GKT: Optimized for Qualcomm Devices

Geometry-guided Kernel Transformer 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 GKT 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
PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	QAIRT 2.45, ONNX Runtime 1.25.0	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	QAIRT 2.45, ONNX Runtime 1.25.0	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.45, ONNX Runtime 1.25.0	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 1 Mobile	QAIRT 2.45, ONNX Runtime 1.25.0	Download
PRECOMPILED_QNN_ONNX	float	Qualcomm® QCS8550 (Proxy)	QAIRT 2.45, ONNX Runtime 1.25.0	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Mobile	QAIRT 2.45, ONNX Runtime 1.25.0	Download
PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.45, ONNX Runtime 1.25.0	Download
PRECOMPILED_QNN_ONNX	float	Qualcomm® QCS9075	QAIRT 2.45, ONNX Runtime 1.25.0	Download
QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 1 Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® QCS8550 (Proxy)	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® SA8775P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® SA8295P	QAIRT 2.45	Download
QNN_CONTEXT_BINARY	float	Qualcomm® QCS9075	QAIRT 2.45	Download

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

Model Details

Model Type: Model_use_case.driver_assistance

Model Stats:

• Model checkpoint: map_segmentation_gkt_7x1_conv_setting2.ckpt
• Input resolution: 1 x 6 x 3 x 224 x 480
• Number of parameters: 1.18M
• Model size: 4.66 MB

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
GKT	PRECOMPILED_QNN_ONNX	float	Snapdragon® X2 Elite	57.734 ms	9 - 9 MB	NPU
GKT	PRECOMPILED_QNN_ONNX	float	Snapdragon® X Elite	107.025 ms	7 - 7 MB	NPU
GKT	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 3 Mobile	81.143 ms	8 - 14 MB	NPU
GKT	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Gen 1 Mobile	198.13 ms	8 - 22 MB	NPU
GKT	PRECOMPILED_QNN_ONNX	float	Qualcomm® QCS8550 (Proxy)	117.021 ms	8 - 12 MB	NPU
GKT	PRECOMPILED_QNN_ONNX	float	Qualcomm® QCS8450	198.13 ms	8 - 22 MB	NPU
GKT	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Gen 5 Mobile	58.48 ms	1 - 9 MB	NPU
GKT	PRECOMPILED_QNN_ONNX	float	Qualcomm® QCS9075	110.005 ms	7 - 10 MB	NPU
GKT	PRECOMPILED_QNN_ONNX	float	Snapdragon® 8 Elite Mobile	71.236 ms	1 - 8 MB	NPU
GKT	PRECOMPILED_QNN_ONNX	float	Qualcomm® QCS8750	71.236 ms	1 - 8 MB	NPU
GKT	PRECOMPILED_QNN_ONNX	float	Qualcomm® QCS7181	107.025 ms	7 - 7 MB	NPU
GKT	QNN_CONTEXT_BINARY	float	Snapdragon® X2 Elite	57.797 ms	7 - 7 MB	NPU
GKT	QNN_CONTEXT_BINARY	float	Snapdragon® X Elite	107.024 ms	7 - 7 MB	NPU
GKT	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 3 Mobile	82.091 ms	8 - 15 MB	NPU
GKT	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Gen 1 Mobile	202.253 ms	6 - 16 MB	NPU
GKT	QNN_CONTEXT_BINARY	float	Qualcomm® QCS8275	189.362 ms	0 - 10 MB	NPU
GKT	QNN_CONTEXT_BINARY	float	Qualcomm® QCS8550 (Proxy)	116.843 ms	8 - 9 MB	NPU
GKT	QNN_CONTEXT_BINARY	float	Qualcomm® QCS8450	202.253 ms	6 - 16 MB	NPU
GKT	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Gen 5 Mobile	58.625 ms	7 - 16 MB	NPU
GKT	QNN_CONTEXT_BINARY	float	Qualcomm® SA7255P	189.362 ms	0 - 10 MB	NPU
GKT	QNN_CONTEXT_BINARY	float	Qualcomm® QCS9075	110.18 ms	7 - 17 MB	NPU
GKT	QNN_CONTEXT_BINARY	float	Snapdragon® 8 Elite Mobile	71.321 ms	7 - 20 MB	NPU
GKT	QNN_CONTEXT_BINARY	float	Qualcomm® SA8295P	140.797 ms	0 - 6 MB	NPU
GKT	QNN_CONTEXT_BINARY	float	Qualcomm® QCS8750	71.321 ms	7 - 20 MB	NPU
GKT	QNN_CONTEXT_BINARY	float	Qualcomm® QCS7181	107.024 ms	7 - 7 MB	NPU

License

• The license for the original implementation of GKT can be found here.

References

• Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer
• 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.