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 11.088 ms 8 - 8 MB NPU
Yolo-v7 ONNX float Snapdragon® 8 Gen 3 Mobile 8.128 ms 6 - 142 MB NPU
Yolo-v7 ONNX float Qualcomm® QCS8550 (Proxy) 11.403 ms 0 - 12 MB NPU
Yolo-v7 ONNX float Qualcomm® QCS9075 11.665 ms 5 - 7 MB NPU
Yolo-v7 ONNX float Snapdragon® 8 Elite For Galaxy Mobile 4.697 ms 1 - 113 MB NPU
Yolo-v7 ONNX float Snapdragon® 8 Elite Gen 5 Mobile 4.376 ms 5 - 127 MB NPU
Yolo-v7 ONNX w8a16 Snapdragon® X Elite 5.449 ms 4 - 4 MB NPU
Yolo-v7 ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 3.584 ms 0 - 307 MB NPU
Yolo-v7 ONNX w8a16 Qualcomm® QCS6490 425.947 ms 85 - 90 MB CPU
Yolo-v7 ONNX w8a16 Qualcomm® QCS8550 (Proxy) 5.19 ms 0 - 11 MB NPU
Yolo-v7 ONNX w8a16 Qualcomm® QCS9075 6.652 ms 2 - 5 MB NPU
Yolo-v7 ONNX w8a16 Qualcomm® QCM6690 215.3 ms 83 - 92 MB CPU
Yolo-v7 ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.683 ms 0 - 281 MB NPU
Yolo-v7 ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 188.489 ms 83 - 91 MB CPU
Yolo-v7 ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.422 ms 0 - 284 MB NPU
Yolo-v7 ONNX w8a8 Snapdragon® X Elite 2.743 ms 5 - 5 MB NPU
Yolo-v7 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 1.779 ms 0 - 158 MB NPU
Yolo-v7 ONNX w8a8 Qualcomm® QCS6490 80.342 ms 39 - 47 MB CPU
Yolo-v7 ONNX w8a8 Qualcomm® QCS8550 (Proxy) 2.767 ms 0 - 46 MB NPU
Yolo-v7 ONNX w8a8 Qualcomm® QCS9075 3.581 ms 1 - 4 MB NPU
Yolo-v7 ONNX w8a8 Qualcomm® QCM6690 54.002 ms 39 - 49 MB CPU
Yolo-v7 ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.414 ms 0 - 138 MB NPU
Yolo-v7 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 42.962 ms 40 - 49 MB CPU
Yolo-v7 ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 1.246 ms 0 - 132 MB NPU
Yolo-v7 QNN_DLC float Snapdragon® X Elite 7.55 ms 5 - 5 MB NPU
Yolo-v7 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 5.474 ms 0 - 179 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® QCS8275 (Proxy) 19.823 ms 0 - 153 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® QCS8550 (Proxy) 7.319 ms 5 - 96 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® SA8775P 8.931 ms 1 - 158 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® QCS9075 9.147 ms 7 - 13 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® QCS8450 (Proxy) 11.338 ms 5 - 183 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® SA7255P 19.823 ms 0 - 153 MB NPU
Yolo-v7 QNN_DLC float Qualcomm® SA8295P 10.454 ms 0 - 151 MB NPU
Yolo-v7 QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 4.337 ms 0 - 158 MB NPU
Yolo-v7 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 3.807 ms 5 - 162 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® X Elite 4.5 ms 2 - 2 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 2.887 ms 2 - 300 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCS6490 11.637 ms 1 - 6 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 9.503 ms 1 - 270 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 4.11 ms 2 - 5 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® SA8775P 4.72 ms 0 - 272 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCS9075 4.809 ms 2 - 6 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCM6690 32.711 ms 2 - 228 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 6.912 ms 2 - 307 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® SA7255P 9.503 ms 1 - 270 MB NPU
Yolo-v7 QNN_DLC w8a16 Qualcomm® SA8295P 5.93 ms 0 - 274 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 2.182 ms 2 - 274 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 5.026 ms 2 - 217 MB NPU
Yolo-v7 QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 1.694 ms 2 - 275 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® X Elite 2.449 ms 1 - 1 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 1.4 ms 1 - 72 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCS6490 6.165 ms 3 - 6 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 4.724 ms 1 - 53 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 2.169 ms 1 - 3 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® SA8775P 2.601 ms 1 - 55 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCS9075 2.478 ms 1 - 4 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCM6690 13.831 ms 1 - 174 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 2.827 ms 1 - 72 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® SA7255P 4.724 ms 1 - 53 MB NPU
Yolo-v7 QNN_DLC w8a8 Qualcomm® SA8295P 3.6 ms 1 - 51 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.08 ms 1 - 55 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 2.686 ms 1 - 263 MB NPU
Yolo-v7 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.863 ms 1 - 54 MB NPU
Yolo-v7 TFLITE float Snapdragon® 8 Gen 3 Mobile 5.455 ms 1 - 185 MB NPU
Yolo-v7 TFLITE float Qualcomm® QCS8275 (Proxy) 20.204 ms 1 - 157 MB NPU
Yolo-v7 TFLITE float Qualcomm® QCS8550 (Proxy) 7.551 ms 1 - 2 MB NPU
Yolo-v7 TFLITE float Qualcomm® SA8775P 9.167 ms 1 - 160 MB NPU
Yolo-v7 TFLITE float Qualcomm® QCS9075 9.243 ms 1 - 20 MB NPU
Yolo-v7 TFLITE float Qualcomm® QCS8450 (Proxy) 11.373 ms 1 - 193 MB NPU
Yolo-v7 TFLITE float Qualcomm® SA7255P 20.204 ms 1 - 157 MB NPU
Yolo-v7 TFLITE float Qualcomm® SA8295P 10.411 ms 1 - 158 MB NPU
Yolo-v7 TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 4.35 ms 1 - 166 MB NPU
Yolo-v7 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 3.807 ms 0 - 163 MB NPU
Yolo-v7 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 1.387 ms 0 - 86 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCS6490 6.147 ms 0 - 10 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 4.689 ms 0 - 66 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 2.154 ms 0 - 3 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® SA8775P 10.921 ms 0 - 65 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCS9075 2.443 ms 0 - 9 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCM6690 14.75 ms 0 - 161 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 3.006 ms 0 - 63 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® SA7255P 4.689 ms 0 - 66 MB NPU
Yolo-v7 TFLITE w8a8 Qualcomm® SA8295P 3.726 ms 0 - 43 MB NPU
Yolo-v7 TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 1.212 ms 0 - 66 MB NPU
Yolo-v7 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 2.637 ms 0 - 171 MB NPU
Yolo-v7 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.988 ms 0 - 84 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