Hugging Face's logo

qualcomm
/
MobileSam

Image Segmentation
PyTorch
foundation
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
c0f5224
·
verified ·
1 Parent(s): fe91523

v0.60.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.60.0 for changelog.

Files changed (2) hide show
  1. README.md +97 -93
  2. release_assets.json +4 -4
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: image-segmentation
15
  Transformer based encoder-decoder where prompts specify what to segment in an image thereby allowing segmentation without the need for additional training. The image encoder generates embeddings and the lightweight decoder operates on the embeddings for point and mask based image segmentation.
16
 
17
  This is based on the implementation of MobileSam found [here](https://github.com/facebookresearch/segment-anything).
18
- 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/v0.59.0/src/qai_hub_models/models/mobilesam) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  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.
21
 
@@ -28,123 +28,127 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilesam/releases/v0.59.0/mobilesam-onnx-float.zip)
32
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilesam/releases/v0.59.0/mobilesam-qnn_dlc-float.zip)
33
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilesam/releases/v0.59.0/mobilesam-tflite-float.zip)
34
 
35
  For more device-specific assets and performance metrics, visit **[MobileSam on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/mobilesam)**.
36
 
37
 
38
  ### Option 2: Export with Custom Configurations
39
 
40
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/mobilesam) Python library to compile and export the model with your own:
41
  - Custom weights (e.g., fine-tuned checkpoints)
42
  - Custom input shapes
43
  - Target device and runtime configurations
44
 
45
  This option is ideal if you need to customize the model beyond the default configuration provided here.
46
 
47
- See our repository for [MobileSam on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/mobilesam) for usage instructions.
48
 
49
  ## Model Details
50
 
51
  **Model Type:** Model_use_case.semantic_segmentation
52
 
53
  **Model Stats:**
54
- - Model checkpoint: vit_t
55
  - Input resolution: 720p (720x1280)
56
- - Number of parameters (sam_encoder): 6.95M
 
57
  - Model size (sam_encoder) (float): 26.6 MB
58
  - Number of parameters (sam_decoder): 6.16M
59
- - Model size (sam_decoder) (float): 23.7 MB
60
 
61
  ## Performance Summary
62
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
63
  |---|---|---|---|---|---|---
64
- | decoder | ONNX | float | Snapdragon® X2 Elite | 2.636 ms | 4 - 4 MB | NPU
65
- | decoder | ONNX | float | Snapdragon® X Elite | 6.113 ms | 11 - 11 MB | NPU
66
- | decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.15 ms | 0 - 241 MB | NPU
67
- | decoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 14.315 ms | 5 - 233 MB | NPU
68
- | decoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.91 ms | 4 - 6 MB | NPU
69
- | decoder | ONNX | float | Qualcomm® QCS8450 | 14.315 ms | 5 - 233 MB | NPU
70
- | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 6.816 ms | 4 - 7 MB | NPU
71
- | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 6.113 ms | 11 - 11 MB | NPU
72
- | decoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 3.184 ms | 0 - 237 MB | NPU
73
- | decoder | ONNX | float | Snapdragon® 8 Elite Mobile | 3.184 ms | 0 - 237 MB | NPU
74
- | decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.544 ms | 1 - 215 MB | NPU
75
- | decoder | QNN_DLC | float | Snapdragon® X2 Elite | 3.005 ms | 4 - 4 MB | NPU
76
- | decoder | QNN_DLC | float | Snapdragon® X Elite | 5.711 ms | 4 - 4 MB | NPU
77
- | decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.735 ms | 4 - 223 MB | NPU
78
- | decoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 11.599 ms | 0 - 252 MB | NPU
79
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 12.588 ms | 0 - 193 MB | NPU
80
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.279 ms | 4 - 33 MB | NPU
81
- | decoder | QNN_DLC | float | Qualcomm® SA8775P | 6.269 ms | 0 - 194 MB | NPU
82
- | decoder | QNN_DLC | float | Qualcomm® SA8650P | 6.269 ms | 0 - 194 MB | NPU
83
- | decoder | QNN_DLC | float | Qualcomm® SA8255P | 6.269 ms | 0 - 194 MB | NPU
84
- | decoder | QNN_DLC | float | Qualcomm® QCS8450 | 11.599 ms | 0 - 252 MB | NPU
85
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 6.05 ms | 4 - 10 MB | NPU
86
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.711 ms | 4 - 4 MB | NPU
87
- | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.835 ms | 0 - 223 MB | NPU
88
- | decoder | QNN_DLC | float | Qualcomm® SA7255P | 12.588 ms | 0 - 193 MB | NPU
89
- | decoder | QNN_DLC | float | Qualcomm® SA8295P | 7.729 ms | 0 - 191 MB | NPU
90
- | decoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.835 ms | 0 - 223 MB | NPU
91
- | decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.537 ms | 4 - 196 MB | NPU
92
- | decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.413 ms | 0 - 211 MB | NPU
93
- | decoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 8.008 ms | 0 - 215 MB | NPU
94
- | decoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 11.845 ms | 0 - 185 MB | NPU
95
- | decoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.941 ms | 0 - 17 MB | NPU
96
- | decoder | TFLITE | float | Qualcomm® SA8775P | 5.934 ms | 0 - 189 MB | NPU
97
- | decoder | TFLITE | float | Qualcomm® SA8650P | 5.934 ms | 0 - 189 MB | NPU
98
- | decoder | TFLITE | float | Qualcomm® SA8255P | 5.934 ms | 0 - 189 MB | NPU
99
- | decoder | TFLITE | float | Qualcomm® QCS8450 | 8.008 ms | 0 - 215 MB | NPU
100
- | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 5.704 ms | 0 - 19 MB | NPU
101
- | decoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.596 ms | 0 - 184 MB | NPU
102
- | decoder | TFLITE | float | Qualcomm® SA7255P | 11.845 ms | 0 - 185 MB | NPU
103
- | decoder | TFLITE | float | Qualcomm® SA8295P | 7.282 ms | 0 - 183 MB | NPU
104
- | decoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.596 ms | 0 - 184 MB | NPU
105
- | decoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.165 ms | 0 - 187 MB | NPU
106
- | encoder | ONNX | float | Snapdragon® X2 Elite | 100.973 ms | 12 - 12 MB | NPU
107
- | encoder | ONNX | float | Snapdragon® X Elite | 168.548 ms | 14 - 14 MB | NPU
108
- | encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 125.733 ms | 12 - 1103 MB | NPU
109
- | encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 407.934 ms | 22 - 1128 MB | NPU
110
- | encoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 173.455 ms | 12 - 30 MB | NPU
111
- | encoder | ONNX | float | Qualcomm® QCS8450 | 407.934 ms | 22 - 1128 MB | NPU
112
- | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 178.544 ms | 12 - 15 MB | NPU
113
- | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 168.548 ms | 14 - 14 MB | NPU
114
- | encoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 100.448 ms | 8 - 919 MB | NPU
115
- | encoder | ONNX | float | Snapdragon® 8 Elite Mobile | 100.448 ms | 8 - 919 MB | NPU
116
- | encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 82.268 ms | 9 - 1036 MB | NPU
117
- | encoder | QNN_DLC | float | Snapdragon® X2 Elite | 46.051 ms | 12 - 12 MB | NPU
118
- | encoder | QNN_DLC | float | Snapdragon® X Elite | 103.021 ms | 12 - 12 MB | NPU
119
- | encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 65.626 ms | 12 - 1328 MB | NPU
120
- | encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 326.924 ms | 11 - 1341 MB | NPU
121
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 207.442 ms | 1 - 1126 MB | NPU
122
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 99.736 ms | 12 - 15 MB | NPU
123
- | encoder | QNN_DLC | float | Qualcomm® SA8775P | 100.378 ms | 1 - 1550 MB | NPU
124
- | encoder | QNN_DLC | float | Qualcomm® SA8650P | 100.378 ms | 1 - 1550 MB | NPU
125
- | encoder | QNN_DLC | float | Qualcomm® SA8255P | 100.378 ms | 1 - 1550 MB | NPU
126
- | encoder | QNN_DLC | float | Qualcomm® QCS8450 | 326.924 ms | 11 - 1341 MB | NPU
127
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 124.552 ms | 14 - 32 MB | NPU
128
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 103.021 ms | 12 - 12 MB | NPU
129
- | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 48.995 ms | 6 - 1122 MB | NPU
130
- | encoder | QNN_DLC | float | Qualcomm® SA7255P | 207.442 ms | 1 - 1126 MB | NPU
131
- | encoder | QNN_DLC | float | Qualcomm® SA8295P | 324.927 ms | 0 - 1557 MB | NPU
132
- | encoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 48.995 ms | 6 - 1122 MB | NPU
133
- | encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 40.341 ms | 12 - 1258 MB | NPU
134
- | encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 66.798 ms | 0 - 3190 MB | NPU
135
- | encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 311.267 ms | 4 - 1362 MB | NPU
136
- | encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 196.878 ms | 4 - 1634 MB | NPU
137
- | encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 90.526 ms | 4 - 8 MB | NPU
138
- | encoder | TFLITE | float | Qualcomm® SA8775P | 100.683 ms | 4 - 1670 MB | NPU
139
- | encoder | TFLITE | float | Qualcomm® SA8650P | 100.683 ms | 4 - 1670 MB | NPU
140
- | encoder | TFLITE | float | Qualcomm® SA8255P | 100.683 ms | 4 - 1670 MB | NPU
141
- | encoder | TFLITE | float | Qualcomm® QCS8450 | 311.267 ms | 4 - 1362 MB | NPU
142
- | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 101.504 ms | 0 - 45 MB | NPU
143
- | encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 48.492 ms | 2 - 1629 MB | NPU
144
- | encoder | TFLITE | float | Qualcomm® SA7255P | 196.878 ms | 4 - 1634 MB | NPU
145
- | encoder | TFLITE | float | Qualcomm® SA8295P | 258.167 ms | 4 - 1714 MB | NPU
146
- | encoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 48.492 ms | 2 - 1629 MB | NPU
147
- | encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 40.214 ms | 4 - 1796 MB | NPU
 
 
 
 
148
 
149
  ## License
150
  * The license for the original implementation of MobileSam can be found
 
15
  Transformer based encoder-decoder where prompts specify what to segment in an image thereby allowing segmentation without the need for additional training. The image encoder generates embeddings and the lightweight decoder operates on the embeddings for point and mask based image segmentation.
16
 
17
  This is based on the implementation of MobileSam found [here](https://github.com/facebookresearch/segment-anything).
18
+ 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/v0.60.0/src/qai_hub_models/models/mobilesam) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  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.
21
 
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilesam/releases/v0.60.0/mobilesam-onnx-float.zip)
32
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilesam/releases/v0.60.0/mobilesam-qnn_dlc-float.zip)
33
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilesam/releases/v0.60.0/mobilesam-tflite-float.zip)
34
 
35
  For more device-specific assets and performance metrics, visit **[MobileSam on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/mobilesam)**.
36
 
37
 
38
  ### Option 2: Export with Custom Configurations
39
 
40
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/mobilesam) Python library to compile and export the model with your own:
41
  - Custom weights (e.g., fine-tuned checkpoints)
42
  - Custom input shapes
43
  - Target device and runtime configurations
44
 
45
  This option is ideal if you need to customize the model beyond the default configuration provided here.
46
 
47
+ See our repository for [MobileSam on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/mobilesam) for usage instructions.
48
 
49
  ## Model Details
50
 
51
  **Model Type:** Model_use_case.semantic_segmentation
52
 
53
  **Model Stats:**
 
54
  - Input resolution: 720p (720x1280)
55
+ - Model checkpoint: vit_t
56
+ - Model size (sam_decoder) (float): 23.7 MB
57
  - Model size (sam_encoder) (float): 26.6 MB
58
  - Number of parameters (sam_decoder): 6.16M
59
+ - Number of parameters (sam_encoder): 6.95M
60
 
61
  ## Performance Summary
62
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
63
  |---|---|---|---|---|---|---
64
+ | decoder | ONNX | float | Snapdragon® X2 Elite | 2.631 ms | 4 - 4 MB | NPU
65
+ | decoder | ONNX | float | Snapdragon® X Elite | 6.205 ms | 11 - 11 MB | NPU
66
+ | decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.046 ms | 0 - 270 MB | NPU
67
+ | decoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 14.679 ms | 5 - 235 MB | NPU
68
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 6.285 ms | 4 - 8 MB | NPU
69
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.902 ms | 4 - 149 MB | NPU
70
+ | decoder | ONNX | float | Qualcomm® QCS8450 | 14.679 ms | 5 - 235 MB | NPU
71
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 6.896 ms | 4 - 7 MB | NPU
72
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 6.205 ms | 11 - 11 MB | NPU
73
+ | decoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 3.2 ms | 2 - 236 MB | NPU
74
+ | decoder | ONNX | float | Snapdragon® 8 Elite Mobile | 3.2 ms | 2 - 236 MB | NPU
75
+ | decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.536 ms | 4 - 217 MB | NPU
76
+ | decoder | QNN_DLC | float | Snapdragon® X2 Elite | 2.929 ms | 4 - 4 MB | NPU
77
+ | decoder | QNN_DLC | float | Snapdragon® X Elite | 5.933 ms | 4 - 4 MB | NPU
78
+ | decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.768 ms | 4 - 221 MB | NPU
79
+ | decoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 11.738 ms | 0 - 220 MB | NPU
80
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 5.763 ms | 4 - 11 MB | NPU
81
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 12.753 ms | 1 - 193 MB | NPU
82
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.462 ms | 4 - 6 MB | NPU
83
+ | decoder | QNN_DLC | float | Qualcomm® SA8775P | 6.377 ms | 0 - 193 MB | NPU
84
+ | decoder | QNN_DLC | float | Qualcomm® SA8650P | 6.377 ms | 0 - 193 MB | NPU
85
+ | decoder | QNN_DLC | float | Qualcomm® SA8255P | 6.377 ms | 0 - 193 MB | NPU
86
+ | decoder | QNN_DLC | float | Qualcomm® QCS8450 | 11.738 ms | 0 - 220 MB | NPU
87
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 6.208 ms | 4 - 10 MB | NPU
88
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.933 ms | 4 - 4 MB | NPU
89
+ | decoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.859 ms | 4 - 226 MB | NPU
90
+ | decoder | QNN_DLC | float | Qualcomm® SA7255P | 12.753 ms | 1 - 193 MB | NPU
91
+ | decoder | QNN_DLC | float | Qualcomm® SA8295P | 7.824 ms | 0 - 195 MB | NPU
92
+ | decoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.859 ms | 4 - 226 MB | NPU
93
+ | decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.57 ms | 4 - 193 MB | NPU
94
+ | decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.456 ms | 0 - 211 MB | NPU
95
+ | decoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 8.327 ms | 0 - 213 MB | NPU
96
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 5.35 ms | 0 - 19 MB | NPU
97
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 11.819 ms | 0 - 185 MB | NPU
98
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.993 ms | 0 - 13 MB | NPU
99
+ | decoder | TFLITE | float | Qualcomm® SA8775P | 5.865 ms | 0 - 186 MB | NPU
100
+ | decoder | TFLITE | float | Qualcomm® SA8650P | 5.865 ms | 0 - 186 MB | NPU
101
+ | decoder | TFLITE | float | Qualcomm® SA8255P | 5.865 ms | 0 - 186 MB | NPU
102
+ | decoder | TFLITE | float | Qualcomm® QCS8450 | 8.327 ms | 0 - 213 MB | NPU
103
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 5.694 ms | 0 - 19 MB | NPU
104
+ | decoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.612 ms | 0 - 184 MB | NPU
105
+ | decoder | TFLITE | float | Qualcomm® SA7255P | 11.819 ms | 0 - 185 MB | NPU
106
+ | decoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.612 ms | 0 - 184 MB | NPU
107
+ | decoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.197 ms | 0 - 184 MB | NPU
108
+ | encoder | ONNX | float | Snapdragon® X2 Elite | 58.844 ms | 12 - 12 MB | NPU
109
+ | encoder | ONNX | float | Snapdragon® X Elite | 116.8 ms | 13 - 13 MB | NPU
110
+ | encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 82.792 ms | 61 - 1181 MB | NPU
111
+ | encoder | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 328.543 ms | 20 - 1188 MB | NPU
112
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 111.548 ms | 12 - 16 MB | NPU
113
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 117.242 ms | 12 - 30 MB | NPU
114
+ | encoder | ONNX | float | Qualcomm® QCS8450 | 328.543 ms | 20 - 1188 MB | NPU
115
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 121.741 ms | 12 - 15 MB | NPU
116
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 116.8 ms | 13 - 13 MB | NPU
117
+ | encoder | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 62.301 ms | 9 - 929 MB | NPU
118
+ | encoder | ONNX | float | Snapdragon® 8 Elite Mobile | 62.301 ms | 9 - 929 MB | NPU
119
+ | encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 52.463 ms | 8 - 1027 MB | NPU
120
+ | encoder | QNN_DLC | float | Snapdragon® X2 Elite | 45.903 ms | 12 - 12 MB | NPU
121
+ | encoder | QNN_DLC | float | Snapdragon® X Elite | 102.849 ms | 12 - 12 MB | NPU
122
+ | encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 66.12 ms | 0 - 1315 MB | NPU
123
+ | encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 328.88 ms | 12 - 1342 MB | NPU
124
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 91.963 ms | 12 - 30 MB | NPU
125
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 207.594 ms | 1 - 1126 MB | NPU
126
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 100.663 ms | 12 - 15 MB | NPU
127
+ | encoder | QNN_DLC | float | Qualcomm® SA8775P | 100.335 ms | 0 - 1549 MB | NPU
128
+ | encoder | QNN_DLC | float | Qualcomm® SA8650P | 100.335 ms | 0 - 1549 MB | NPU
129
+ | encoder | QNN_DLC | float | Qualcomm® SA8255P | 100.335 ms | 0 - 1549 MB | NPU
130
+ | encoder | QNN_DLC | float | Qualcomm® QCS8450 | 328.88 ms | 12 - 1342 MB | NPU
131
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 101.207 ms | 14 - 32 MB | NPU
132
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 102.849 ms | 12 - 12 MB | NPU
133
+ | encoder | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 49.202 ms | 10 - 1125 MB | NPU
134
+ | encoder | QNN_DLC | float | Qualcomm® SA7255P | 207.594 ms | 1 - 1126 MB | NPU
135
+ | encoder | QNN_DLC | float | Qualcomm® SA8295P | 324.884 ms | 0 - 1556 MB | NPU
136
+ | encoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 49.202 ms | 10 - 1125 MB | NPU
137
+ | encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 40.35 ms | 11 - 1258 MB | NPU
138
+ | encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 66.668 ms | 3 - 3193 MB | NPU
139
+ | encoder | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 310.589 ms | 4 - 1362 MB | NPU
140
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 86.395 ms | 0 - 47 MB | NPU
141
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 196.915 ms | 4 - 1633 MB | NPU
142
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 90.801 ms | 4 - 8 MB | NPU
143
+ | encoder | TFLITE | float | Qualcomm® SA8775P | 100.654 ms | 0 - 1666 MB | NPU
144
+ | encoder | TFLITE | float | Qualcomm® SA8650P | 100.654 ms | 0 - 1666 MB | NPU
145
+ | encoder | TFLITE | float | Qualcomm® SA8255P | 100.654 ms | 0 - 1666 MB | NPU
146
+ | encoder | TFLITE | float | Qualcomm® QCS8450 | 310.589 ms | 4 - 1362 MB | NPU
147
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 101.13 ms | 0 - 45 MB | NPU
148
+ | encoder | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 47.785 ms | 2 - 1631 MB | NPU
149
+ | encoder | TFLITE | float | Qualcomm® SA7255P | 196.915 ms | 4 - 1633 MB | NPU
150
+ | encoder | TFLITE | float | Snapdragon® 8 Elite Mobile | 47.785 ms | 2 - 1631 MB | NPU
151
+ | encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 39.872 ms | 3 - 1795 MB | NPU
152
 
153
  ## License
154
  * The license for the original implementation of MobileSam can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.59.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,19 +8,19 @@
8
  "qairt": "2.45.0.260326154327",
9
  "onnx_runtime": "1.27.1"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilesam/releases/v0.59.0/mobilesam-onnx-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/mobilesam/releases/v0.59.0/mobilesam-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327"
22
  },
23
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilesam/releases/v0.59.0/mobilesam-tflite-float.zip"
24
  }
25
  }
26
  }
 
1
  {
2
+ "version": "0.60.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
8
  "qairt": "2.45.0.260326154327",
9
  "onnx_runtime": "1.27.1"
10
  },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilesam/releases/v0.60.0/mobilesam-onnx-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/mobilesam/releases/v0.60.0/mobilesam-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
  "qairt": "2.45.0.260326154327"
22
  },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilesam/releases/v0.60.0/mobilesam-tflite-float.zip"
24
  }
25
  }
26
  }