| | --- |
| | library_name: pytorch |
| | license: other |
| | tags: |
| | - bu_auto |
| | - android |
| | pipeline_tag: other |
| |
|
| | --- |
| | |
| |  |
| |
|
| | # StateTransformer: Optimized for Qualcomm Devices |
| |
|
| | StateTransformer is a transformer-based model designed for trajectory prediction in self-driving scenarios. It integrates rasterized map data, agent context, and temporal dynamics to generate accurate future trajectories. |
| |
|
| | 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/main/qai_hub_models/models/statetransformer) 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 | |
| | |---|---|---|---|---| |
| | | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/statetransformer/releases/v0.48.0/statetransformer-onnx-float.zip) |
| | | TFLITE | float | Universal | TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/statetransformer/releases/v0.48.0/statetransformer-tflite-float.zip) |
| |
|
| | For more device-specific assets and performance metrics, visit **[StateTransformer on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/statetransformer)**. |
| |
|
| |
|
| | ### Option 2: Export with Custom Configurations |
| |
|
| | Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/statetransformer) 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 [StateTransformer on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/statetransformer) for usage instructions. |
| |
|
| | ## Model Details |
| |
|
| | **Model Type:** Model_use_case.driver_assistance |
| | |
| | **Model Stats:** |
| | - Model checkpoint: pretrained-mixtral-small |
| | - Input resolution: 1x224x224x58, 1x224x224x58, 1x4x7 |
| | - Number of parameters: 90.7M |
| | - Model size (float): 348 MB |
| | |
| | ## Performance Summary |
| | | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
| | |---|---|---|---|---|---|--- |
| | | StateTransformer | ONNX | float | Snapdragon® X2 Elite | 825.712 ms | 205 - 205 MB | NPU |
| | | StateTransformer | ONNX | float | Snapdragon® X Elite | 1335.801 ms | 184 - 184 MB | NPU |
| | | StateTransformer | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 593.726 ms | 93 - 2120 MB | NPU |
| | | StateTransformer | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 519.387 ms | 222 - 240 MB | CPU |
| | | StateTransformer | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 1003.679 ms | 226 - 242 MB | CPU |
| | | StateTransformer | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 566.153 ms | 163 - 236 MB | CPU |
| | | StateTransformer | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 773.28 ms | 216 - 238 MB | CPU |
| | | StateTransformer | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 400.564 ms | 202 - 224 MB | CPU |
| | | StateTransformer | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 351.862 ms | 226 - 247 MB | CPU |
| | |
| | ## License |
| | * The license for the original implementation of StateTransformer can be found |
| | [here](https://github.com/Tsinghua-MARS-Lab/StateTransformer/blob/main/setup.py). |
| | |
| | |
| | |
| | ## 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). |
| | |
