo-v7 ONNX w8a16 Qualcomm® QCS9075 6.166 ms 2 - 5 MB NPU
Yolo-v7 ONNX w8a16 Qualcomm® QCM6690 215.721 ms 83 - 91 MB CPU
Yolo-v7 ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.244 ms 0 - 188 MB NPU
Yolo-v7 ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 190.095 ms 83 - 92 MB CPU
Yolo-v7 ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.966 ms 0 - 60 MB NPU
Yolo-v7 ONNX w8a8 Snapdragon® X2 Elite 1.018 ms 5 - 5 MB NPU
Yolo-v7 ONNX w8a8 Snapdragon® X Elite 2.631 ms 5 - 5 MB NPU
Yolo-v7 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 1.521 ms 0 - 78 MB NPU
Yolo-v7 ONNX w8a8 Qualcomm® QCS6490 75.741 ms 39 - 45 MB CPU
Yolo-v7 ONNX w8a8 Qualcomm® QCS8550 (Proxy) 2.334 ms 0 - 16 MB NPU
Yolo-v7 ONNX w8a8 Qualcomm® QCS9075 2.881 ms 0 - 3 MB NPU
Yolo-v7 ONNX w8a8 Qualcomm® QCM6690 54.641 ms 39 - 48 MB CPU
Yolo-v7 ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.179 ms 0 - 52 MB NPU
Yolo-v7 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 44.216 ms 46 - 56 MB CPU
Yolo-v7 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 3.819 ms 4 - 164 MB NPU
Yolo-v7 QNN_DLC float Snapdragon® X2 Elite 3.987 ms 5 - 5 MB NPU
Yolo-v7 QNN_DLC float Snapdragon® X Elite 7.593 ms 5 - 5 MB NPU
Yolo-v7 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 5.486 ms 5 - 185 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® QCS8275 (Proxy) 19.886 ms 0 - 153 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® QCS8550 (Proxy) 7.347 ms 5 - 6 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® SA8775P 9.011 ms 1 - 157 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® QCS9075 9.147 ms 5 - 11 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® QCS8450 (Proxy) 11.395 ms 3 - 182 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® SA7255P 19.886 ms 0 - 153 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® SA8295P 10.456 ms 0 - 151 MB NPU
Yolo-v7 QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 4.331 ms 0 - 158 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.449 ms 2 - 171 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® X2 Elite 2.02 ms 2 - 2 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® X Elite 4.142 ms 2 - 2 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 2.656 ms 2 - 196 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCS6490 11.173 ms 3 - 7 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 8.898 ms 0 - 165 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 3.734 ms 2 - 4 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® SA8775P 4.419 ms 0 - 168 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCS9075 4.379 ms 1 - 5 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCM6690 33.203 ms 2 - 170 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 4.775 ms 2 - 204 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® SA7255P 8.898 ms 0 - 165 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® SA8295P 5.243 ms 0 - 170 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.038 ms 0 - 172 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 4.685 ms 2 - 169 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.795 ms 1 - 43 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® X2 Elite 1.274 ms 1 - 1 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® X Elite 2.227 ms 1 - 1 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 1.348 ms 1 - 59 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCS6490 6.005 ms 3 - 6 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 4.39 ms 1 - 41 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 1.999 ms 1 - 3 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® SA8775P 2.482 ms 1 - 43 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCS9075 2.375 ms 1 - 4 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCM6690 13.466 ms 1 - 156 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 2.771 ms 1 - 61 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® SA7255P 4.39 ms 1 - 41 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® SA8295P 3.315 ms 0 - 37 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.035 ms 1 - 39 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 2.547 ms 1 - 156 MB NPU
Yolo-v7 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 3.814 ms 0 - 167 MB NPU
Yolo-v7 TFLITE float Snapdragon® 8 Gen 3 Mobile 5.485 ms 1 - 188 MB NPU
Yolo-v7 TFLITE float Qualcomm® QCS8275 (Proxy) 79.686 ms 17 - 44 MB GPU
Yolo-v7 TFLITE float Qualcomm® QCS8550 (Proxy) 7.531 ms 1 - 3 MB NPU
Yolo-v7 TFLITE float Qualcomm® SA8775P 9.181 ms 1 - 159 MB NPU
Yolo-v7 TFLITE float Qualcomm® QCS9075 9.241 ms 0 - 19 MB NPU
Yolo-v7 TFLITE float Qualcomm® QCS8450 (Proxy) 11.362 ms 1 - 190 MB NPU
Yolo-v7 TFLITE float Qualcomm® SA7255P 79.686 ms 17 - 44 MB GPU
Yolo-v7 TFLITE float Qualcomm® SA8295P 10.501 ms 1 - 158 MB NPU
Yolo-v7 TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 4.328 ms 1 - 164 MB NPU
Yolo-v7 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 1.017 ms 0 - 86 MB NPU
Yolo-v7 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 1.387 ms 0 - 63 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCS6490 6.043 ms 0 - 10 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 4.712 ms 0 - 43 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 2.084 ms 0 - 2 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® SA8775P 2.592 ms 0 - 61 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCS9075 2.416 ms 0 - 9 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCM6690 13.833 ms 0 - 157 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 2.969 ms 0 - 64 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® SA7255P 4.712 ms 0 - 43 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® SA8295P 3.52 ms 0 - 42 MB NPU
Yolo-v7 TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.147 ms 0 - 70 MB NPU
Yolo-v7 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 2.642 ms 0 - 174 MB NPU

License

  • The license for the original implementation of Yolo-v7 can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/Yolo-v7