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 1.24.3 | Download |
| QNN_DLC | float | Universal | QAIRT 2.45 | Download |
| TFLITE | float | Universal | QAIRT 2.45 | 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 | 18.984 ms | 15 - 263 MB | NPU |
| FastSam-X | ONNX | float | Snapdragon® 8 Elite Mobile | 27.537 ms | 12 - 251 MB | NPU |
| FastSam-X | ONNX | float | Snapdragon® X2 Elite | 24.092 ms | 140 - 140 MB | NPU |
| FastSam-X | ONNX | float | Snapdragon® X Elite | 46.412 ms | 139 - 139 MB | NPU |
| FastSam-X | ONNX | float | Snapdragon® X Elite | 46.412 ms | 139 - 139 MB | NPU |
| FastSam-X | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 35.447 ms | 16 - 337 MB | NPU |
| FastSam-X | ONNX | float | Qualcomm® QCS8550 (Proxy) | 46.057 ms | 0 - 163 MB | NPU |
| FastSam-X | ONNX | float | Qualcomm® QCS9075 | 74.081 ms | 12 - 19 MB | NPU |
| FastSam-X | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 27.537 ms | 12 - 251 MB | NPU |
| FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.604 ms | 5 - 236 MB | NPU |
| FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 25.375 ms | 5 - 225 MB | NPU |
| FastSam-X | QNN_DLC | float | Snapdragon® X2 Elite | 23.211 ms | 5 - 5 MB | NPU |
| FastSam-X | QNN_DLC | float | Snapdragon® X Elite | 43.962 ms | 5 - 5 MB | NPU |
| FastSam-X | QNN_DLC | float | Snapdragon® X Elite | 43.962 ms | 5 - 5 MB | NPU |
| FastSam-X | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 32.823 ms | 5 - 304 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 279.816 ms | 1 - 216 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 42.669 ms | 5 - 7 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® SA8775P | 68.478 ms | 1 - 214 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® SA8775P | 68.478 ms | 1 - 214 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® SA8775P | 68.478 ms | 1 - 214 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® QCS9075 | 70.888 ms | 5 - 15 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 91.933 ms | 4 - 387 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® SA7255P | 279.816 ms | 1 - 216 MB | NPU |
| FastSam-X | QNN_DLC | float | Qualcomm® SA8295P | 77.724 ms | 0 - 298 MB | NPU |
| FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 25.375 ms | 5 - 225 MB | NPU |
| FastSam-X | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.085 ms | 4 - 263 MB | NPU |
| FastSam-X | TFLITE | float | Snapdragon® 8 Elite Mobile | 25.444 ms | 0 - 247 MB | NPU |
| FastSam-X | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 32.395 ms | 3 - 418 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 279.323 ms | 4 - 256 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 42.249 ms | 4 - 41 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® SA8775P | 67.969 ms | 4 - 257 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® SA8775P | 67.969 ms | 4 - 257 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® SA8775P | 67.969 ms | 4 - 257 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® QCS9075 | 69.977 ms | 3 - 156 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 90.337 ms | 0 - 501 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® SA7255P | 279.323 ms | 4 - 256 MB | NPU |
| FastSam-X | TFLITE | float | Qualcomm® SA8295P | 77.162 ms | 4 - 336 MB | NPU |
| FastSam-X | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 25.444 ms | 0 - 247 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.