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® X Elite 11.584 ms 8 - 8 MB NPU
Yolo-v7 ONNX float Snapdragon® 8 Gen 3 Mobile 8.277 ms 6 - 192 MB NPU
Yolo-v7 ONNX float Qualcomm® QCS8550 (Proxy) 11.527 ms 0 - 11 MB NPU
Yolo-v7 ONNX float Qualcomm® QCS9075 11.248 ms 5 - 7 MB NPU
Yolo-v7 ONNX float Snapdragon® 8 Elite For Galaxy Mobile 5.034 ms 3 - 168 MB NPU
Yolo-v7 ONNX float Snapdragon® 8 Elite Gen 5 Mobile 4.233 ms 6 - 181 MB NPU
Yolo-v7 ONNX float Snapdragon® X2 Elite 4.044 ms 8 - 8 MB NPU
Yolo-v7 ONNX w8a16 Snapdragon® X Elite 5.49 ms 4 - 4 MB NPU
Yolo-v7 ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 3.298 ms 3 - 320 MB NPU
Yolo-v7 ONNX w8a16 Qualcomm® QCS6490 435.331 ms 84 - 87 MB CPU
Yolo-v7 ONNX w8a16 Qualcomm® QCS8550 (Proxy) 5.005 ms 0 - 8 MB NPU
Yolo-v7 ONNX w8a16 Qualcomm® QCS9075 6.545 ms 2 - 5 MB NPU
Yolo-v7 ONNX w8a16 Qualcomm® QCM6690 215.633 ms 101 - 109 MB CPU
Yolo-v7 ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.489 ms 0 - 285 MB NPU
Yolo-v7 ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 191.34 ms 89 - 98 MB CPU
Yolo-v7 ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.032 ms 0 - 282 MB NPU
Yolo-v7 ONNX w8a16 Snapdragon® X2 Elite 2.262 ms 5 - 5 MB NPU
Yolo-v7 ONNX w8a8 Snapdragon® X Elite 2.75 ms 5 - 5 MB NPU
Yolo-v7 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 1.596 ms 0 - 95 MB NPU
Yolo-v7 ONNX w8a8 Qualcomm® QCS6490 72.815 ms 40 - 47 MB CPU
Yolo-v7 ONNX w8a8 Qualcomm® QCS8550 (Proxy) 2.459 ms 0 - 16 MB NPU
Yolo-v7 ONNX w8a8 Qualcomm® QCS9075 3.046 ms 1 - 4 MB NPU
Yolo-v7 ONNX w8a8 Qualcomm® QCM6690 55.763 ms 41 - 50 MB CPU
Yolo-v7 ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.241 ms 0 - 69 MB NPU
Yolo-v7 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 45.628 ms 40 - 50 MB CPU
Yolo-v7 ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 1.011 ms 0 - 67 MB NPU
Yolo-v7 ONNX w8a8 Snapdragon® X2 Elite 1.104 ms 5 - 5 MB NPU
Yolo-v7 QNN_DLC float Snapdragon® X Elite 7.585 ms 5 - 5 MB NPU
Yolo-v7 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 5.534 ms 5 - 183 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® QCS8275 (Proxy) 19.931 ms 1 - 153 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® QCS8550 (Proxy) 7.326 ms 5 - 98 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® SA8775P 9.012 ms 0 - 157 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® QCS9075 9.152 ms 7 - 13 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® QCS8450 (Proxy) 11.282 ms 5 - 184 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® SA7255P 19.931 ms 1 - 153 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® SA8295P 10.413 ms 0 - 151 MB NPU
Yolo-v7 QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 4.337 ms 0 - 156 MB NPU
Yolo-v7 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 3.815 ms 5 - 166 MB NPU
Yolo-v7 QNN_DLC float Snapdragon® X2 Elite 4.027 ms 5 - 5 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® X Elite 4.415 ms 2 - 2 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 2.884 ms 2 - 301 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCS6490 11.342 ms 2 - 7 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 9.387 ms 0 - 270 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 4.014 ms 2 - 5 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® SA8775P 4.677 ms 1 - 272 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCS9075 4.86 ms 1 - 5 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCM6690 28.701 ms 2 - 228 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 6.969 ms 2 - 310 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® SA7255P 9.387 ms 0 - 270 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® SA8295P 5.935 ms 0 - 274 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.148 ms 2 - 274 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 5.032 ms 2 - 218 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.722 ms 2 - 280 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® X2 Elite 2.347 ms 2 - 2 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® X Elite 2.442 ms 1 - 1 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 1.395 ms 1 - 73 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCS6490 6.032 ms 3 - 6 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 4.928 ms 1 - 54 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 2.189 ms 1 - 3 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® SA8775P 2.763 ms 1 - 53 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCS9075 2.498 ms 0 - 3 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCM6690 13.987 ms 1 - 170 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 2.841 ms 1 - 72 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® SA7255P 4.928 ms 1 - 54 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® SA8295P 3.468 ms 0 - 50 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.094 ms 1 - 51 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 2.69 ms 1 - 263 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.865 ms 1 - 54 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® X2 Elite 1.141 ms 1 - 1 MB NPU
Yolo-v7 TFLITE float Snapdragon® 8 Gen 3 Mobile 5.529 ms 0 - 190 MB NPU
Yolo-v7 TFLITE float Qualcomm® QCS8275 (Proxy) 20.212 ms 1 - 157 MB NPU
Yolo-v7 TFLITE float Qualcomm® QCS8550 (Proxy) 7.533 ms 1 - 2 MB NPU
Yolo-v7 TFLITE float Qualcomm® SA8775P 9.203 ms 1 - 160 MB NPU
Yolo-v7 TFLITE float Qualcomm® QCS9075 9.26 ms 0 - 19 MB NPU
Yolo-v7 TFLITE float Qualcomm® QCS8450 (Proxy) 11.37 ms 1 - 192 MB NPU
Yolo-v7 TFLITE float Qualcomm® SA7255P 20.212 ms 1 - 157 MB NPU
Yolo-v7 TFLITE float Qualcomm® SA8295P 10.432 ms 1 - 159 MB NPU
Yolo-v7 TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 4.333 ms 1 - 165 MB NPU
Yolo-v7 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 3.824 ms 0 - 167 MB NPU
Yolo-v7 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 1.429 ms 0 - 64 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCS6490 6.02 ms 0 - 10 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 4.702 ms 0 - 46 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 2.205 ms 0 - 2 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® SA8775P 2.668 ms 0 - 60 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCS9075 2.456 ms 0 - 9 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCM6690 14.496 ms 0 - 158 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 3.062 ms 0 - 64 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® SA7255P 4.702 ms 0 - 46 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® SA8295P 3.66 ms 0 - 42 MB NPU
Yolo-v7 TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.243 ms 0 - 65 MB NPU
Yolo-v7 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 2.685 ms 0 - 175 MB NPU
Yolo-v7 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 1.018 ms 0 - 83 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