qaihm-bot commited on
Commit
02b127d
·
verified ·
1 Parent(s): 9c0dc12

See https://github.com/qualcomm/ai-hub-models/releases/v0.56.0 for changelog.

Files changed (2) hide show
  1. README.md +152 -106
  2. release_assets.json +13 -13
README.md CHANGED
@@ -28,10 +28,10 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.55.0/sam2-onnx-float.zip)
32
- | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.55.0/sam2-onnx-w8a8.zip)
33
- | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.55.0/sam2-qnn_dlc-w8a8.zip)
34
- | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.55.0/sam2-tflite-w8a8.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[Segment-Anything-Model-2 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/sam2)**.
37
 
@@ -62,108 +62,154 @@ See our repository for [Segment-Anything-Model-2 on GitHub](https://github.com/q
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
- | decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.17 ms | 16 - 235 MB | NPU
66
- | decoder | ONNX | float | Snapdragon® X2 Elite | 3.275 ms | 196 - 196 MB | NPU
67
- | decoder | ONNX | float | Snapdragon® X Elite | 6.616 ms | 164 - 164 MB | NPU
68
- | decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.713 ms | 17 - 340 MB | NPU
69
- | decoder | ONNX | float | Qualcomm® QCS8550 (Proxy) | 6.727 ms | 16 - 45 MB | NPU
70
- | decoder | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.493 ms | 3 - 240 MB | NPU
71
- | decoder | ONNX | float | Qualcomm® QCS9075 | 8.35 ms | 16 - 61 MB | NPU
72
- | decoder | ONNX | float | Qualcomm® QCS8750 | 3.493 ms | 3 - 240 MB | NPU
73
- | decoder | ONNX | float | Qualcomm® QCS7181 | 6.616 ms | 164 - 164 MB | NPU
74
- | decoder | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 5.281 ms | 4 - 276 MB | NPU
75
- | decoder | ONNX | w8a8 | Snapdragon® X2 Elite | 5.446 ms | 208 - 208 MB | NPU
76
- | decoder | ONNX | w8a8 | Snapdragon® X Elite | 12.356 ms | 177 - 177 MB | NPU
77
- | decoder | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 9.205 ms | 4 - 284 MB | NPU
78
- | decoder | ONNX | w8a8 | Qualcomm® QCS6490 | 138.336 ms | 47 - 68 MB | CPU
79
- | decoder | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 11.963 ms | 1 - 53 MB | NPU
80
- | decoder | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 50.617 ms | 50 - 70 MB | CPU
81
- | decoder | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 7.0 ms | 2 - 250 MB | NPU
82
- | decoder | ONNX | w8a8 | Qualcomm® QCS9075 | 13.715 ms | 1 - 49 MB | NPU
83
- | decoder | ONNX | w8a8 | Qualcomm® QCM6690 | 58.145 ms | 45 - 68 MB | CPU
84
- | decoder | ONNX | w8a8 | Qualcomm® QCS7790 | 50.617 ms | 50 - 70 MB | CPU
85
- | decoder | ONNX | w8a8 | Qualcomm® QCS8750 | 7.0 ms | 2 - 250 MB | NPU
86
- | decoder | ONNX | w8a8 | Qualcomm® QCS7181 | 12.356 ms | 177 - 177 MB | NPU
87
- | decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.724 ms | 4 - 190 MB | NPU
88
- | decoder | QNN_DLC | float | Snapdragon® X2 Elite | 3.19 ms | 16 - 16 MB | NPU
89
- | decoder | QNN_DLC | float | Snapdragon® X Elite | 5.818 ms | 16 - 16 MB | NPU
90
- | decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.733 ms | 4 - 215 MB | NPU
91
- | decoder | QNN_DLC | float | Qualcomm® QCS8275 | 12.586 ms | 16 - 199 MB | NPU
92
- | decoder | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 5.565 ms | 16 - 18 MB | NPU
93
- | decoder | QNN_DLC | float | Qualcomm® SA8775P | 7.265 ms | 16 - 231 MB | NPU
94
- | decoder | QNN_DLC | float | Qualcomm® SA8650P | 7.265 ms | 16 - 231 MB | NPU
95
- | decoder | QNN_DLC | float | Qualcomm® SA8255P | 7.265 ms | 16 - 231 MB | NPU
96
- | decoder | QNN_DLC | float | Qualcomm® SA7255P | 12.586 ms | 16 - 199 MB | NPU
97
- | decoder | QNN_DLC | float | Qualcomm® SA8295P | 8.889 ms | 0 - 194 MB | NPU
98
- | decoder | QNN_DLC | float | Qualcomm® QCS9075 | 7.242 ms | 16 - 34 MB | NPU
99
- | decoder | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 10.936 ms | 4 - 220 MB | NPU
100
- | decoder | QNN_DLC | float | Qualcomm® QCS7181 | 5.818 ms | 16 - 16 MB | NPU
101
- | decoder | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.931 ms | 1 - 110 MB | NPU
102
- | decoder | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 1.381 ms | 4 - 4 MB | NPU
103
- | decoder | QNN_DLC | w8a8 | Snapdragon® X Elite | 2.438 ms | 4 - 4 MB | NPU
104
- | decoder | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.413 ms | 0 - 110 MB | NPU
105
- | decoder | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 9.535 ms | 1 - 7 MB | NPU
106
- | decoder | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 2.124 ms | 4 - 6 MB | NPU
107
- | decoder | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 2.694 ms | 4 - 215 MB | NPU
108
- | decoder | QNN_DLC | w8a8 | Qualcomm® SA8295P | 3.167 ms | 4 - 88 MB | NPU
109
- | decoder | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 1.082 ms | 1 - 90 MB | NPU
110
- | decoder | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 2.543 ms | 1 - 6 MB | NPU
111
- | decoder | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 2.61 ms | 0 - 112 MB | NPU
112
- | decoder | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 10.537 ms | 4 - 263 MB | NPU
113
- | decoder | QNN_DLC | w8a8 | Qualcomm® QCS7790 | 2.694 ms | 4 - 215 MB | NPU
114
- | decoder | QNN_DLC | w8a8 | Qualcomm® QCS8750 | 1.082 ms | 1 - 90 MB | NPU
115
- | decoder | QNN_DLC | w8a8 | Qualcomm® QCS7181 | 2.438 ms | 4 - 4 MB | NPU
116
- | encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 86.21 ms | 56 - 1635 MB | NPU
117
- | encoder | ONNX | float | Snapdragon® X2 Elite | 90.819 ms | 200 - 200 MB | NPU
118
- | encoder | ONNX | float | Snapdragon® X Elite | 159.174 ms | 169 - 169 MB | NPU
119
- | encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 121.266 ms | 36 - 3794 MB | NPU
120
- | encoder | ONNX | float | Qualcomm® QCS8550 (Proxy) | 161.393 ms | 39 - 46 MB | NPU
121
- | encoder | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 93.481 ms | 44 - 1589 MB | NPU
122
- | encoder | ONNX | float | Qualcomm® QCS9075 | 215.791 ms | 12 - 69 MB | NPU
123
- | encoder | ONNX | float | Qualcomm® QCS8750 | 93.481 ms | 44 - 1589 MB | NPU
124
- | encoder | ONNX | float | Qualcomm® QCS7181 | 159.174 ms | 169 - 169 MB | NPU
125
- | encoder | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 36.776 ms | 14 - 1699 MB | NPU
126
- | encoder | ONNX | w8a8 | Snapdragon® X2 Elite | 38.896 ms | 210 - 210 MB | NPU
127
- | encoder | ONNX | w8a8 | Snapdragon® X Elite | 85.405 ms | 178 - 178 MB | NPU
128
- | encoder | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 58.874 ms | 14 - 1938 MB | NPU
129
- | encoder | ONNX | w8a8 | Qualcomm® QCS6490 | 2210.942 ms | 519 - 542 MB | CPU
130
- | encoder | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 85.855 ms | 12 - 109 MB | NPU
131
- | encoder | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1278.774 ms | 417 - 432 MB | CPU
132
- | encoder | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 44.977 ms | 12 - 1679 MB | NPU
133
- | encoder | ONNX | w8a8 | Qualcomm® QCS9075 | 108.831 ms | 13 - 58 MB | NPU
134
- | encoder | ONNX | w8a8 | Qualcomm® QCM6690 | 1354.249 ms | 440 - 454 MB | CPU
135
- | encoder | ONNX | w8a8 | Qualcomm® QCS7790 | 1278.774 ms | 417 - 432 MB | CPU
136
- | encoder | ONNX | w8a8 | Qualcomm® QCS8750 | 44.977 ms | 12 - 1679 MB | NPU
137
- | encoder | ONNX | w8a8 | Qualcomm® QCS7181 | 85.405 ms | 178 - 178 MB | NPU
138
- | encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 90.75 ms | 12 - 2375 MB | NPU
139
- | encoder | QNN_DLC | float | Snapdragon® X2 Elite | 97.103 ms | 12 - 12 MB | NPU
140
- | encoder | QNN_DLC | float | Snapdragon® X Elite | 173.289 ms | 12 - 12 MB | NPU
141
- | encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 131.252 ms | 88 - 1945 MB | NPU
142
- | encoder | QNN_DLC | float | Qualcomm® QCS8275 | 416.989 ms | 1 - 1588 MB | NPU
143
- | encoder | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 173.333 ms | 12 - 15 MB | NPU
144
- | encoder | QNN_DLC | float | Qualcomm® SA8775P | 187.953 ms | 1 - 1584 MB | NPU
145
- | encoder | QNN_DLC | float | Qualcomm® SA8650P | 187.953 ms | 1 - 1584 MB | NPU
146
- | encoder | QNN_DLC | float | Qualcomm® SA8255P | 187.953 ms | 1 - 1584 MB | NPU
147
- | encoder | QNN_DLC | float | Qualcomm® SA7255P | 416.989 ms | 1 - 1588 MB | NPU
148
- | encoder | QNN_DLC | float | Qualcomm® SA8295P | 266.723 ms | 0 - 1572 MB | NPU
149
- | encoder | QNN_DLC | float | Qualcomm® QCS9075 | 228.938 ms | 12 - 46 MB | NPU
150
- | encoder | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 354.948 ms | 12 - 1870 MB | NPU
151
- | encoder | QNN_DLC | float | Qualcomm® QCS7181 | 173.289 ms | 12 - 12 MB | NPU
152
- | encoder | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 35.063 ms | 3 - 1756 MB | NPU
153
- | encoder | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 37.509 ms | 3 - 3 MB | NPU
154
- | encoder | QNN_DLC | w8a8 | Snapdragon® X Elite | 82.057 ms | 3 - 3 MB | NPU
155
- | encoder | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 54.876 ms | 3 - 2207 MB | NPU
156
- | encoder | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 630.421 ms | 3 - 13 MB | NPU
157
- | encoder | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 78.447 ms | 3 - 1315 MB | NPU
158
- | encoder | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 98.667 ms | 3 - 2385 MB | NPU
159
- | encoder | QNN_DLC | w8a8 | Qualcomm® SA8295P | 91.426 ms | 3 - 1740 MB | NPU
160
- | encoder | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 40.554 ms | 3 - 1678 MB | NPU
161
- | encoder | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 92.282 ms | 4 - 13 MB | NPU
162
- | encoder | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 136.838 ms | 4 - 2201 MB | NPU
163
- | encoder | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 1500.794 ms | 18 - 2768 MB | NPU
164
- | encoder | QNN_DLC | w8a8 | Qualcomm® QCS7790 | 98.667 ms | 3 - 2385 MB | NPU
165
- | encoder | QNN_DLC | w8a8 | Qualcomm® QCS8750 | 40.554 ms | 3 - 1678 MB | NPU
166
- | encoder | QNN_DLC | w8a8 | Qualcomm® QCS7181 | 82.057 ms | 3 - 3 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
167
 
168
  ## License
169
  * The license for the original implementation of Segment-Anything-Model-2 can be found
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | 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/sam2/releases/v0.56.0/sam2-onnx-float.zip)
32
+ | ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.56.0/sam2-onnx-w8a8.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.56.0/sam2-qnn_dlc-float.zip)
34
+ | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.56.0/sam2-tflite-w8a8.zip)
35
 
36
  For more device-specific assets and performance metrics, visit **[Segment-Anything-Model-2 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/sam2)**.
37
 
 
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
+ | decoder | ONNX | float | Snapdragon® X2 Elite | 3.313 ms | 197 - 197 MB | NPU
66
+ | decoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.756 ms | 2 - 243 MB | NPU
67
+ | decoder | ONNX | float | Qualcomm® QCS8550 (Proxy) | 6.758 ms | 16 - 20 MB | NPU
68
+ | decoder | ONNX | float | Snapdragon® 8 Elite Mobile | 3.779 ms | 3 - 222 MB | NPU
69
+ | decoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.198 ms | 2 - 219 MB | NPU
70
+ | decoder | ONNX | float | Qualcomm® QCS9075 | 8.242 ms | 16 - 61 MB | NPU
71
+ | decoder | ONNX | float | Qualcomm® QCS8750 | 3.779 ms | 3 - 222 MB | NPU
72
+ | decoder | ONNX | w8a8 | Snapdragon® X2 Elite | 1.328 ms | 209 - 209 MB | NPU
73
+ | decoder | ONNX | w8a8 | Snapdragon® X Elite | 2.764 ms | 178 - 178 MB | NPU
74
+ | decoder | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.745 ms | 0 - 144 MB | NPU
75
+ | decoder | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 3.493 ms | 4 - 156 MB | NPU
76
+ | decoder | ONNX | w8a8 | Qualcomm® QCS6490 | 11.004 ms | 4 - 49 MB | NPU
77
+ | decoder | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 2.642 ms | 4 - 8 MB | NPU
78
+ | decoder | ONNX | w8a8 | Qualcomm® QCS8450 | 3.493 ms | 4 - 156 MB | NPU
79
+ | decoder | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 1.253 ms | 0 - 155 MB | NPU
80
+ | decoder | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 3.365 ms | 4 - 296 MB | NPU
81
+ | decoder | ONNX | w8a8 | Qualcomm® QCM6690 | 16.61 ms | 2 - 249 MB | NPU
82
+ | decoder | ONNX | w8a8 | Qualcomm® QCS9075 | 3.267 ms | 1 - 49 MB | NPU
83
+ | decoder | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 1.423 ms | 0 - 131 MB | NPU
84
+ | decoder | ONNX | w8a8 | Qualcomm® QCS7790 | 3.365 ms | 4 - 296 MB | NPU
85
+ | decoder | ONNX | w8a8 | Qualcomm® QCS8750 | 1.423 ms | 0 - 131 MB | NPU
86
+ | decoder | ONNX | w8a8 | Qualcomm® QCS7181 | 2.764 ms | 178 - 178 MB | NPU
87
+ | decoder | QNN_DLC | float | Snapdragon® X2 Elite | 3.062 ms | 16 - 16 MB | NPU
88
+ | decoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.714 ms | 4 - 216 MB | NPU
89
+ | decoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 10.035 ms | 4 - 218 MB | NPU
90
+ | decoder | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 5.378 ms | 16 - 20 MB | NPU
91
+ | decoder | QNN_DLC | float | Qualcomm® QCS8450 | 10.035 ms | 4 - 218 MB | NPU
92
+ | decoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.932 ms | 0 - 186 MB | NPU
93
+ | decoder | QNN_DLC | float | Qualcomm® SA8295P | 8.23 ms | 0 - 195 MB | NPU
94
+ | decoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.584 ms | 4 - 192 MB | NPU
95
+ | decoder | QNN_DLC | float | Qualcomm® QCS9075 | 6.682 ms | 16 - 34 MB | NPU
96
+ | decoder | QNN_DLC | float | Qualcomm® QCS8750 | 2.932 ms | 0 - 186 MB | NPU
97
+ | decoder | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 1.738 ms | 4 - 4 MB | NPU
98
+ | decoder | QNN_DLC | w8a8 | Snapdragon® X Elite | 2.29 ms | 4 - 4 MB | NPU
99
+ | decoder | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 1.29 ms | 0 - 108 MB | NPU
100
+ | decoder | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 2.562 ms | 0 - 109 MB | NPU
101
+ | decoder | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 8.279 ms | 1 - 7 MB | NPU
102
+ | decoder | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 1.987 ms | 4 - 25 MB | NPU
103
+ | decoder | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 2.562 ms | 0 - 109 MB | NPU
104
+ | decoder | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.909 ms | 1 - 109 MB | NPU
105
+ | decoder | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 2.671 ms | 4 - 216 MB | NPU
106
+ | decoder | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 9.965 ms | 4 - 273 MB | NPU
107
+ | decoder | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 2.42 ms | 1 - 7 MB | NPU
108
+ | decoder | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 1.011 ms | 1 - 92 MB | NPU
109
+ | decoder | QNN_DLC | w8a8 | Qualcomm® SA8295P | 2.971 ms | 4 - 103 MB | NPU
110
+ | decoder | QNN_DLC | w8a8 | Qualcomm® QCS7790 | 2.671 ms | 4 - 216 MB | NPU
111
+ | decoder | QNN_DLC | w8a8 | Qualcomm® QCS8750 | 1.011 ms | 1 - 92 MB | NPU
112
+ | decoder | QNN_DLC | w8a8 | Qualcomm® QCS7181 | 2.29 ms | 4 - 4 MB | NPU
113
+ | decoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.72 ms | 0 - 213 MB | NPU
114
+ | decoder | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 5.328 ms | 0 - 8 MB | NPU
115
+ | decoder | TFLITE | float | Qualcomm® SA8775P | 42.72 ms | 0 - 33 MB | GPU
116
+ | decoder | TFLITE | float | Qualcomm® SA8650P | 42.72 ms | 0 - 33 MB | GPU
117
+ | decoder | TFLITE | float | Qualcomm® SA8255P | 42.72 ms | 0 - 33 MB | GPU
118
+ | decoder | TFLITE | float | Qualcomm® SA8295P | 8.211 ms | 0 - 196 MB | NPU
119
+ | decoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.625 ms | 0 - 182 MB | NPU
120
+ | decoder | TFLITE | float | Qualcomm® QCS9075 | 6.904 ms | 0 - 30 MB | NPU
121
+ | decoder | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 5.77 ms | 0 - 268 MB | NPU
122
+ | decoder | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 10.205 ms | 0 - 246 MB | NPU
123
+ | decoder | TFLITE | w8a8 | Qualcomm® QCS6490 | 33.535 ms | 12 - 58 MB | NPU
124
+ | decoder | TFLITE | w8a8 | Qualcomm® QCS8275 | 13.534 ms | 0 - 237 MB | NPU
125
+ | decoder | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 7.744 ms | 0 - 22 MB | NPU
126
+ | decoder | TFLITE | w8a8 | Qualcomm® SA8775P | 41.987 ms | 17 - 52 MB | GPU
127
+ | decoder | TFLITE | w8a8 | Qualcomm® SA8650P | 41.987 ms | 17 - 52 MB | GPU
128
+ | decoder | TFLITE | w8a8 | Qualcomm® SA8255P | 41.987 ms | 17 - 52 MB | GPU
129
+ | decoder | TFLITE | w8a8 | Qualcomm® QCS8450 | 10.205 ms | 0 - 246 MB | NPU
130
+ | decoder | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.107 ms | 0 - 260 MB | NPU
131
+ | decoder | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 14.815 ms | 12 - 201 MB | NPU
132
+ | decoder | TFLITE | w8a8 | Qualcomm® QCM6690 | 32.284 ms | 12 - 211 MB | NPU
133
+ | decoder | TFLITE | w8a8 | Qualcomm® QCS9075 | 8.536 ms | 0 - 14 MB | NPU
134
+ | decoder | TFLITE | w8a8 | Qualcomm® SA7255P | 13.534 ms | 0 - 237 MB | NPU
135
+ | decoder | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 3.516 ms | 0 - 239 MB | NPU
136
+ | decoder | TFLITE | w8a8 | Qualcomm® SA8295P | 9.456 ms | 0 - 239 MB | NPU
137
+ | decoder | TFLITE | w8a8 | Qualcomm® QCS7790 | 14.815 ms | 12 - 201 MB | NPU
138
+ | decoder | TFLITE | w8a8 | Qualcomm® QCS8750 | 3.516 ms | 0 - 239 MB | NPU
139
+ | encoder | ONNX | float | Snapdragon® X2 Elite | 86.407 ms | 202 - 202 MB | NPU
140
+ | encoder | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 126.384 ms | 58 - 2157 MB | NPU
141
+ | encoder | ONNX | float | Qualcomm® QCS8550 (Proxy) | 168.886 ms | 8 - 95 MB | NPU
142
+ | encoder | ONNX | float | Snapdragon® 8 Elite Mobile | 98.542 ms | 44 - 1798 MB | NPU
143
+ | encoder | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 78.81 ms | 15 - 1681 MB | NPU
144
+ | encoder | ONNX | float | Qualcomm® QCS9075 | 226.812 ms | 12 - 69 MB | NPU
145
+ | encoder | ONNX | float | Qualcomm® QCS8750 | 98.542 ms | 44 - 1798 MB | NPU
146
+ | encoder | ONNX | w8a8 | Snapdragon® X2 Elite | 35.714 ms | 211 - 211 MB | NPU
147
+ | encoder | ONNX | w8a8 | Snapdragon® X Elite | 91.637 ms | 179 - 179 MB | NPU
148
+ | encoder | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 64.07 ms | 14 - 1933 MB | NPU
149
+ | encoder | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 123.485 ms | 14 - 2449 MB | NPU
150
+ | encoder | ONNX | w8a8 | Qualcomm® QCS6490 | 609.502 ms | 9 - 54 MB | NPU
151
+ | encoder | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 88.496 ms | 12 - 17 MB | NPU
152
+ | encoder | ONNX | w8a8 | Qualcomm® QCS8450 | 123.485 ms | 14 - 2449 MB | NPU
153
+ | encoder | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 33.968 ms | 11 - 1675 MB | NPU
154
+ | encoder | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 90.665 ms | 4 - 2343 MB | NPU
155
+ | encoder | ONNX | w8a8 | Qualcomm® QCM6690 | 1710.399 ms | 3 - 1930 MB | NPU
156
+ | encoder | ONNX | w8a8 | Qualcomm® QCS9075 | 93.189 ms | 15 - 60 MB | NPU
157
+ | encoder | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 39.187 ms | 11 - 2121 MB | NPU
158
+ | encoder | ONNX | w8a8 | Qualcomm® QCS7790 | 90.665 ms | 4 - 2343 MB | NPU
159
+ | encoder | ONNX | w8a8 | Qualcomm® QCS8750 | 39.187 ms | 11 - 2121 MB | NPU
160
+ | encoder | ONNX | w8a8 | Qualcomm® QCS7181 | 91.637 ms | 179 - 179 MB | NPU
161
+ | encoder | QNN_DLC | float | Snapdragon® X2 Elite | 86.374 ms | 12 - 12 MB | NPU
162
+ | encoder | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 128.059 ms | 12 - 2146 MB | NPU
163
+ | encoder | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 342.121 ms | 12 - 1862 MB | NPU
164
+ | encoder | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 179.716 ms | 9 - 16 MB | NPU
165
+ | encoder | QNN_DLC | float | Qualcomm® QCS8450 | 342.121 ms | 12 - 1862 MB | NPU
166
+ | encoder | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 101.744 ms | 12 - 2522 MB | NPU
167
+ | encoder | QNN_DLC | float | Qualcomm® SA8295P | 282.43 ms | 0 - 1581 MB | NPU
168
+ | encoder | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 78.185 ms | 12 - 1718 MB | NPU
169
+ | encoder | QNN_DLC | float | Qualcomm® QCS9075 | 218.985 ms | 12 - 46 MB | NPU
170
+ | encoder | QNN_DLC | float | Qualcomm® QCS8750 | 101.744 ms | 12 - 2522 MB | NPU
171
+ | encoder | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 36.008 ms | 3 - 3 MB | NPU
172
+ | encoder | QNN_DLC | w8a8 | Snapdragon® X Elite | 82.781 ms | 3 - 3 MB | NPU
173
+ | encoder | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 54.397 ms | 3 - 2370 MB | NPU
174
+ | encoder | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 139.076 ms | 3 - 2385 MB | NPU
175
+ | encoder | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 613.773 ms | 3 - 13 MB | NPU
176
+ | encoder | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 79.296 ms | 3 - 666 MB | NPU
177
+ | encoder | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 139.076 ms | 3 - 2385 MB | NPU
178
+ | encoder | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 35.326 ms | 3 - 1662 MB | NPU
179
+ | encoder | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 94.722 ms | 3 - 2357 MB | NPU
180
+ | encoder | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 1700.608 ms | 3 - 1919 MB | NPU
181
+ | encoder | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 95.786 ms | 4 - 13 MB | NPU
182
+ | encoder | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 39.575 ms | 3 - 1621 MB | NPU
183
+ | encoder | QNN_DLC | w8a8 | Qualcomm® SA8295P | 95.708 ms | 0 - 1605 MB | NPU
184
+ | encoder | QNN_DLC | w8a8 | Qualcomm® QCS7790 | 94.722 ms | 3 - 2357 MB | NPU
185
+ | encoder | QNN_DLC | w8a8 | Qualcomm® QCS8750 | 39.575 ms | 3 - 1621 MB | NPU
186
+ | encoder | QNN_DLC | w8a8 | Qualcomm® QCS7181 | 82.781 ms | 3 - 3 MB | NPU
187
+ | encoder | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 129.64 ms | 20 - 2227 MB | NPU
188
+ | encoder | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 180.195 ms | 20 - 23 MB | NPU
189
+ | encoder | TFLITE | float | Qualcomm® SA8775P | 2416.888 ms | 39 - 65 MB | CPU
190
+ | encoder | TFLITE | float | Qualcomm® SA8650P | 2416.888 ms | 39 - 65 MB | CPU
191
+ | encoder | TFLITE | float | Qualcomm® SA8255P | 2416.888 ms | 39 - 65 MB | CPU
192
+ | encoder | TFLITE | float | Qualcomm® SA8295P | 282.733 ms | 20 - 1665 MB | NPU
193
+ | encoder | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 76.301 ms | 20 - 1776 MB | NPU
194
+ | encoder | TFLITE | float | Qualcomm® QCS9075 | 218.941 ms | 0 - 114 MB | NPU
195
+ | encoder | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 69.462 ms | 5 - 2221 MB | NPU
196
+ | encoder | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 186.937 ms | 5 - 2293 MB | NPU
197
+ | encoder | TFLITE | w8a8 | Qualcomm® QCS6490 | 1724.645 ms | 76 - 338 MB | CPU
198
+ | encoder | TFLITE | w8a8 | Qualcomm® QCS8275 | 162.696 ms | 6 - 1874 MB | NPU
199
+ | encoder | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 100.759 ms | 5 - 10 MB | NPU
200
+ | encoder | TFLITE | w8a8 | Qualcomm® SA8775P | 1227.827 ms | 78 - 104 MB | CPU
201
+ | encoder | TFLITE | w8a8 | Qualcomm® SA8650P | 1227.827 ms | 78 - 104 MB | CPU
202
+ | encoder | TFLITE | w8a8 | Qualcomm® SA8255P | 1227.827 ms | 78 - 104 MB | CPU
203
+ | encoder | TFLITE | w8a8 | Qualcomm® QCS8450 | 186.937 ms | 5 - 2293 MB | NPU
204
+ | encoder | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 34.521 ms | 4 - 1787 MB | NPU
205
+ | encoder | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 1131.84 ms | 78 - 311 MB | CPU
206
+ | encoder | TFLITE | w8a8 | Qualcomm® QCM6690 | 2361.942 ms | 32 - 265 MB | CPU
207
+ | encoder | TFLITE | w8a8 | Qualcomm® QCS9075 | 108.995 ms | 4 - 62 MB | NPU
208
+ | encoder | TFLITE | w8a8 | Qualcomm® SA7255P | 162.696 ms | 6 - 1874 MB | NPU
209
+ | encoder | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 55.081 ms | 5 - 1793 MB | NPU
210
+ | encoder | TFLITE | w8a8 | Qualcomm® SA8295P | 117.632 ms | 5 - 1883 MB | NPU
211
+ | encoder | TFLITE | w8a8 | Qualcomm® QCS7790 | 1131.84 ms | 78 - 311 MB | CPU
212
+ | encoder | TFLITE | w8a8 | Qualcomm® QCS8750 | 55.081 ms | 5 - 1793 MB | NPU
213
 
214
  ## License
215
  * The license for the original implementation of Segment-Anything-Model-2 can be found
release_assets.json CHANGED
@@ -1,14 +1,20 @@
1
  {
2
- "version": "0.55.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
 
 
 
 
 
 
6
  "onnx": {
7
  "tool_versions": {
8
- "qairt": "2.42.0.251225135753_193295",
9
  "onnx_runtime": "1.25.0"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.55.0/sam2-onnx-float.zip"
12
  }
13
  }
14
  },
@@ -17,22 +23,16 @@
17
  "tflite": {
18
  "tool_versions": {
19
  "qairt": "2.45.0.260326154327",
20
- "litert": "1.4.3"
21
  },
22
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.55.0/sam2-tflite-w8a8.zip"
23
- },
24
- "qnn_dlc": {
25
- "tool_versions": {
26
- "qairt": "2.45.0.260326154327"
27
- },
28
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.55.0/sam2-qnn_dlc-w8a8.zip"
29
  },
30
  "onnx": {
31
  "tool_versions": {
32
- "qairt": "2.42.0.251225135753_193295",
33
  "onnx_runtime": "1.25.0"
34
  },
35
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.55.0/sam2-onnx-w8a8.zip"
36
  }
37
  }
38
  }
 
1
  {
2
+ "version": "0.56.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
+ "qnn_dlc": {
7
+ "tool_versions": {
8
+ "qairt": "2.45.0.260326154327"
9
+ },
10
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.56.0/sam2-qnn_dlc-float.zip"
11
+ },
12
  "onnx": {
13
  "tool_versions": {
14
+ "qairt": "2.45.0.260326154327",
15
  "onnx_runtime": "1.25.0"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.56.0/sam2-onnx-float.zip"
18
  }
19
  }
20
  },
 
23
  "tflite": {
24
  "tool_versions": {
25
  "qairt": "2.45.0.260326154327",
26
+ "litert": "1.4.4"
27
  },
28
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.56.0/sam2-tflite-w8a8.zip"
 
 
 
 
 
 
29
  },
30
  "onnx": {
31
  "tool_versions": {
32
+ "qairt": "2.45.0.260326154327",
33
  "onnx_runtime": "1.25.0"
34
  },
35
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/sam2/releases/v0.56.0/sam2-onnx-w8a8.zip"
36
  }
37
  }
38
  }