--- library_name: pytorch license: other tags: - android pipeline_tag: image-segmentation --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/web-assets/model_demo.png) # FastSam-X: Optimized for Qualcomm Devices The Fast Segment Anything Model (FastSAM) is a novel, real-time CNN-based solution for the Segment Anything task. This task is designed to segment any object within an image based on various possible user interaction prompts. The model performs competitively despite significantly reduced computation, making it a practical choice for a variety of vision tasks. This is based on the implementation of FastSam-X found [here](https://github.com/CASIA-IVA-Lab/FastSAM). 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/fastsam_x) 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/fastsam_x/releases/v0.48.0/fastsam_x-onnx-float.zip) | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.48.0/fastsam_x-qnn_dlc-float.zip) | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.48.0/fastsam_x-tflite-float.zip) For more device-specific assets and performance metrics, visit **[FastSam-X on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/fastsam_x)**. ### 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/fastsam_x) 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 [FastSam-X on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/fastsam_x) for usage instructions. ## Model Details **Model Type:** Model_use_case.semantic_segmentation **Model Stats:** - Model checkpoint: fastsam-x.pt - Inference latency: RealTime - Input resolution: 640x640 - Number of parameters: 72.2M - Model size (float): 276 MB ## Performance Summary | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |---|---|---|---|---|---|--- | FastSam-X | ONNX | float | Snapdragon® X2 Elite | 23.885 ms | 139 - 139 MB | NPU | FastSam-X | ONNX | float | Snapdragon® X Elite | 46.64 ms | 138 - 138 MB | NPU | FastSam-X | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 36.048 ms | 16 - 345 MB | NPU | FastSam-X | ONNX | float | Qualcomm® QCS8550 (Proxy) | 46.008 ms | 6 - 167 MB | NPU | FastSam-X | ONNX | float | Qualcomm® QCS9075 | 73.295 ms | 10 - 18 MB | NPU | FastSam-X | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 27.829 ms | 11 - 249 MB | NPU | FastSam-X | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 18.119 ms | 16 - 263 MB | NPU | FastSam-X | QNN_DLC | float | Snapdragon® X2 Elite | 22.92 ms | 5 - 5 MB | NPU | FastSam-X | QNN_DLC | float | Snapdragon® X Elite | 43.749 ms | 5 - 5 MB | NPU | FastSam-X | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 32.583 ms | 3 - 305 MB | NPU | FastSam-X | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 279.781 ms | 0 - 217 MB | NPU | FastSam-X | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 42.702 ms | 5 - 10 MB | NPU | FastSam-X | QNN_DLC | float | Qualcomm® SA8775P | 68.451 ms | 1 - 216 MB | NPU | FastSam-X | QNN_DLC | float | Qualcomm® QCS9075 | 70.273 ms | 5 - 15 MB | NPU | FastSam-X | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 92.539 ms | 0 - 391 MB | NPU | FastSam-X | QNN_DLC | float | Qualcomm® SA7255P | 279.781 ms | 0 - 217 MB | NPU | FastSam-X | QNN_DLC | float | Qualcomm® SA8295P | 77.495 ms | 1 - 298 MB | NPU | FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 25.239 ms | 5 - 222 MB | NPU | FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.227 ms | 5 - 228 MB | NPU | FastSam-X | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 32.622 ms | 28 - 456 MB | NPU | FastSam-X | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 279.313 ms | 4 - 264 MB | NPU | FastSam-X | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 41.844 ms | 4 - 42 MB | NPU | FastSam-X | TFLITE | float | Qualcomm® SA8775P | 67.917 ms | 4 - 264 MB | NPU | FastSam-X | TFLITE | float | Qualcomm® QCS9075 | 70.048 ms | 4 - 158 MB | NPU | FastSam-X | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 91.271 ms | 0 - 522 MB | NPU | FastSam-X | TFLITE | float | Qualcomm® SA7255P | 279.313 ms | 4 - 264 MB | NPU | FastSam-X | TFLITE | float | Qualcomm® SA8295P | 76.789 ms | 4 - 343 MB | NPU | FastSam-X | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 24.942 ms | 3 - 270 MB | NPU | FastSam-X | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 16.902 ms | 0 - 266 MB | NPU ## License * The license for the original implementation of FastSam-X can be found [here](https://github.com/CASIA-IVA-Lab/FastSAM/blob/main/LICENSE). ## References * [Fast Segment Anything](https://arxiv.org/abs/2306.12156) * [Source Model Implementation](https://github.com/CASIA-IVA-Lab/FastSAM) ## 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).