Fast Segment Anything
Paper • 2306.12156 • Published • 36
FastSam-S: 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-S 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-S 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-S on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.semantic_segmentation
Model Stats:
- Model checkpoint: fastsam-s.pt
- Inference latency: RealTime
- Input resolution: 640x640
- Number of parameters: 11.8M
- Model size (float): 45.1 MB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| FastSam-S | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.613 ms | 0 - 213 MB | NPU |
| FastSam-S | ONNX | float | Snapdragon® 8 Elite Mobile | 4.725 ms | 11 - 217 MB | NPU |
| FastSam-S | ONNX | float | Snapdragon® X2 Elite | 4.51 ms | 21 - 21 MB | NPU |
| FastSam-S | ONNX | float | Snapdragon® X Elite | 8.751 ms | 20 - 20 MB | NPU |
| FastSam-S | ONNX | float | Snapdragon® X Elite | 8.751 ms | 20 - 20 MB | NPU |
| FastSam-S | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 6.047 ms | 16 - 251 MB | NPU |
| FastSam-S | ONNX | float | Qualcomm® QCS8550 (Proxy) | 8.215 ms | 0 - 27 MB | NPU |
| FastSam-S | ONNX | float | Qualcomm® QCS9075 | 13.653 ms | 12 - 14 MB | NPU |
| FastSam-S | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.725 ms | 11 - 217 MB | NPU |
| FastSam-S | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.131 ms | 5 - 196 MB | NPU |
| FastSam-S | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 4.477 ms | 5 - 196 MB | NPU |
| FastSam-S | QNN_DLC | float | Snapdragon® X2 Elite | 4.594 ms | 5 - 5 MB | NPU |
| FastSam-S | QNN_DLC | float | Snapdragon® X Elite | 8.222 ms | 5 - 5 MB | NPU |
| FastSam-S | QNN_DLC | float | Snapdragon® X Elite | 8.222 ms | 5 - 5 MB | NPU |
| FastSam-S | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.845 ms | 5 - 218 MB | NPU |
| FastSam-S | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 39.252 ms | 1 - 187 MB | NPU |
| FastSam-S | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 7.661 ms | 5 - 12 MB | NPU |
| FastSam-S | QNN_DLC | float | Qualcomm® SA8775P | 11.589 ms | 0 - 182 MB | NPU |
| FastSam-S | QNN_DLC | float | Qualcomm® SA8775P | 11.589 ms | 0 - 182 MB | NPU |
| FastSam-S | QNN_DLC | float | Qualcomm® SA8775P | 11.589 ms | 0 - 182 MB | NPU |
| FastSam-S | QNN_DLC | float | Qualcomm® QCS9075 | 10.915 ms | 5 - 15 MB | NPU |
| FastSam-S | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 16.089 ms | 4 - 213 MB | NPU |
| FastSam-S | QNN_DLC | float | Qualcomm® SA7255P | 39.252 ms | 1 - 187 MB | NPU |
| FastSam-S | QNN_DLC | float | Qualcomm® SA8295P | 13.773 ms | 0 - 178 MB | NPU |
| FastSam-S | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.477 ms | 5 - 196 MB | NPU |
| FastSam-S | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.017 ms | 0 - 98 MB | NPU |
| FastSam-S | TFLITE | float | Snapdragon® 8 Elite Mobile | 3.938 ms | 3 - 102 MB | NPU |
| FastSam-S | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.161 ms | 0 - 116 MB | NPU |
| FastSam-S | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 37.811 ms | 4 - 85 MB | NPU |
| FastSam-S | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 6.965 ms | 4 - 7 MB | NPU |
| FastSam-S | TFLITE | float | Qualcomm® SA8775P | 10.745 ms | 0 - 85 MB | NPU |
| FastSam-S | TFLITE | float | Qualcomm® SA8775P | 10.745 ms | 0 - 85 MB | NPU |
| FastSam-S | TFLITE | float | Qualcomm® SA8775P | 10.745 ms | 0 - 85 MB | NPU |
| FastSam-S | TFLITE | float | Qualcomm® QCS9075 | 10.669 ms | 4 - 39 MB | NPU |
| FastSam-S | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 14.121 ms | 4 - 234 MB | NPU |
| FastSam-S | TFLITE | float | Qualcomm® SA7255P | 37.811 ms | 4 - 85 MB | NPU |
| FastSam-S | TFLITE | float | Qualcomm® SA8295P | 13.044 ms | 4 - 196 MB | NPU |
| FastSam-S | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.938 ms | 3 - 102 MB | NPU |
License
- The license for the original implementation of FastSam-S 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.