BEVDet: Optimized for Qualcomm Devices

BEVDet is a machine learning model for generating a birds eye view represenation from the sensors(cameras) mounted on a vehicle.

This is based on the implementation of BEVDet 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	ONNX Runtime 1.24.1	Download
ONNX	w8a16_mixed_fp16	Universal	ONNX Runtime 1.24.1	Download
TFLITE	float	Universal	TFLite 2.17.0	Download

For more device-specific assets and performance metrics, visit BEVDet 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 BEVDet on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.driver_assistance

Model Stats:

• Model checkpoint: bevdet-r50.pth
• Input resolution: 1 x 6 x 3 x 256 x 704
• Number of parameters: 44M
• Model size: 171 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
BEVDet	ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	1406.545 ms	250 - 261 MB	CPU
BEVDet	ONNX	float	Snapdragon® X2 Elite	585.738 ms	732 - 732 MB	CPU
BEVDet	ONNX	float	Snapdragon® X Elite	731.623 ms	731 - 731 MB	CPU
BEVDet	ONNX	float	Snapdragon® 8 Gen 3 Mobile	2030.734 ms	217 - 227 MB	CPU
BEVDet	ONNX	float	Qualcomm® QCS8550 (Proxy)	2719.76 ms	184 - 189 MB	CPU
BEVDet	ONNX	float	Qualcomm® QCS9075	1518.07 ms	235 - 251 MB	CPU
BEVDet	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	1394.902 ms	238 - 246 MB	CPU
BEVDet	ONNX	w8a16_mixed_fp16	Snapdragon® 8 Elite Gen 5 Mobile	1903.039 ms	319 - 333 MB	CPU
BEVDet	ONNX	w8a16_mixed_fp16	Snapdragon® X2 Elite	783.304 ms	1240 - 1240 MB	CPU
BEVDet	ONNX	w8a16_mixed_fp16	Snapdragon® X Elite	973.916 ms	712 - 712 MB	CPU
BEVDet	ONNX	w8a16_mixed_fp16	Snapdragon® 8 Gen 3 Mobile	2276.386 ms	362 - 374 MB	CPU
BEVDet	ONNX	w8a16_mixed_fp16	Qualcomm® QCS8550 (Proxy)	2635.28 ms	327 - 410 MB	CPU
BEVDet	ONNX	w8a16_mixed_fp16	Qualcomm® QCS9075	1869.979 ms	423 - 430 MB	CPU
BEVDet	ONNX	w8a16_mixed_fp16	Snapdragon® 8 Elite For Galaxy Mobile	1663.062 ms	324 - 334 MB	CPU
BEVDet	TFLITE	float	Snapdragon® 8 Elite Gen 5 Mobile	1050.395 ms	88 - 100 MB	CPU
BEVDet	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	1915.137 ms	124 - 139 MB	CPU
BEVDet	TFLITE	float	Qualcomm® QCS8275 (Proxy)	3128.487 ms	128 - 138 MB	CPU
BEVDet	TFLITE	float	Qualcomm® QCS8550 (Proxy)	1963.926 ms	102 - 106 MB	CPU
BEVDet	TFLITE	float	Qualcomm® SA8775P	2517.53 ms	129 - 140 MB	CPU
BEVDet	TFLITE	float	Qualcomm® QCS9075	2401.122 ms	126 - 1473 MB	CPU
BEVDet	TFLITE	float	Qualcomm® QCS8450 (Proxy)	2380.625 ms	129 - 151 MB	CPU
BEVDet	TFLITE	float	Qualcomm® SA7255P	3128.487 ms	128 - 138 MB	CPU
BEVDet	TFLITE	float	Qualcomm® SA8295P	2017.215 ms	79 - 86 MB	CPU
BEVDet	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	1366.433 ms	127 - 143 MB	CPU

License

• The license for the original implementation of BEVDet can be found [here](https://github.com/HuangJunJie2017/BEVDet/blob/dev3.0/LICENSE https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf).

References

• BEVDet: High-Performance Multi-Camera 3D Object Detection in Bird-Eye-View
• Source Model Implementation

Community

• Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
• For questions or feedback please reach out to us.