Hugging Peers

DETR-ResNet101-DC5

☆ Save
by qualcomm object-detection pytorch apache-2.0
685 downloads 1 likes on Hugging Face updated

Model card

DETR-ResNet101-DC5: Optimized for Qualcomm Devices

DETR is a machine learning model that can detect objects (trained on COCO dataset).

This is based on the implementation of DETR-ResNet101-DC5 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

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime Precision Chipset SDK Versions Download
ONNX float Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit DETR-ResNet101-DC5 on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

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

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for DETR-ResNet101-DC5 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

  • Input resolution: 480x480
  • Model checkpoint: ResNet101-DC5
  • Model size (float): 232 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
DETR-ResNet101-DC5 ONNX float Snapdragon® X2 Elite 23.625 ms 5 - 5 MB NPU
DETR-ResNet101-DC5 ONNX float Snapdragon® X Elite 51.34 ms 115 - 115 MB NPU
DETR-ResNet101-DC5 ONNX float Snapdragon® 8 Gen 3 Mobile 36.41 ms 5 - 572 MB NPU
DETR-ResNet101-DC5 ONNX float Snapdragon® 8 Gen 1 Mobile 84.556 ms 1 - 476 MB NPU
DETR-ResNet101-DC5 ONNX float Qualcomm® Dragonwing™ IQ-8275 72.506 ms 5 - 13 MB NPU
DETR-ResNet101-DC5 ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 49.717 ms 0 - 127 MB NPU
DETR-ResNet101-DC5 ONNX float Qualcomm® QCS8450 84.556 ms 1 - 476 MB NPU
DETR-ResNet101-DC5 ONNX float Qualcomm® Dragonwing™ IQ-9075 68.977 ms 5 - 12 MB NPU
DETR-ResNet101-DC5 ONNX float Qualcomm® Dragonwing™ IQ-X7181 51.34 ms 115 - 115 MB NPU
DETR-ResNet101-DC5 ONNX float Qualcomm® Dragonwing™ Q-8750 27.174 ms 3 - 436 MB NPU
DETR-ResNet101-DC5 ONNX float Snapdragon® 8 Elite Mobile 27.174 ms 3 - 436 MB NPU
DETR-ResNet101-DC5 ONNX float Snapdragon® 8 Elite Gen 5 Mobile 21.756 ms 1 - 446 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Snapdragon® X2 Elite 24.72 ms 5 - 5 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Snapdragon® X Elite 53.521 ms 5 - 5 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 37.618 ms 2 - 553 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Snapdragon® 8 Gen 1 Mobile 108.871 ms 5 - 468 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 73.503 ms 5 - 12 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 51.201 ms 5 - 7 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Qualcomm® SA8775P 69.864 ms 0 - 426 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Qualcomm® SA8650P 69.864 ms 0 - 426 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Qualcomm® SA8255P 69.864 ms 0 - 426 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Qualcomm® QCS8450 108.871 ms 5 - 468 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 69.742 ms 5 - 11 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 53.521 ms 5 - 5 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Qualcomm® Dragonwing™ Q-8750 27.982 ms 5 - 453 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Qualcomm® SA7255P 220.255 ms 1 - 426 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Qualcomm® SA8295P 86.104 ms 2 - 343 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Snapdragon® 8 Elite Mobile 27.982 ms 5 - 453 MB NPU
DETR-ResNet101-DC5 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 22.645 ms 5 - 449 MB NPU
DETR-ResNet101-DC5 TFLITE float Snapdragon® 8 Gen 3 Mobile 37.26 ms 0 - 599 MB NPU
DETR-ResNet101-DC5 TFLITE float Snapdragon® 8 Gen 1 Mobile 84.498 ms 1 - 479 MB NPU
DETR-ResNet101-DC5 TFLITE float Qualcomm® Dragonwing™ IQ-8275 73.019 ms 0 - 127 MB NPU
DETR-ResNet101-DC5 TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 50.767 ms 0 - 3 MB NPU
DETR-ResNet101-DC5 TFLITE float Qualcomm® SA8775P 69.524 ms 0 - 470 MB NPU
DETR-ResNet101-DC5 TFLITE float Qualcomm® SA8650P 69.524 ms 0 - 470 MB NPU
DETR-ResNet101-DC5 TFLITE float Qualcomm® SA8255P 69.524 ms 0 - 470 MB NPU
DETR-ResNet101-DC5 TFLITE float Qualcomm® QCS8450 84.498 ms 1 - 479 MB NPU
DETR-ResNet101-DC5 TFLITE float Qualcomm® Dragonwing™ IQ-9075 69.79 ms 0 - 126 MB NPU
DETR-ResNet101-DC5 TFLITE float Qualcomm® Dragonwing™ Q-8750 27.966 ms 0 - 480 MB NPU
DETR-ResNet101-DC5 TFLITE float Qualcomm® SA7255P 219.47 ms 1 - 472 MB NPU
DETR-ResNet101-DC5 TFLITE float Qualcomm® SA8295P 76.612 ms 0 - 358 MB NPU
DETR-ResNet101-DC5 TFLITE float Snapdragon® 8 Elite Mobile 27.966 ms 0 - 480 MB NPU
DETR-ResNet101-DC5 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 22.281 ms 0 - 493 MB NPU

License

  • The license for the original implementation of DETR-ResNet101-DC5 can be found here.

References

Community