--- library_name: pytorch license: other tags: - android pipeline_tag: other --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/web-assets/model_demo.png) # 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](https://github.com/hustvl/GKT/). This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/gkt) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary). Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen1.zip) | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip) | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip) | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip) | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip) | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip) | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-qnn_context_binary-float-qualcomm_snapdragon_8gen1.zip) | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip) | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-qnn_context_binary-float-qualcomm_sa8775p.zip) | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip) | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip) | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-qnn_context_binary-float-qualcomm_sa7255p.zip) | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-qnn_context_binary-float-qualcomm_sa8295p.zip) | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/gkt/releases/v0.57.3/gkt-qnn_context_binary-float-qualcomm_qcs9075.zip) For more device-specific assets and performance metrics, visit **[GKT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/gkt)**. ### Option 2: Export with Custom Configurations Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/gkt) 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](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/gkt) 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](https://github.com/hustvl/GKT/blob/main/LICENSE). ## References * [Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer](https://arxiv.org/abs/2206.04584) * [Source Model Implementation](https://github.com/hustvl/GKT/) ## Community * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).