Hugging Face's logo

qualcomm
/
Yolo-R

Object Detection
PyTorch
bu_auto
real_time
android
Model card Files
xet
 Community
Yolo-R / README.md
qaihm-bot's picture
qaihm-bot
v0.55.0
5cd6069 verified
preview code
|
raw
history blame contribute delete
5.89 kB
metadata 
library_name: pytorch
license: other
tags:
  - bu_auto
  - real_time
  - android
pipeline_tag: object-detection

Yolo-R: Optimized for Qualcomm Devices

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

This is based on the implementation of Yolo-R 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-R on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

  • Model checkpoint: yolor_p6
  • Input resolution: 640x640
  • Number of parameters: 4.68M
  • Model size (float): 17.9 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Yolo-R ONNX float Snapdragon® 8 Elite Gen 5 Mobile 25.358 ms 6 - 314 MB NPU
Yolo-R ONNX float Snapdragon® X2 Elite 24.773 ms 207 - 207 MB NPU
Yolo-R ONNX float Snapdragon® 8 Gen 3 Mobile 29.356 ms 6 - 352 MB NPU
Yolo-R ONNX float Qualcomm® QCS8550 (Proxy) 37.862 ms 0 - 92 MB NPU
Yolo-R ONNX float Snapdragon® 8 Elite For Galaxy Mobile 25.289 ms 2 - 231 MB NPU
Yolo-R ONNX float Qualcomm® QCS9075 51.735 ms 5 - 50 MB NPU
Yolo-R ONNX float Qualcomm® QCS8750 25.289 ms 2 - 231 MB NPU
Yolo-R ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 18.087 ms 3 - 454 MB NPU
Yolo-R ONNX w8a16 Snapdragon® X2 Elite 18.509 ms 210 - 210 MB NPU
Yolo-R ONNX w8a16 Snapdragon® X Elite 30.372 ms 153 - 153 MB NPU
Yolo-R ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 20.937 ms 3 - 501 MB NPU
Yolo-R ONNX w8a16 Qualcomm® QCS6490 2274.876 ms 130 - 136 MB CPU
Yolo-R ONNX w8a16 Qualcomm® QCS8550 (Proxy) 29.093 ms 0 - 62 MB NPU
Yolo-R ONNX w8a16 Qualcomm® QCM6690 1171.766 ms 68 - 81 MB CPU
Yolo-R ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 1122.444 ms 123 - 136 MB CPU
Yolo-R ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 17.392 ms 1 - 368 MB NPU
Yolo-R ONNX w8a16 Qualcomm® QCS9075 29.118 ms 2 - 47 MB NPU
Yolo-R ONNX w8a16 Qualcomm® QCS7790 1122.444 ms 123 - 136 MB CPU
Yolo-R ONNX w8a16 Qualcomm® QCS8750 17.392 ms 1 - 368 MB NPU
Yolo-R ONNX w8a16 Qualcomm® QCS7181 30.372 ms 153 - 153 MB NPU
Yolo-R QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 7.704 ms 2 - 306 MB NPU
Yolo-R QNN_DLC w8a16 Snapdragon® X2 Elite 8.714 ms 2 - 2 MB NPU
Yolo-R QNN_DLC w8a16 Snapdragon® X Elite 20.344 ms 2 - 2 MB NPU
Yolo-R QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 13.111 ms 2 - 358 MB NPU
Yolo-R QNN_DLC w8a16 Qualcomm® QCS6490 75.364 ms 3 - 7 MB NPU
Yolo-R QNN_DLC w8a16 Qualcomm® QCS8275 39.54 ms 0 - 292 MB NPU
Yolo-R QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 19.503 ms 2 - 5 MB NPU
Yolo-R QNN_DLC w8a16 Qualcomm® SA8775P 19.626 ms 2 - 292 MB NPU
Yolo-R QNN_DLC w8a16 Qualcomm® SA8650P 19.626 ms 2 - 292 MB NPU
Yolo-R QNN_DLC w8a16 Qualcomm® SA8255P 19.626 ms 2 - 292 MB NPU
Yolo-R QNN_DLC w8a16 Qualcomm® QCM6690 210.094 ms 2 - 398 MB NPU
Yolo-R QNN_DLC w8a16 Qualcomm® SA7255P 39.54 ms 0 - 292 MB NPU
Yolo-R QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 25.896 ms 2 - 311 MB NPU
Yolo-R QNN_DLC w8a16 Qualcomm® SA8295P 25.065 ms 0 - 294 MB NPU
Yolo-R QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 9.831 ms 2 - 305 MB NPU
Yolo-R QNN_DLC w8a16 Qualcomm® QCS9075 20.36 ms 1 - 5 MB NPU
Yolo-R QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 28.206 ms 2 - 358 MB NPU
Yolo-R QNN_DLC w8a16 Qualcomm® QCS7790 25.896 ms 2 - 311 MB NPU
Yolo-R QNN_DLC w8a16 Qualcomm® QCS8750 9.831 ms 2 - 305 MB NPU
Yolo-R QNN_DLC w8a16 Qualcomm® QCS7181 20.344 ms 2 - 2 MB NPU

License

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

References

Community