qaihm-bot commited on
Commit
7776bbf
·
verified ·
1 Parent(s): a20ad3b

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

Files changed (2) hide show
  1. README.md +159 -140
  2. release_assets.json +10 -10
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: image-classification
15
  VIT is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
16
 
17
  This is based on the implementation of VIT found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/vision_transformer.py).
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/vit) 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
 
@@ -28,171 +28,190 @@ 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/vit/releases/v0.59.0/vit-onnx-float.zip)
32
- | ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.59.0/vit-onnx-w8a16.zip)
33
- | ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.59.0/vit-onnx-w8a8.zip)
34
- | ONNX | w8a8_mixed_int16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.59.0/vit-onnx-w8a8_mixed_int16.zip)
35
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.59.0/vit-qnn_dlc-float.zip)
36
- | QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.59.0/vit-qnn_dlc-w8a16.zip)
37
- | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.59.0/vit-qnn_dlc-w8a8.zip)
38
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.59.0/vit-tflite-float.zip)
39
- | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.59.0/vit-tflite-w8a8.zip)
40
 
41
  For more device-specific assets and performance metrics, visit **[VIT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/vit)**.
42
 
43
 
44
  ### Option 2: Export with Custom Configurations
45
 
46
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/vit) Python library to compile and export the model with your own:
47
  - Custom weights (e.g., fine-tuned checkpoints)
48
  - Custom input shapes
49
  - Target device and runtime configurations
50
 
51
  This option is ideal if you need to customize the model beyond the default configuration provided here.
52
 
53
- See our repository for [VIT on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/vit) for usage instructions.
54
 
55
  ## Model Details
56
 
57
  **Model Type:** Model_use_case.image_classification
58
 
59
  **Model Stats:**
60
- - Model checkpoint: Imagenet
61
  - Input resolution: 224x224
62
- - Number of parameters: 86.6M
63
  - Model size (float): 330 MB
64
  - Model size (w8a16): 86.2 MB
65
  - Model size (w8a8): 83.2 MB
 
66
 
67
  ## Performance Summary
68
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
69
  |---|---|---|---|---|---|---
70
- | VIT | ONNX | float | Snapdragon® X2 Elite | 3.051 ms | 2 - 2 MB | NPU
71
- | VIT | ONNX | float | Snapdragon® X Elite | 7.513 ms | 170 - 170 MB | NPU
72
- | VIT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.013 ms | 0 - 304 MB | NPU
73
- | VIT | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 12.197 ms | 1 - 283 MB | NPU
74
- | VIT | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.169 ms | 0 - 320 MB | NPU
75
- | VIT | ONNX | float | Qualcomm® QCS8450 | 12.197 ms | 1 - 283 MB | NPU
76
- | VIT | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 9.54 ms | 0 - 4 MB | NPU
77
- | VIT | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 7.513 ms | 170 - 170 MB | NPU
78
- | VIT | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 3.462 ms | 0 - 178 MB | NPU
79
- | VIT | ONNX | float | Snapdragon® 8 Elite Mobile | 3.462 ms | 0 - 178 MB | NPU
80
- | VIT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.811 ms | 0 - 161 MB | NPU
81
- | VIT | ONNX | w8a16 | Snapdragon® X2 Elite | 2.01 ms | 1 - 1 MB | NPU
82
- | VIT | ONNX | w8a16 | Snapdragon® X Elite | 4.759 ms | 86 - 86 MB | NPU
83
- | VIT | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.112 ms | 0 - 314 MB | NPU
84
- | VIT | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 6.433 ms | 0 - 316 MB | NPU
85
- | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 21.374 ms | 0 - 3 MB | NPU
86
- | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.568 ms | 0 - 3 MB | NPU
87
- | VIT | ONNX | w8a16 | Qualcomm® QCS8450 | 6.433 ms | 0 - 316 MB | NPU
88
- | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 4.451 ms | 0 - 3 MB | NPU
89
- | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 4.759 ms | 86 - 86 MB | NPU
90
- | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.444 ms | 0 - 261 MB | NPU
91
- | VIT | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 2.444 ms | 0 - 261 MB | NPU
92
- | VIT | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.794 ms | 0 - 269 MB | NPU
93
- | VIT | ONNX | w8a8 | Snapdragon® X2 Elite | 4.123 ms | 1 - 1 MB | NPU
94
- | VIT | ONNX | w8a8 | Snapdragon® X Elite | 9.747 ms | 85 - 85 MB | NPU
95
- | VIT | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.285 ms | 0 - 335 MB | NPU
96
- | VIT | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 13.151 ms | 0 - 340 MB | NPU
97
- | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 62.502 ms | 0 - 3 MB | NPU
98
- | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.377 ms | 0 - 106 MB | NPU
99
- | VIT | ONNX | w8a8 | Qualcomm® QCS8450 | 13.151 ms | 0 - 340 MB | NPU
100
- | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 8.112 ms | 0 - 3 MB | NPU
101
- | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 9.747 ms | 85 - 85 MB | NPU
102
- | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 5.407 ms | 0 - 239 MB | NPU
103
- | VIT | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 5.407 ms | 0 - 239 MB | NPU
104
- | VIT | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.515 ms | 0 - 246 MB | NPU
105
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 57.294 ms | 123 - 563 MB | NPU
106
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 70.971 ms | 118 - 121 MB | NPU
107
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ IQ-9075 | 84.027 ms | 125 - 131 MB | NPU
108
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ Q-8750 | 48.304 ms | 127 - 465 MB | NPU
109
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite Mobile | 48.304 ms | 127 - 465 MB | NPU
110
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 38.152 ms | 123 - 476 MB | NPU
111
- | VIT | QNN_DLC | float | Snapdragon® X2 Elite | 3.493 ms | 1 - 1 MB | NPU
112
- | VIT | QNN_DLC | float | Snapdragon® X Elite | 8.358 ms | 1 - 1 MB | NPU
113
- | VIT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.403 ms | 0 - 253 MB | NPU
114
- | VIT | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 13.034 ms | 1 - 229 MB | NPU
115
- | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 34.784 ms | 1 - 168 MB | NPU
116
- | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.703 ms | 1 - 400 MB | NPU
117
- | VIT | QNN_DLC | float | Qualcomm® SA8775P | 10.471 ms | 1 - 169 MB | NPU
118
- | VIT | QNN_DLC | float | Qualcomm® SA8650P | 10.471 ms | 1 - 169 MB | NPU
119
- | VIT | QNN_DLC | float | Qualcomm® SA8255P | 10.471 ms | 1 - 169 MB | NPU
120
- | VIT | QNN_DLC | float | Qualcomm® QCS8450 | 13.034 ms | 1 - 229 MB | NPU
121
- | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 10.169 ms | 3 - 5 MB | NPU
122
- | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 8.358 ms | 1 - 1 MB | NPU
123
- | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 3.751 ms | 1 - 157 MB | NPU
124
- | VIT | QNN_DLC | float | Qualcomm® SA7255P | 34.784 ms | 1 - 168 MB | NPU
125
- | VIT | QNN_DLC | float | Qualcomm® SA8295P | 12.942 ms | 1 - 145 MB | NPU
126
- | VIT | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 3.751 ms | 1 - 157 MB | NPU
127
- | VIT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.946 ms | 1 - 156 MB | NPU
128
- | VIT | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 3.596 ms | 0 - 0 MB | NPU
129
- | VIT | QNN_DLC | w8a16 | Snapdragon® X Elite | 8.219 ms | 0 - 0 MB | NPU
130
- | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.088 ms | 0 - 319 MB | NPU
131
- | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8275 | 17.354 ms | 0 - 258 MB | NPU
132
- | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.6 ms | 0 - 2 MB | NPU
133
- | VIT | QNN_DLC | w8a16 | Qualcomm® SA8775P | 7.778 ms | 0 - 259 MB | NPU
134
- | VIT | QNN_DLC | w8a16 | Qualcomm® SA8650P | 7.778 ms | 0 - 259 MB | NPU
135
- | VIT | QNN_DLC | w8a16 | Qualcomm® SA8255P | 7.778 ms | 0 - 259 MB | NPU
136
- | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 7.607 ms | 0 - 2 MB | NPU
137
- | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 8.219 ms | 0 - 0 MB | NPU
138
- | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 117.255 ms | 1 - 405 MB | NPU
139
- | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 12.881 ms | 0 - 403 MB | NPU
140
- | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.904 ms | 0 - 260 MB | NPU
141
- | VIT | QNN_DLC | w8a16 | Qualcomm® SA7255P | 17.354 ms | 0 - 258 MB | NPU
142
- | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 3.904 ms | 0 - 260 MB | NPU
143
- | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.867 ms | 0 - 279 MB | NPU
144
- | VIT | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 12.881 ms | 0 - 403 MB | NPU
145
- | VIT | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 4.448 ms | 0 - 0 MB | NPU
146
- | VIT | QNN_DLC | w8a8 | Snapdragon® X Elite | 10.216 ms | 0 - 0 MB | NPU
147
- | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.482 ms | 0 - 305 MB | NPU
148
- | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 13.207 ms | 0 - 314 MB | NPU
149
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 62.275 ms | 2 - 4 MB | NPU
150
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8275 | 28.467 ms | 0 - 201 MB | NPU
151
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.595 ms | 0 - 2 MB | NPU
152
- | VIT | QNN_DLC | w8a8 | Qualcomm® SA8775P | 8.67 ms | 0 - 203 MB | NPU
153
- | VIT | QNN_DLC | w8a8 | Qualcomm® SA8650P | 8.67 ms | 0 - 203 MB | NPU
154
- | VIT | QNN_DLC | w8a8 | Qualcomm® SA8255P | 8.67 ms | 0 - 203 MB | NPU
155
- | VIT | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 13.207 ms | 0 - 314 MB | NPU
156
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 8.366 ms | 0 - 2 MB | NPU
157
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 10.216 ms | 0 - 0 MB | NPU
158
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 212.341 ms | 0 - 496 MB | NPU
159
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 19.182 ms | 0 - 358 MB | NPU
160
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 5.385 ms | 0 - 203 MB | NPU
161
- | VIT | QNN_DLC | w8a8 | Qualcomm® SA7255P | 28.467 ms | 0 - 201 MB | NPU
162
- | VIT | QNN_DLC | w8a8 | Qualcomm® SA8295P | 15.601 ms | 0 - 211 MB | NPU
163
- | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 5.385 ms | 0 - 203 MB | NPU
164
- | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.546 ms | 0 - 213 MB | NPU
165
- | VIT | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 19.182 ms | 0 - 358 MB | NPU
166
- | VIT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.284 ms | 0 - 309 MB | NPU
167
- | VIT | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 12.955 ms | 0 - 288 MB | NPU
168
- | VIT | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 34.607 ms | 0 - 168 MB | NPU
169
- | VIT | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.235 ms | 0 - 3 MB | NPU
170
- | VIT | TFLITE | float | Qualcomm® SA8775P | 10.164 ms | 0 - 186 MB | NPU
171
- | VIT | TFLITE | float | Qualcomm® SA8650P | 10.164 ms | 0 - 186 MB | NPU
172
- | VIT | TFLITE | float | Qualcomm® SA8255P | 10.164 ms | 0 - 186 MB | NPU
173
- | VIT | TFLITE | float | Qualcomm® QCS8450 | 12.955 ms | 0 - 288 MB | NPU
174
- | VIT | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 9.841 ms | 0 - 174 MB | NPU
175
- | VIT | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 3.643 ms | 0 - 177 MB | NPU
176
- | VIT | TFLITE | float | Qualcomm® SA7255P | 34.607 ms | 0 - 168 MB | NPU
177
- | VIT | TFLITE | float | Qualcomm® SA8295P | 13.268 ms | 0 - 156 MB | NPU
178
- | VIT | TFLITE | float | Snapdragon® 8 Elite Mobile | 3.643 ms | 0 - 177 MB | NPU
179
- | VIT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.031 ms | 0 - 171 MB | NPU
180
- | VIT | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 8.697 ms | 0 - 488 MB | NPU
181
- | VIT | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 20.112 ms | 0 - 447 MB | NPU
182
- | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 139.29 ms | 1 - 100 MB | NPU
183
- | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 12.364 ms | 0 - 3 MB | NPU
184
- | VIT | TFLITE | w8a8 | Qualcomm® SA8775P | 12.214 ms | 0 - 388 MB | NPU
185
- | VIT | TFLITE | w8a8 | Qualcomm® SA8650P | 12.214 ms | 0 - 388 MB | NPU
186
- | VIT | TFLITE | w8a8 | Qualcomm® SA8255P | 12.214 ms | 0 - 388 MB | NPU
187
- | VIT | TFLITE | w8a8 | Qualcomm® QCS8450 | 20.112 ms | 0 - 447 MB | NPU
188
- | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 13.986 ms | 0 - 88 MB | NPU
189
- | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 199.781 ms | 2 - 282 MB | NPU
190
- | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 29.603 ms | 2 - 216 MB | NPU
191
- | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 6.93 ms | 0 - 379 MB | NPU
192
- | VIT | TFLITE | w8a8 | Qualcomm® SA8295P | 19.272 ms | 0 - 346 MB | NPU
193
- | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 6.93 ms | 0 - 379 MB | NPU
194
- | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 4.602 ms | 0 - 382 MB | NPU
195
- | VIT | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 29.603 ms | 2 - 216 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
196
 
197
  ## License
198
  * The license for the original implementation of VIT can be found
 
15
  VIT is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
16
 
17
  This is based on the implementation of VIT found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/vision_transformer.py).
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/vit) 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/vit/releases/v0.60.0/vit-onnx-float.zip)
32
+ | ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.60.0/vit-onnx-w8a16.zip)
33
+ | ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.60.0/vit-onnx-w8a8.zip)
34
+ | ONNX | w8a8_mixed_int16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.60.0/vit-onnx-w8a8_mixed_int16.zip)
35
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.60.0/vit-qnn_dlc-float.zip)
36
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.60.0/vit-qnn_dlc-w8a16.zip)
37
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.60.0/vit-qnn_dlc-w8a8.zip)
38
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.60.0/vit-tflite-float.zip)
39
+ | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.60.0/vit-tflite-w8a8.zip)
40
 
41
  For more device-specific assets and performance metrics, visit **[VIT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/vit)**.
42
 
43
 
44
  ### Option 2: Export with Custom Configurations
45
 
46
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/vit) Python library to compile and export the model with your own:
47
  - Custom weights (e.g., fine-tuned checkpoints)
48
  - Custom input shapes
49
  - Target device and runtime configurations
50
 
51
  This option is ideal if you need to customize the model beyond the default configuration provided here.
52
 
53
+ See our repository for [VIT on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/vit) for usage instructions.
54
 
55
  ## Model Details
56
 
57
  **Model Type:** Model_use_case.image_classification
58
 
59
  **Model Stats:**
 
60
  - Input resolution: 224x224
61
+ - Model checkpoint: Imagenet
62
  - Model size (float): 330 MB
63
  - Model size (w8a16): 86.2 MB
64
  - Model size (w8a8): 83.2 MB
65
+ - Number of parameters: 86.6M
66
 
67
  ## Performance Summary
68
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
69
  |---|---|---|---|---|---|---
70
+ | VIT | ONNX | float | Snapdragon® X2 Elite | 3.879 ms | 2 - 2 MB | NPU
71
+ | VIT | ONNX | float | Snapdragon® X Elite | 9.689 ms | 170 - 170 MB | NPU
72
+ | VIT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 6.47 ms | 1 - 302 MB | NPU
73
+ | VIT | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 14.173 ms | 1 - 299 MB | NPU
74
+ | VIT | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 12.961 ms | 0 - 4 MB | NPU
75
+ | VIT | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.235 ms | 0 - 194 MB | NPU
76
+ | VIT | ONNX | float | Qualcomm® QCS8450 | 14.173 ms | 1 - 299 MB | NPU
77
+ | VIT | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 12.177 ms | 1 - 4 MB | NPU
78
+ | VIT | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 9.689 ms | 170 - 170 MB | NPU
79
+ | VIT | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.585 ms | 0 - 170 MB | NPU
80
+ | VIT | ONNX | float | Snapdragon® 8 Elite Mobile | 4.585 ms | 0 - 170 MB | NPU
81
+ | VIT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.555 ms | 0 - 158 MB | NPU
82
+ | VIT | ONNX | w8a16 | Snapdragon® X2 Elite | 3.575 ms | 1 - 1 MB | NPU
83
+ | VIT | ONNX | w8a16 | Snapdragon® X Elite | 8.191 ms | 85 - 85 MB | NPU
84
+ | VIT | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.329 ms | 0 - 321 MB | NPU
85
+ | VIT | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 9.323 ms | 0 - 322 MB | NPU
86
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 38.302 ms | 0 - 3 MB | NPU
87
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 7.455 ms | 0 - 4 MB | NPU
88
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.812 ms | 0 - 98 MB | NPU
89
+ | VIT | ONNX | w8a16 | Qualcomm® QCS8450 | 9.323 ms | 0 - 322 MB | NPU
90
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 7.945 ms | 0 - 3 MB | NPU
91
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 8.191 ms | 85 - 85 MB | NPU
92
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 109.442 ms | 1 - 466 MB | NPU
93
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 9.687 ms | 0 - 396 MB | NPU
94
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 4.067 ms | 0 - 264 MB | NPU
95
+ | VIT | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 4.067 ms | 0 - 264 MB | NPU
96
+ | VIT | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.091 ms | 0 - 268 MB | NPU
97
+ | VIT | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 9.687 ms | 0 - 396 MB | NPU
98
+ | VIT | ONNX | w8a8 | Snapdragon® X2 Elite | 4.94 ms | 1 - 1 MB | NPU
99
+ | VIT | ONNX | w8a8 | Snapdragon® X Elite | 10.92 ms | 86 - 86 MB | NPU
100
+ | VIT | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 7.063 ms | 0 - 334 MB | NPU
101
+ | VIT | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 15.238 ms | 0 - 342 MB | NPU
102
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 73.486 ms | 0 - 3 MB | NPU
103
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 10.235 ms | 0 - 4 MB | NPU
104
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.489 ms | 0 - 99 MB | NPU
105
+ | VIT | ONNX | w8a8 | Qualcomm® QCS8450 | 15.238 ms | 0 - 342 MB | NPU
106
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 9.894 ms | 0 - 3 MB | NPU
107
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 10.92 ms | 86 - 86 MB | NPU
108
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 250.726 ms | 0 - 504 MB | NPU
109
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 18.89 ms | 0 - 338 MB | NPU
110
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 5.975 ms | 0 - 213 MB | NPU
111
+ | VIT | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 5.975 ms | 0 - 213 MB | NPU
112
+ | VIT | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 4.298 ms | 0 - 221 MB | NPU
113
+ | VIT | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 18.89 ms | 0 - 338 MB | NPU
114
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 15.939 ms | 19 - 501 MB | NPU
115
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Gen 1 Mobile | 31.211 ms | 16 - 487 MB | NPU
116
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ IQ-8275 | 24.165 ms | 16 - 19 MB | NPU
117
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 21.795 ms | 16 - 20 MB | NPU
118
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCS8450 | 31.211 ms | 16 - 487 MB | NPU
119
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ IQ-9075 | 25.143 ms | 17 - 19 MB | NPU
120
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ Q-8750 | 13.521 ms | 17 - 371 MB | NPU
121
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite Mobile | 13.521 ms | 17 - 371 MB | NPU
122
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 10.058 ms | 19 - 384 MB | NPU
123
+ | VIT | QNN_DLC | float | Snapdragon® X2 Elite | 5.755 ms | 1 - 1 MB | NPU
124
+ | VIT | QNN_DLC | float | Snapdragon® X Elite | 12.644 ms | 1 - 1 MB | NPU
125
+ | VIT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.263 ms | 0 - 305 MB | NPU
126
+ | VIT | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 15.437 ms | 0 - 303 MB | NPU
127
+ | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 14.903 ms | 1 - 4 MB | NPU
128
+ | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 42.281 ms | 1 - 168 MB | NPU
129
+ | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.86 ms | 1 - 2 MB | NPU
130
+ | VIT | QNN_DLC | float | Qualcomm® SA8775P | 14.623 ms | 1 - 169 MB | NPU
131
+ | VIT | QNN_DLC | float | Qualcomm® SA8650P | 14.623 ms | 1 - 169 MB | NPU
132
+ | VIT | QNN_DLC | float | Qualcomm® SA8255P | 14.623 ms | 1 - 169 MB | NPU
133
+ | VIT | QNN_DLC | float | Qualcomm® QCS8450 | 15.437 ms | 0 - 303 MB | NPU
134
+ | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 17.975 ms | 1 - 3 MB | NPU
135
+ | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 12.644 ms | 1 - 1 MB | NPU
136
+ | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 6.18 ms | 1 - 173 MB | NPU
137
+ | VIT | QNN_DLC | float | Qualcomm® SA7255P | 42.281 ms | 1 - 168 MB | NPU
138
+ | VIT | QNN_DLC | float | Qualcomm® SA8295P | 16.193 ms | 1 - 165 MB | NPU
139
+ | VIT | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 6.18 ms | 1 - 173 MB | NPU
140
+ | VIT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.184 ms | 1 - 158 MB | NPU
141
+ | VIT | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 5.813 ms | 0 - 0 MB | NPU
142
+ | VIT | QNN_DLC | w8a16 | Snapdragon® X Elite | 13.177 ms | 0 - 0 MB | NPU
143
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 8.736 ms | 0 - 337 MB | NPU
144
+ | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 11.837 ms | 0 - 3 MB | NPU
145
+ | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 28.674 ms | 0 - 276 MB | NPU
146
+ | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 12.39 ms | 0 - 2 MB | NPU
147
+ | VIT | QNN_DLC | w8a16 | Qualcomm® SA8775P | 12.786 ms | 0 - 278 MB | NPU
148
+ | VIT | QNN_DLC | w8a16 | Qualcomm® SA8650P | 12.786 ms | 0 - 278 MB | NPU
149
+ | VIT | QNN_DLC | w8a16 | Qualcomm® SA8255P | 12.786 ms | 0 - 278 MB | NPU
150
+ | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 12.805 ms | 0 - 2 MB | NPU
151
+ | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 13.177 ms | 0 - 0 MB | NPU
152
+ | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 140.385 ms | 0 - 477 MB | NPU
153
+ | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 18.295 ms | 0 - 427 MB | NPU
154
+ | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 6.322 ms | 0 - 277 MB | NPU
155
+ | VIT | QNN_DLC | w8a16 | Qualcomm® SA7255P | 28.674 ms | 0 - 276 MB | NPU
156
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 6.322 ms | 0 - 277 MB | NPU
157
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 4.777 ms | 0 - 280 MB | NPU
158
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 18.295 ms | 0 - 427 MB | NPU
159
+ | VIT | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 5.373 ms | 0 - 0 MB | NPU
160
+ | VIT | QNN_DLC | w8a8 | Snapdragon® X Elite | 11.376 ms | 1 - 1 MB | NPU
161
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 7.045 ms | 0 - 322 MB | NPU
162
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 14.712 ms | 0 - 335 MB | NPU
163
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 73.62 ms | 0 - 2 MB | NPU
164
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 10.152 ms | 0 - 3 MB | NPU
165
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 31.163 ms | 0 - 202 MB | NPU
166
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.635 ms | 0 - 11 MB | NPU
167
+ | VIT | QNN_DLC | w8a8 | Qualcomm® SA8775P | 10.359 ms | 0 - 202 MB | NPU
168
+ | VIT | QNN_DLC | w8a8 | Qualcomm® SA8650P | 10.359 ms | 0 - 202 MB | NPU
169
+ | VIT | QNN_DLC | w8a8 | Qualcomm® SA8255P | 10.359 ms | 0 - 202 MB | NPU
170
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 14.712 ms | 0 - 335 MB | NPU
171
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 10.045 ms | 2 - 4 MB | NPU
172
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 11.376 ms | 1 - 1 MB | NPU
173
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 251.718 ms | 0 - 508 MB | NPU
174
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 18.693 ms | 0 - 334 MB | NPU
175
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 6.011 ms | 0 - 203 MB | NPU
176
+ | VIT | QNN_DLC | w8a8 | Qualcomm® SA7255P | 31.163 ms | 0 - 202 MB | NPU
177
+ | VIT | QNN_DLC | w8a8 | Qualcomm® SA8295P | 17.47 ms | 0 - 211 MB | NPU
178
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 6.011 ms | 0 - 203 MB | NPU
179
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 4.339 ms | 0 - 211 MB | NPU
180
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 18.693 ms | 0 - 334 MB | NPU
181
+ | VIT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 6.798 ms | 0 - 302 MB | NPU
182
+ | VIT | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 15.253 ms | 0 - 300 MB | NPU
183
+ | VIT | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 13.013 ms | 0 - 173 MB | NPU
184
+ | VIT | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 38.633 ms | 0 - 168 MB | NPU
185
+ | VIT | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.349 ms | 0 - 3 MB | NPU
186
+ | VIT | TFLITE | float | Qualcomm® SA8775P | 12.52 ms | 0 - 170 MB | NPU
187
+ | VIT | TFLITE | float | Qualcomm® SA8650P | 12.52 ms | 0 - 170 MB | NPU
188
+ | VIT | TFLITE | float | Qualcomm® SA8255P | 12.52 ms | 0 - 170 MB | NPU
189
+ | VIT | TFLITE | float | Qualcomm® QCS8450 | 15.253 ms | 0 - 300 MB | NPU
190
+ | VIT | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 12.582 ms | 0 - 173 MB | NPU
191
+ | VIT | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.822 ms | 0 - 176 MB | NPU
192
+ | VIT | TFLITE | float | Qualcomm® SA7255P | 38.633 ms | 0 - 168 MB | NPU
193
+ | VIT | TFLITE | float | Qualcomm® SA8295P | 15.651 ms | 0 - 162 MB | NPU
194
+ | VIT | TFLITE | float | Snapdragon® 8 Elite Mobile | 4.822 ms | 0 - 176 MB | NPU
195
+ | VIT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.737 ms | 0 - 166 MB | NPU
196
+ | VIT | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 9.505 ms | 0 - 474 MB | NPU
197
+ | VIT | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 21.726 ms | 0 - 466 MB | NPU
198
+ | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 147.572 ms | 1 - 100 MB | NPU
199
+ | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 13.645 ms | 0 - 87 MB | NPU
200
+ | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 37.336 ms | 0 - 341 MB | NPU
201
+ | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 13.797 ms | 0 - 2 MB | NPU
202
+ | VIT | TFLITE | w8a8 | Qualcomm® SA8775P | 13.795 ms | 0 - 342 MB | NPU
203
+ | VIT | TFLITE | w8a8 | Qualcomm® SA8650P | 13.795 ms | 0 - 342 MB | NPU
204
+ | VIT | TFLITE | w8a8 | Qualcomm® SA8255P | 13.795 ms | 0 - 342 MB | NPU
205
+ | VIT | TFLITE | w8a8 | Qualcomm® QCS8450 | 21.726 ms | 0 - 466 MB | NPU
206
+ | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 14.268 ms | 0 - 87 MB | NPU
207
+ | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 203.327 ms | 1 - 259 MB | NPU
208
+ | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 30.996 ms | 1 - 187 MB | NPU
209
+ | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 7.791 ms | 0 - 344 MB | NPU
210
+ | VIT | TFLITE | w8a8 | Qualcomm® SA7255P | 37.336 ms | 0 - 341 MB | NPU
211
+ | VIT | TFLITE | w8a8 | Qualcomm® SA8295P | 21.403 ms | 0 - 335 MB | NPU
212
+ | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 7.791 ms | 0 - 344 MB | NPU
213
+ | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 5.523 ms | 0 - 350 MB | NPU
214
+ | VIT | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 30.996 ms | 1 - 187 MB | NPU
215
 
216
  ## License
217
  * The license for the original implementation of VIT 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/vit/releases/v0.59.0/vit-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/vit/releases/v0.59.0/vit-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/vit/releases/v0.59.0/vit-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -31,13 +31,13 @@
31
  "qairt": "2.45.0.260326154327",
32
  "onnx_runtime": "1.27.1"
33
  },
34
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.59.0/vit-onnx-w8a16.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
  "qairt": "2.45.0.260326154327"
39
  },
40
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.59.0/vit-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  },
@@ -48,19 +48,19 @@
48
  "qairt": "2.45.0.260326154327",
49
  "onnx_runtime": "1.27.1"
50
  },
51
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.59.0/vit-onnx-w8a8.zip"
52
  },
53
  "qnn_dlc": {
54
  "tool_versions": {
55
  "qairt": "2.45.0.260326154327"
56
  },
57
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.59.0/vit-qnn_dlc-w8a8.zip"
58
  },
59
  "tflite": {
60
  "tool_versions": {
61
  "qairt": "2.45.0.260326154327"
62
  },
63
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.59.0/vit-tflite-w8a8.zip"
64
  }
65
  }
66
  },
@@ -71,7 +71,7 @@
71
  "qairt": "2.45.0.260326154327",
72
  "onnx_runtime": "1.27.1"
73
  },
74
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.59.0/vit-onnx-w8a8_mixed_int16.zip"
75
  }
76
  }
77
  }
 
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/vit/releases/v0.60.0/vit-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/vit/releases/v0.60.0/vit-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/vit/releases/v0.60.0/vit-tflite-float.zip"
24
  }
25
  }
26
  },
 
31
  "qairt": "2.45.0.260326154327",
32
  "onnx_runtime": "1.27.1"
33
  },
34
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.60.0/vit-onnx-w8a16.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
  "qairt": "2.45.0.260326154327"
39
  },
40
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.60.0/vit-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  },
 
48
  "qairt": "2.45.0.260326154327",
49
  "onnx_runtime": "1.27.1"
50
  },
51
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.60.0/vit-onnx-w8a8.zip"
52
  },
53
  "qnn_dlc": {
54
  "tool_versions": {
55
  "qairt": "2.45.0.260326154327"
56
  },
57
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.60.0/vit-qnn_dlc-w8a8.zip"
58
  },
59
  "tflite": {
60
  "tool_versions": {
61
  "qairt": "2.45.0.260326154327"
62
  },
63
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.60.0/vit-tflite-w8a8.zip"
64
  }
65
  }
66
  },
 
71
  "qairt": "2.45.0.260326154327",
72
  "onnx_runtime": "1.27.1"
73
  },
74
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.60.0/vit-onnx-w8a8_mixed_int16.zip"
75
  }
76
  }
77
  }