Fast Segment Anything
Paper • 2306.12156 • Published • 36
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. 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 | QAIRT 2.42, ONNX Runtime 1.24.1 | Download |
| QNN_DLC | float | Universal | QAIRT 2.43 | Download |
| TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | Download |
For more device-specific assets and performance metrics, visit FastSam-X 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 FastSam-X on GitHub 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® 8 Elite Gen 5 Mobile | 18.071 ms | 15 - 262 MB | NPU |
| FastSam-X | ONNX | float | Snapdragon® X2 Elite | 23.895 ms | 139 - 139 MB | NPU |
| FastSam-X | ONNX | float | Snapdragon® X Elite | 46.677 ms | 138 - 138 MB | NPU |
| FastSam-X | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 36.377 ms | 1 - 329 MB | NPU |
| FastSam-X | ONNX | float | Qualcomm® QCS8550 (Proxy) | 47.205 ms | 0 - 158 MB | NPU |
| FastSam-X | ONNX | float | Qualcomm® QCS9075 | 73.836 ms | 11 - 19 MB | NPU |
| FastSam-X | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 27.075 ms | 10 - 252 MB | NPU |
| FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.3 ms | 5 - 229 MB | NPU |
| FastSam-X | QNN_DLC | float | Snapdragon® X2 Elite | 22.934 ms | 5 - 5 MB | NPU |
| FastSam-X | QNN_DLC | float | Snapdragon® X Elite | 43.809 ms | 5 - 5 MB | NPU |
| FastSam-X | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 32.685 ms | 0 - 305 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 279.736 ms | 1 - 218 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 42.794 ms | 5 - 7 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® SA8775P | 322.821 ms | 0 - 215 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® QCS9075 | 70.378 ms | 5 - 15 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 92.32 ms | 4 - 395 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® SA7255P | 279.736 ms | 1 - 218 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® SA8295P | 77.491 ms | 0 - 297 MB | NPU |
| FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 25.319 ms | 0 - 220 MB | NPU |
| FastSam-X | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.014 ms | 4 - 271 MB | NPU |
| FastSam-X | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 32.502 ms | 4 - 436 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 279.303 ms | 4 - 265 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 43.191 ms | 4 - 7 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® SA8775P | 67.91 ms | 4 - 264 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® QCS9075 | 70.016 ms | 4 - 158 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 92.338 ms | 5 - 528 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® SA7255P | 279.303 ms | 4 - 265 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® SA8295P | 76.853 ms | 0 - 339 MB | NPU |
| FastSam-X | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 25.064 ms | 4 - 271 MB | NPU |
License
- The license for the original implementation of FastSam-X can be found here.
References
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.