Hugging Face's logo

qualcomm
/
FastSam-X

Image Segmentation
PyTorch
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
ecfce5c
·
verified ·
1 Parent(s): 35ddc81

v0.58.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.58.0 for changelog.

Files changed (2) hide show
  1. README.md +84 -45
  2. release_assets.json +4 -4
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-LMC-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/v0.57.3/src/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 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.57.3/fastsam_x-onnx-float.zip)
31
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.57.3/fastsam_x-qnn_dlc-float.zip)
32
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.57.3/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/v0.57.3/src/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/v0.57.3/src/qai_hub_models/models/fastsam_x) for usage instructions.
47
 
48
  ## Model Details
49
 
@@ -59,45 +59,84 @@ 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 | 24.677 ms | 176 - 176 MB | NPU
63
- | FastSam-X | ONNX | float | Snapdragon® X Elite | 47.169 ms | 144 - 144 MB | NPU
64
- | FastSam-X | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 37.26 ms | 18 - 323 MB | NPU
65
- | FastSam-X | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 95.669 ms | 17 - 405 MB | NPU
66
- | FastSam-X | ONNX | float | Qualcomm® QCS8550 (Proxy) | 46.734 ms | 0 - 158 MB | NPU
67
- | FastSam-X | ONNX | float | Qualcomm® QCS8450 | 95.669 ms | 17 - 405 MB | NPU
68
- | FastSam-X | ONNX | float | Snapdragon® 8 Elite Mobile | 27.7 ms | 12 - 242 MB | NPU
69
- | FastSam-X | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 19.596 ms | 13 - 260 MB | NPU
70
- | FastSam-X | ONNX | float | Qualcomm® QCS9075 | 73.66 ms | 12 - 58 MB | NPU
71
- | FastSam-X | ONNX | float | Qualcomm® QCS8750 | 27.7 ms | 12 - 242 MB | NPU
72
- | FastSam-X | ONNX | float | Qualcomm® QCS7181 | 47.169 ms | 144 - 144 MB | NPU
73
- | FastSam-X | QNN_DLC | float | Snapdragon® X2 Elite | 23.203 ms | 5 - 5 MB | NPU
74
- | FastSam-X | QNN_DLC | float | Snapdragon® X Elite | 44.036 ms | 5 - 5 MB | NPU
75
- | FastSam-X | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 32.796 ms | 2 - 300 MB | NPU
76
- | FastSam-X | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 91.676 ms | 4 - 385 MB | NPU
77
- | FastSam-X | QNN_DLC | float | Qualcomm® QCS8275 | 279.864 ms | 1 - 216 MB | NPU
78
- | FastSam-X | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 43.014 ms | 5 - 7 MB | NPU
79
- | FastSam-X | QNN_DLC | float | Qualcomm® QCS8450 | 91.676 ms | 4 - 385 MB | NPU
80
- | FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 25.6 ms | 0 - 223 MB | NPU
81
- | FastSam-X | QNN_DLC | float | Qualcomm® SA8295P | 77.754 ms | 0 - 298 MB | NPU
82
- | FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.523 ms | 5 - 237 MB | NPU
83
- | FastSam-X | QNN_DLC | float | Qualcomm® SA7255P | 279.864 ms | 1 - 216 MB | NPU
84
- | FastSam-X | QNN_DLC | float | Qualcomm® QCS9075 | 71.176 ms | 7 - 17 MB | NPU
85
- | FastSam-X | QNN_DLC | float | Qualcomm® QCS8750 | 25.6 ms | 0 - 223 MB | NPU
86
- | FastSam-X | QNN_DLC | float | Qualcomm® QCS7181 | 44.036 ms | 5 - 5 MB | NPU
87
- | FastSam-X | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 32.538 ms | 21 - 436 MB | NPU
88
- | FastSam-X | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 93.102 ms | 5 - 507 MB | NPU
89
- | FastSam-X | TFLITE | float | Qualcomm® QCS8275 | 279.412 ms | 5 - 257 MB | NPU
90
- | FastSam-X | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 42.53 ms | 4 - 9 MB | NPU
91
- | FastSam-X | TFLITE | float | Qualcomm® SA8775P | 532.533 ms | 5 - 30 MB | GPU
92
- | FastSam-X | TFLITE | float | Qualcomm® SA8650P | 532.533 ms | 5 - 30 MB | GPU
93
- | FastSam-X | TFLITE | float | Qualcomm® SA8255P | 532.533 ms | 5 - 30 MB | GPU
94
- | FastSam-X | TFLITE | float | Qualcomm® QCS8450 | 93.102 ms | 5 - 507 MB | NPU
95
- | FastSam-X | TFLITE | float | Snapdragon® 8 Elite Mobile | 25.615 ms | 3 - 261 MB | NPU
96
- | FastSam-X | TFLITE | float | Qualcomm® SA8295P | 77.163 ms | 5 - 335 MB | NPU
97
- | FastSam-X | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.11 ms | 0 - 261 MB | NPU
98
- | FastSam-X | TFLITE | float | Qualcomm® SA7255P | 279.412 ms | 5 - 257 MB | NPU
99
- | FastSam-X | TFLITE | float | Qualcomm® QCS9075 | 70.199 ms | 4 - 158 MB | NPU
100
- | FastSam-X | TFLITE | float | Qualcomm® QCS8750 | 25.615 ms | 3 - 261 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
101
 
102
  ## License
103
  * 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-LMC-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/v0.58.0/src/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 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.58.0/fastsam_x-onnx-float.zip)
31
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.58.0/fastsam_x-qnn_dlc-float.zip)
32
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.58.0/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/v0.58.0/src/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/v0.58.0/src/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® X2 Elite | 24.597 ms | 17 - 17 MB | NPU
63
+ | FastSam-X | ONNX | float | Snapdragon® X Elite | 47.21 ms | 139 - 139 MB | NPU
64
+ | FastSam-X | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 36.123 ms | 1 - 318 MB | NPU
65
+ | FastSam-X | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 92.802 ms | 17 - 415 MB | NPU
66
+ | FastSam-X | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 47.327 ms | 15 - 18 MB | NPU
67
+ | FastSam-X | ONNX | float | Qualcomm® QCS8450 | 92.802 ms | 17 - 415 MB | NPU
68
+ | FastSam-X | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 74.96 ms | 10 - 18 MB | NPU
69
+ | FastSam-X | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 20.025 ms | 13 - 266 MB | NPU
70
+ | FastSam-X | ONNX | float | Snapdragon® 8 Elite Mobile | 27.459 ms | 12 - 245 MB | NPU
71
+ | FastSam-X | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 27.459 ms | 12 - 245 MB | NPU
72
+ | FastSam-X | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 47.21 ms | 139 - 139 MB | NPU
73
+ | FastSam-X | ONNX | w8a16 | Snapdragon® X2 Elite | 15.502 ms | 9 - 9 MB | NPU
74
+ | FastSam-X | ONNX | w8a16 | Snapdragon® X Elite | 33.673 ms | 72 - 72 MB | NPU
75
+ | FastSam-X | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 24.626 ms | 1 - 453 MB | NPU
76
+ | FastSam-X | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 53.707 ms | 1 - 454 MB | NPU
77
+ | FastSam-X | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 183.569 ms | 6 - 11 MB | NPU
78
+ | FastSam-X | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 33.782 ms | 0 - 80 MB | NPU
79
+ | FastSam-X | ONNX | w8a16 | Qualcomm® QCS8450 | 53.707 ms | 1 - 454 MB | NPU
80
+ | FastSam-X | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 31.763 ms | 6 - 11 MB | NPU
81
+ | FastSam-X | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 61.143 ms | 8 - 432 MB | NPU
82
+ | FastSam-X | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 12.921 ms | 6 - 371 MB | NPU
83
+ | FastSam-X | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 662.064 ms | 0 - 547 MB | NPU
84
+ | FastSam-X | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 19.685 ms | 6 - 365 MB | NPU
85
+ | FastSam-X | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 61.143 ms | 8 - 432 MB | NPU
86
+ | FastSam-X | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 19.685 ms | 6 - 365 MB | NPU
87
+ | FastSam-X | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 33.673 ms | 72 - 72 MB | NPU
88
+ | FastSam-X | QNN_DLC | float | Snapdragon® X2 Elite | 23.121 ms | 5 - 5 MB | NPU
89
+ | FastSam-X | QNN_DLC | float | Snapdragon® X Elite | 44.042 ms | 5 - 5 MB | NPU
90
+ | FastSam-X | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 32.704 ms | 0 - 297 MB | NPU
91
+ | FastSam-X | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 91.178 ms | 4 - 387 MB | NPU
92
+ | FastSam-X | QNN_DLC | float | Qualcomm® QCS8275 | 279.826 ms | 1 - 216 MB | NPU
93
+ | FastSam-X | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 42.986 ms | 5 - 7 MB | NPU
94
+ | FastSam-X | QNN_DLC | float | Qualcomm® SA8775P | 68.448 ms | 1 - 213 MB | NPU
95
+ | FastSam-X | QNN_DLC | float | Qualcomm® SA8650P | 68.448 ms | 1 - 213 MB | NPU
96
+ | FastSam-X | QNN_DLC | float | Qualcomm® SA8255P | 68.448 ms | 1 - 213 MB | NPU
97
+ | FastSam-X | QNN_DLC | float | Qualcomm® QCS8450 | 91.178 ms | 4 - 387 MB | NPU
98
+ | FastSam-X | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 69.095 ms | 7 - 17 MB | NPU
99
+ | FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.965 ms | 4 - 238 MB | NPU
100
+ | FastSam-X | QNN_DLC | float | Qualcomm® SA7255P | 279.826 ms | 1 - 216 MB | NPU
101
+ | FastSam-X | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 25.416 ms | 0 - 223 MB | NPU
102
+ | FastSam-X | QNN_DLC | float | Qualcomm® SA8295P | 77.701 ms | 0 - 298 MB | NPU
103
+ | FastSam-X | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 25.416 ms | 0 - 223 MB | NPU
104
+ | FastSam-X | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 44.042 ms | 5 - 5 MB | NPU
105
+ | FastSam-X | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 15.128 ms | 2 - 2 MB | NPU
106
+ | FastSam-X | QNN_DLC | w8a16 | Snapdragon® X Elite | 31.559 ms | 2 - 2 MB | NPU
107
+ | FastSam-X | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 22.326 ms | 2 - 418 MB | NPU
108
+ | FastSam-X | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 49.615 ms | 2 - 417 MB | NPU
109
+ | FastSam-X | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 179.257 ms | 2 - 8 MB | NPU
110
+ | FastSam-X | QNN_DLC | w8a16 | Qualcomm® QCS8275 | 86.272 ms | 1 - 319 MB | NPU
111
+ | FastSam-X | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 31.333 ms | 2 - 5 MB | NPU
112
+ | FastSam-X | QNN_DLC | w8a16 | Qualcomm® SA8775P | 28.458 ms | 1 - 322 MB | NPU
113
+ | FastSam-X | QNN_DLC | w8a16 | Qualcomm® SA8650P | 28.458 ms | 1 - 322 MB | NPU
114
+ | FastSam-X | QNN_DLC | w8a16 | Qualcomm® SA8255P | 28.458 ms | 1 - 322 MB | NPU
115
+ | FastSam-X | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 49.615 ms | 2 - 417 MB | NPU
116
+ | FastSam-X | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 29.291 ms | 1 - 7 MB | NPU
117
+ | FastSam-X | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 53.974 ms | 2 - 398 MB | NPU
118
+ | FastSam-X | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 12.21 ms | 2 - 332 MB | NPU
119
+ | FastSam-X | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 700.692 ms | 3 - 480 MB | NPU
120
+ | FastSam-X | QNN_DLC | w8a16 | Qualcomm® SA7255P | 86.272 ms | 1 - 319 MB | NPU
121
+ | FastSam-X | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 18.598 ms | 2 - 329 MB | NPU
122
+ | FastSam-X | QNN_DLC | w8a16 | Qualcomm® SA8295P | 45.075 ms | 2 - 320 MB | NPU
123
+ | FastSam-X | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 53.974 ms | 2 - 398 MB | NPU
124
+ | FastSam-X | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 18.598 ms | 2 - 329 MB | NPU
125
+ | FastSam-X | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 31.559 ms | 2 - 2 MB | NPU
126
+ | FastSam-X | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 32.302 ms | 3 - 416 MB | NPU
127
+ | FastSam-X | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 92.08 ms | 5 - 506 MB | NPU
128
+ | FastSam-X | TFLITE | float | Qualcomm® QCS8275 | 279.354 ms | 5 - 256 MB | NPU
129
+ | FastSam-X | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 42.794 ms | 4 - 9 MB | NPU
130
+ | FastSam-X | TFLITE | float | Qualcomm® SA8775P | 67.984 ms | 5 - 257 MB | NPU
131
+ | FastSam-X | TFLITE | float | Qualcomm® SA8650P | 67.984 ms | 5 - 257 MB | NPU
132
+ | FastSam-X | TFLITE | float | Qualcomm® SA8255P | 67.984 ms | 5 - 257 MB | NPU
133
+ | FastSam-X | TFLITE | float | Qualcomm® QCS8450 | 92.08 ms | 5 - 506 MB | NPU
134
+ | FastSam-X | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 69.178 ms | 4 - 158 MB | NPU
135
+ | FastSam-X | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 17.077 ms | 0 - 261 MB | NPU
136
+ | FastSam-X | TFLITE | float | Qualcomm® SA7255P | 279.354 ms | 5 - 256 MB | NPU
137
+ | FastSam-X | TFLITE | float | Snapdragon® 8 Elite Mobile | 25.538 ms | 3 - 260 MB | NPU
138
+ | FastSam-X | TFLITE | float | Qualcomm® SA8295P | 77.161 ms | 5 - 336 MB | NPU
139
+ | FastSam-X | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 25.538 ms | 3 - 260 MB | NPU
140
 
141
  ## License
142
  * The license for the original implementation of FastSam-X can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.57.3",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,20 +8,20 @@
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.57.3/fastsam_x-tflite-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.57.3/fastsam_x-qnn_dlc-float.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327",
22
  "onnx_runtime": "1.25.0"
23
  },
24
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.57.3/fastsam_x-onnx-float.zip"
25
  }
26
  }
27
  }
 
1
  {
2
+ "version": "0.58.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
9
  "litert": "1.4.4"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.58.0/fastsam_x-tflite-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
  "qairt": "2.45.0.260326154327"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.58.0/fastsam_x-qnn_dlc-float.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327",
22
  "onnx_runtime": "1.25.0"
23
  },
24
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/fastsam_x/releases/v0.58.0/fastsam_x-onnx-float.zip"
25
  }
26
  }
27
  }