Hugging Face's logo

qualcomm
/
FastSam-X

Image Segmentation
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
d4e8343
·
verified ·
1 Parent(s): fedf844

v0.49.1

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.49.1 for changelog.

Files changed (1) hide show
  1. README.md +35 -35
README.md CHANGED
@@ -14,7 +14,7 @@ pipeline_tag: image-segmentation
14
  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.
15
 
16
  This is based on the implementation of FastSam-X found [here](https://github.com/CASIA-IVA-Lab/FastSAM).
17
- 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).
18
 
19
  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.
20
 
@@ -27,23 +27,23 @@ Below are pre-exported model assets ready for deployment.
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
- | 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)
31
- | 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)
32
- | 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)
33
 
34
  For more device-specific assets and performance metrics, visit **[FastSam-X on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/fastsam_x)**.
35
 
36
 
37
  ### Option 2: Export with Custom Configurations
38
 
39
- 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:
40
  - Custom weights (e.g., fine-tuned checkpoints)
41
  - Custom input shapes
42
  - Target device and runtime configurations
43
 
44
  This option is ideal if you need to customize the model beyond the default configuration provided here.
45
 
46
- 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.
47
 
48
  ## Model Details
49
 
@@ -59,35 +59,35 @@ See our repository for [FastSam-X on GitHub](https://github.com/qualcomm/ai-hub-
59
  ## Performance Summary
60
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
61
  |---|---|---|---|---|---|---
62
- | FastSam-X | ONNX | float | Snapdragon® X2 Elite | 23.885 ms | 139 - 139 MB | NPU
63
- | FastSam-X | ONNX | float | Snapdragon® X Elite | 46.64 ms | 138 - 138 MB | NPU
64
- | FastSam-X | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 36.048 ms | 16 - 345 MB | NPU
65
- | FastSam-X | ONNX | float | Qualcomm® QCS8550 (Proxy) | 46.008 ms | 6 - 167 MB | NPU
66
- | FastSam-X | ONNX | float | Qualcomm® QCS9075 | 73.295 ms | 10 - 18 MB | NPU
67
- | FastSam-X | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 27.829 ms | 11 - 249 MB | NPU
68
- | FastSam-X | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 18.119 ms | 16 - 263 MB | NPU
69
- | FastSam-X | QNN_DLC | float | Snapdragon® X2 Elite | 22.92 ms | 5 - 5 MB | NPU
70
- | FastSam-X | QNN_DLC | float | Snapdragon® X Elite | 43.749 ms | 5 - 5 MB | NPU
71
- | FastSam-X | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 32.583 ms | 3 - 305 MB | NPU
72
- | FastSam-X | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 279.781 ms | 0 - 217 MB | NPU
73
- | FastSam-X | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 42.702 ms | 5 - 10 MB | NPU
74
- | FastSam-X | QNN_DLC | float | Qualcomm® SA8775P | 68.451 ms | 1 - 216 MB | NPU
75
- | FastSam-X | QNN_DLC | float | Qualcomm® QCS9075 | 70.273 ms | 5 - 15 MB | NPU
76
- | FastSam-X | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 92.539 ms | 0 - 391 MB | NPU
77
- | FastSam-X | QNN_DLC | float | Qualcomm® SA7255P | 279.781 ms | 0 - 217 MB | NPU
78
- | FastSam-X | QNN_DLC | float | Qualcomm® SA8295P | 77.495 ms | 1 - 298 MB | NPU
79
- | FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 25.239 ms | 5 - 222 MB | NPU
80
- | FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.227 ms | 5 - 228 MB | NPU
81
- | FastSam-X | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 32.622 ms | 28 - 456 MB | NPU
82
- | FastSam-X | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 279.313 ms | 4 - 264 MB | NPU
83
- | FastSam-X | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 41.844 ms | 4 - 42 MB | NPU
84
- | FastSam-X | TFLITE | float | Qualcomm® SA8775P | 67.917 ms | 4 - 264 MB | NPU
85
- | FastSam-X | TFLITE | float | Qualcomm® QCS9075 | 70.048 ms | 4 - 158 MB | NPU
86
- | FastSam-X | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 91.271 ms | 0 - 522 MB | NPU
87
- | FastSam-X | TFLITE | float | Qualcomm® SA7255P | 279.313 ms | 4 - 264 MB | NPU
88
- | FastSam-X | TFLITE | float | Qualcomm® SA8295P | 76.789 ms | 4 - 343 MB | NPU
89
- | FastSam-X | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 24.942 ms | 3 - 270 MB | NPU
90
- | FastSam-X | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 16.902 ms | 0 - 266 MB | NPU
91
 
92
  ## License
93
  * The license for the original implementation of FastSam-X can be found
 
14
  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.
15
 
16
  This is based on the implementation of FastSam-X found [here](https://github.com/CASIA-IVA-Lab/FastSAM).
17
+ 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/tree/v0.49.1/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).
18
 
19
  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.
20
 
 
27
 
28
  | Runtime | Precision | Chipset | SDK Versions | Download |
29
  |---|---|---|---|---|
30
+ | 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/v0.49.1/fastsam_x-onnx-float.zip)
31
+ | 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/v0.49.1/fastsam_x-qnn_dlc-float.zip)
32
+ | 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/v0.49.1/fastsam_x-tflite-float.zip)
33
 
34
  For more device-specific assets and performance metrics, visit **[FastSam-X on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/fastsam_x)**.
35
 
36
 
37
  ### Option 2: Export with Custom Configurations
38
 
39
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/fastsam_x) Python library to compile and export the model with your own:
40
  - Custom weights (e.g., fine-tuned checkpoints)
41
  - Custom input shapes
42
  - Target device and runtime configurations
43
 
44
  This option is ideal if you need to customize the model beyond the default configuration provided here.
45
 
46
+ See our repository for [FastSam-X on GitHub](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/fastsam_x) for usage instructions.
47
 
48
  ## Model Details
49
 
 
59
  ## Performance Summary
60
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
61
  |---|---|---|---|---|---|---
62
+ | FastSam-X | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 18.071 ms | 15 - 262 MB | NPU
63
+ | FastSam-X | ONNX | float | Snapdragon® X2 Elite | 23.895 ms | 139 - 139 MB | NPU
64
+ | FastSam-X | ONNX | float | Snapdragon® X Elite | 46.677 ms | 138 - 138 MB | NPU
65
+ | FastSam-X | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 36.377 ms | 1 - 329 MB | NPU
66
+ | FastSam-X | ONNX | float | Qualcomm® QCS8550 (Proxy) | 47.205 ms | 0 - 158 MB | NPU
67
+ | FastSam-X | ONNX | float | Qualcomm® QCS9075 | 73.836 ms | 11 - 19 MB | NPU
68
+ | FastSam-X | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 27.075 ms | 10 - 252 MB | NPU
69
+ | FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.3 ms | 5 - 229 MB | NPU
70
+ | FastSam-X | QNN_DLC | float | Snapdragon® X2 Elite | 22.934 ms | 5 - 5 MB | NPU
71
+ | FastSam-X | QNN_DLC | float | Snapdragon® X Elite | 43.809 ms | 5 - 5 MB | NPU
72
+ | FastSam-X | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 32.685 ms | 0 - 305 MB | NPU
73
+ | FastSam-X | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 279.736 ms | 1 - 218 MB | NPU
74
+ | FastSam-X | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 42.794 ms | 5 - 7 MB | NPU
75
+ | FastSam-X | QNN_DLC | float | Qualcomm® SA8775P | 322.821 ms | 0 - 215 MB | NPU
76
+ | FastSam-X | QNN_DLC | float | Qualcomm® QCS9075 | 70.378 ms | 5 - 15 MB | NPU
77
+ | FastSam-X | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 92.32 ms | 4 - 395 MB | NPU
78
+ | FastSam-X | QNN_DLC | float | Qualcomm® SA7255P | 279.736 ms | 1 - 218 MB | NPU
79
+ | FastSam-X | QNN_DLC | float | Qualcomm® SA8295P | 77.491 ms | 0 - 297 MB | NPU
80
+ | FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 25.319 ms | 0 - 220 MB | NPU
81
+ | FastSam-X | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.014 ms | 4 - 271 MB | NPU
82
+ | FastSam-X | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 32.502 ms | 4 - 436 MB | NPU
83
+ | FastSam-X | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 279.303 ms | 4 - 265 MB | NPU
84
+ | FastSam-X | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 43.191 ms | 4 - 7 MB | NPU
85
+ | FastSam-X | TFLITE | float | Qualcomm® SA8775P | 67.91 ms | 4 - 264 MB | NPU
86
+ | FastSam-X | TFLITE | float | Qualcomm® QCS9075 | 70.016 ms | 4 - 158 MB | NPU
87
+ | FastSam-X | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 92.338 ms | 5 - 528 MB | NPU
88
+ | FastSam-X | TFLITE | float | Qualcomm® SA7255P | 279.303 ms | 4 - 265 MB | NPU
89
+ | FastSam-X | TFLITE | float | Qualcomm® SA8295P | 76.853 ms | 0 - 339 MB | NPU
90
+ | FastSam-X | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 25.064 ms | 4 - 271 MB | NPU
91
 
92
  ## License
93
  * The license for the original implementation of FastSam-X can be found