qaihm-bot commited on
Commit
027973a
·
verified ·
1 Parent(s): 9b09141

See https://github.com/quic/ai-hub-models/releases/v0.47.0 for changelog.

Files changed (1) hide show
  1. README.md +70 -64
README.md CHANGED
@@ -28,14 +28,14 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | ONNX | float | Universal | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/segformer_base/releases/v0.46.0/segformer_base-onnx-float.zip)
32
- | ONNX | w8a16 | Universal | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/segformer_base/releases/v0.46.0/segformer_base-onnx-w8a16.zip)
33
- | ONNX | w8a8 | Universal | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/segformer_base/releases/v0.46.0/segformer_base-onnx-w8a8.zip)
34
- | QNN_DLC | float | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/segformer_base/releases/v0.46.0/segformer_base-qnn_dlc-float.zip)
35
- | QNN_DLC | w8a16 | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/segformer_base/releases/v0.46.0/segformer_base-qnn_dlc-w8a16.zip)
36
- | QNN_DLC | w8a8 | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/segformer_base/releases/v0.46.0/segformer_base-qnn_dlc-w8a8.zip)
37
- | TFLITE | float | Universal | QAIRT 2.42, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/segformer_base/releases/v0.46.0/segformer_base-tflite-float.zip)
38
- | TFLITE | w8a8 | Universal | QAIRT 2.42, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/segformer_base/releases/v0.46.0/segformer_base-tflite-w8a8.zip)
39
 
40
  For more device-specific assets and performance metrics, visit **[Segformer-Base on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/segformer_base)**.
41
 
@@ -67,62 +67,68 @@ See our repository for [Segformer-Base on GitHub](https://github.com/quic/ai-hub
67
  ## Performance Summary
68
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
69
  |---|---|---|---|---|---|---
70
- | Segformer-Base | ONNX | float | Snapdragon® X Elite | 112.756 ms | 33 - 33 MB | NPU
71
- | Segformer-Base | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 84.305 ms | 24 - 201 MB | NPU
72
- | Segformer-Base | ONNX | float | Qualcomm® QCS8550 (Proxy) | 108.769 ms | 19 - 28 MB | NPU
73
- | Segformer-Base | ONNX | float | Qualcomm® QCS9075 | 120.239 ms | 23 - 26 MB | NPU
74
- | Segformer-Base | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 74.648 ms | 21 - 160 MB | NPU
75
- | Segformer-Base | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 73.716 ms | 27 - 175 MB | NPU
76
- | Segformer-Base | ONNX | w8a16 | Snapdragon® X Elite | 51.865 ms | 131 - 131 MB | NPU
77
- | Segformer-Base | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 49.215 ms | 90 - 271 MB | NPU
78
- | Segformer-Base | ONNX | w8a16 | Qualcomm® QCS6490 | 841.672 ms | 379 - 385 MB | CPU
79
- | Segformer-Base | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 61.921 ms | 83 - 87 MB | NPU
80
- | Segformer-Base | ONNX | w8a16 | Qualcomm® QCS9075 | 68.104 ms | 89 - 92 MB | NPU
81
- | Segformer-Base | ONNX | w8a16 | Qualcomm® QCM6690 | 574.842 ms | 324 - 334 MB | CPU
82
- | Segformer-Base | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 45.505 ms | 90 - 228 MB | NPU
83
- | Segformer-Base | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 412.489 ms | 323 - 333 MB | CPU
84
- | Segformer-Base | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 39.672 ms | 90 - 227 MB | NPU
85
- | Segformer-Base | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 42.463 ms | 58 - 219 MB | NPU
86
- | Segformer-Base | ONNX | w8a8 | Qualcomm® QCS6490 | 352.803 ms | 200 - 207 MB | CPU
87
- | Segformer-Base | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 51.706 ms | 54 - 59 MB | NPU
88
- | Segformer-Base | ONNX | w8a8 | Qualcomm® QCS9075 | 56.372 ms | 58 - 61 MB | NPU
89
- | Segformer-Base | ONNX | w8a8 | Qualcomm® QCM6690 | 214.217 ms | 203 - 213 MB | CPU
90
- | Segformer-Base | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 39.85 ms | 57 - 181 MB | NPU
91
- | Segformer-Base | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 191.097 ms | 201 - 211 MB | CPU
92
- | Segformer-Base | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 34.78 ms | 58 - 187 MB | NPU
93
- | Segformer-Base | QNN_DLC | float | Snapdragon® X Elite | 114.563 ms | 3 - 3 MB | NPU
94
- | Segformer-Base | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 83.817 ms | 2 - 228 MB | NPU
95
- | Segformer-Base | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 214.645 ms | 1 - 183 MB | NPU
96
- | Segformer-Base | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 110.097 ms | 3 - 5 MB | NPU
97
- | Segformer-Base | QNN_DLC | float | Qualcomm® SA8775P | 472.472 ms | 1 - 189 MB | NPU
98
- | Segformer-Base | QNN_DLC | float | Qualcomm® QCS9075 | 113.605 ms | 3 - 17 MB | NPU
99
- | Segformer-Base | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 121.904 ms | 2 - 225 MB | NPU
100
- | Segformer-Base | QNN_DLC | float | Qualcomm® SA7255P | 214.645 ms | 1 - 183 MB | NPU
101
- | Segformer-Base | QNN_DLC | float | Qualcomm® SA8295P | 122.206 ms | 3 - 181 MB | NPU
102
- | Segformer-Base | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 75.008 ms | 3 - 197 MB | NPU
103
- | Segformer-Base | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 74.055 ms | 3 - 195 MB | NPU
104
- | Segformer-Base | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 83.556 ms | 9 - 241 MB | NPU
105
- | Segformer-Base | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 172.201 ms | 10 - 39 MB | GPU
106
- | Segformer-Base | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 110.21 ms | 9 - 12 MB | NPU
107
- | Segformer-Base | TFLITE | float | Qualcomm® SA8775P | 110.706 ms | 0 - 193 MB | NPU
108
- | Segformer-Base | TFLITE | float | Qualcomm® QCS9075 | 114.107 ms | 8 - 30 MB | NPU
109
- | Segformer-Base | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 122.524 ms | 9 - 235 MB | NPU
110
- | Segformer-Base | TFLITE | float | Qualcomm® SA7255P | 172.201 ms | 10 - 39 MB | GPU
111
- | Segformer-Base | TFLITE | float | Qualcomm® SA8295P | 122.282 ms | 10 - 198 MB | NPU
112
- | Segformer-Base | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 74.86 ms | 9 - 198 MB | NPU
113
- | Segformer-Base | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 74.212 ms | 14 - 213 MB | NPU
114
- | Segformer-Base | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 10.304 ms | 1 - 214 MB | NPU
115
- | Segformer-Base | TFLITE | w8a8 | Qualcomm® QCS6490 | 134.981 ms | 13 - 48 MB | NPU
116
- | Segformer-Base | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 170.87 ms | 15 - 45 MB | GPU
117
- | Segformer-Base | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 14.171 ms | 2 - 5 MB | NPU
118
- | Segformer-Base | TFLITE | w8a8 | Qualcomm® SA8775P | 14.948 ms | 2 - 180 MB | NPU
119
- | Segformer-Base | TFLITE | w8a8 | Qualcomm® QCS9075 | 12.574 ms | 2 - 12 MB | NPU
120
- | Segformer-Base | TFLITE | w8a8 | Qualcomm® QCM6690 | 148.583 ms | 13 - 190 MB | NPU
121
- | Segformer-Base | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 18.904 ms | 2 - 213 MB | NPU
122
- | Segformer-Base | TFLITE | w8a8 | Qualcomm® SA7255P | 170.87 ms | 15 - 45 MB | GPU
123
- | Segformer-Base | TFLITE | w8a8 | Qualcomm® SA8295P | 17.819 ms | 2 - 184 MB | NPU
124
- | Segformer-Base | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 7.856 ms | 2 - 173 MB | NPU
125
- | Segformer-Base | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 7.214 ms | 2 - 188 MB | NPU
 
 
 
 
 
 
126
 
127
  ## License
128
  * The license for the original implementation of Segformer-Base can be found
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | 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/segformer_base/releases/v0.47.0/segformer_base-onnx-float.zip)
32
+ | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/segformer_base/releases/v0.47.0/segformer_base-onnx-w8a16.zip)
33
+ | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/segformer_base/releases/v0.47.0/segformer_base-onnx-w8a8.zip)
34
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/segformer_base/releases/v0.47.0/segformer_base-qnn_dlc-float.zip)
35
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/segformer_base/releases/v0.47.0/segformer_base-qnn_dlc-w8a16.zip)
36
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/segformer_base/releases/v0.47.0/segformer_base-qnn_dlc-w8a8.zip)
37
+ | 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/segformer_base/releases/v0.47.0/segformer_base-tflite-float.zip)
38
+ | TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/segformer_base/releases/v0.47.0/segformer_base-tflite-w8a8.zip)
39
 
40
  For more device-specific assets and performance metrics, visit **[Segformer-Base on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/segformer_base)**.
41
 
 
67
  ## Performance Summary
68
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
69
  |---|---|---|---|---|---|---
70
+ | Segformer-Base | ONNX | float | Snapdragon® X Elite | 112.193 ms | 33 - 33 MB | NPU
71
+ | Segformer-Base | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 82.391 ms | 27 - 256 MB | NPU
72
+ | Segformer-Base | ONNX | float | Qualcomm® QCS8550 (Proxy) | 107.912 ms | 9 - 19 MB | NPU
73
+ | Segformer-Base | ONNX | float | Qualcomm® QCS9075 | 115.066 ms | 23 - 26 MB | NPU
74
+ | Segformer-Base | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 74.136 ms | 23 - 216 MB | NPU
75
+ | Segformer-Base | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 74.063 ms | 24 - 220 MB | NPU
76
+ | Segformer-Base | ONNX | float | Snapdragon® X2 Elite | 72.6 ms | 34 - 34 MB | NPU
77
+ | Segformer-Base | ONNX | w8a16 | Snapdragon® X Elite | 15.32 ms | 18 - 18 MB | NPU
78
+ | Segformer-Base | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 10.398 ms | 14 - 257 MB | NPU
79
+ | Segformer-Base | ONNX | w8a16 | Qualcomm® QCS6490 | 731.309 ms | 381 - 387 MB | CPU
80
+ | Segformer-Base | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 14.805 ms | 9 - 16 MB | NPU
81
+ | Segformer-Base | ONNX | w8a16 | Qualcomm® QCS9075 | 20.672 ms | 14 - 16 MB | NPU
82
+ | Segformer-Base | ONNX | w8a16 | Qualcomm® QCM6690 | 351.402 ms | 328 - 338 MB | CPU
83
+ | Segformer-Base | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 8.287 ms | 13 - 216 MB | NPU
84
+ | Segformer-Base | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 318.756 ms | 329 - 340 MB | CPU
85
+ | Segformer-Base | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 6.818 ms | 13 - 221 MB | NPU
86
+ | Segformer-Base | ONNX | w8a16 | Snapdragon® X2 Elite | 6.823 ms | 16 - 16 MB | NPU
87
+ | Segformer-Base | ONNX | w8a8 | Snapdragon® X Elite | 11.663 ms | 9 - 9 MB | NPU
88
+ | Segformer-Base | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 7.605 ms | 7 - 230 MB | NPU
89
+ | Segformer-Base | ONNX | w8a8 | Qualcomm® QCS6490 | 272.285 ms | 194 - 202 MB | CPU
90
+ | Segformer-Base | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 10.992 ms | 5 - 12 MB | NPU
91
+ | Segformer-Base | ONNX | w8a8 | Qualcomm® QCS9075 | 11.914 ms | 8 - 10 MB | NPU
92
+ | Segformer-Base | ONNX | w8a8 | Qualcomm® QCM6690 | 174.574 ms | 195 - 207 MB | CPU
93
+ | Segformer-Base | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 5.553 ms | 6 - 203 MB | NPU
94
+ | Segformer-Base | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 156.824 ms | 192 - 203 MB | CPU
95
+ | Segformer-Base | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 4.593 ms | 6 - 205 MB | NPU
96
+ | Segformer-Base | ONNX | w8a8 | Snapdragon® X2 Elite | 4.57 ms | 3 - 3 MB | NPU
97
+ | Segformer-Base | QNN_DLC | float | Snapdragon® X Elite | 114.454 ms | 3 - 3 MB | NPU
98
+ | Segformer-Base | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 83.435 ms | 3 - 230 MB | NPU
99
+ | Segformer-Base | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 214.728 ms | 0 - 182 MB | NPU
100
+ | Segformer-Base | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 110.199 ms | 3 - 5 MB | NPU
101
+ | Segformer-Base | QNN_DLC | float | Qualcomm® SA8775P | 472.291 ms | 1 - 188 MB | NPU
102
+ | Segformer-Base | QNN_DLC | float | Qualcomm® QCS9075 | 113.297 ms | 3 - 17 MB | NPU
103
+ | Segformer-Base | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 121.922 ms | 3 - 227 MB | NPU
104
+ | Segformer-Base | QNN_DLC | float | Qualcomm® SA7255P | 214.728 ms | 0 - 182 MB | NPU
105
+ | Segformer-Base | QNN_DLC | float | Qualcomm® SA8295P | 122.22 ms | 0 - 179 MB | NPU
106
+ | Segformer-Base | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 74.944 ms | 0 - 194 MB | NPU
107
+ | Segformer-Base | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 73.799 ms | 3 - 196 MB | NPU
108
+ | Segformer-Base | QNN_DLC | float | Snapdragon® X2 Elite | 73.2 ms | 3 - 3 MB | NPU
109
+ | Segformer-Base | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 83.768 ms | 8 - 235 MB | NPU
110
+ | Segformer-Base | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 214.951 ms | 0 - 183 MB | NPU
111
+ | Segformer-Base | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 110.231 ms | 9 - 12 MB | NPU
112
+ | Segformer-Base | TFLITE | float | Qualcomm® SA8775P | 100.963 ms | 9 - 198 MB | NPU
113
+ | Segformer-Base | TFLITE | float | Qualcomm® QCS9075 | 113.533 ms | 8 - 30 MB | NPU
114
+ | Segformer-Base | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 122.071 ms | 9 - 233 MB | NPU
115
+ | Segformer-Base | TFLITE | float | Qualcomm® SA7255P | 214.951 ms | 0 - 183 MB | NPU
116
+ | Segformer-Base | TFLITE | float | Qualcomm® SA8295P | 122.249 ms | 2 - 180 MB | NPU
117
+ | Segformer-Base | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 74.946 ms | 9 - 205 MB | NPU
118
+ | Segformer-Base | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 74.206 ms | 14 - 211 MB | NPU
119
+ | Segformer-Base | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 10.246 ms | 2 - 214 MB | NPU
120
+ | Segformer-Base | TFLITE | w8a8 | Qualcomm® QCS6490 | 137.007 ms | 15 - 50 MB | NPU
121
+ | Segformer-Base | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 23.183 ms | 2 - 175 MB | NPU
122
+ | Segformer-Base | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 14.087 ms | 2 - 70 MB | NPU
123
+ | Segformer-Base | TFLITE | w8a8 | Qualcomm® SA8775P | 14.446 ms | 2 - 177 MB | NPU
124
+ | Segformer-Base | TFLITE | w8a8 | Qualcomm® QCS9075 | 12.816 ms | 1 - 11 MB | NPU
125
+ | Segformer-Base | TFLITE | w8a8 | Qualcomm® QCM6690 | 147.706 ms | 15 - 178 MB | NPU
126
+ | Segformer-Base | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 18.802 ms | 2 - 213 MB | NPU
127
+ | Segformer-Base | TFLITE | w8a8 | Qualcomm® SA7255P | 23.183 ms | 2 - 175 MB | NPU
128
+ | Segformer-Base | TFLITE | w8a8 | Qualcomm® SA8295P | 17.867 ms | 2 - 179 MB | NPU
129
+ | Segformer-Base | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 7.834 ms | 0 - 173 MB | NPU
130
+ | Segformer-Base | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 46.507 ms | 9 - 169 MB | NPU
131
+ | Segformer-Base | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 7.201 ms | 0 - 179 MB | NPU
132
 
133
  ## License
134
  * The license for the original implementation of Segformer-Base can be found