Image Classification
PyTorch
backbone
android
qaihm-bot commited on
Commit
954bf92
·
verified ·
1 Parent(s): bcfc306

See https://github.com/qualcomm/ai-hub-models/releases/v0.63.0 for changelog.

Files changed (2) hide show
  1. README.md +159 -169
  2. release_assets.json +21 -21
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/v0.62.2/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
 
@@ -28,30 +28,30 @@ 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/v0.62.2/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/v0.62.2/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/v0.62.2/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/v0.62.2/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/v0.62.2/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/v0.62.2/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/v0.62.2/vit-qnn_dlc-w8a8.zip)
38
- | QNN_DLC | w8a8_mixed_int16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.62.2/vit-qnn_dlc-w8a8_mixed_int16.zip)
39
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.62.2/vit-tflite-float.zip)
40
- | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.62.2/vit-tflite-w8a8.zip)
41
 
42
  For more device-specific assets and performance metrics, visit **[VIT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/vit)**.
43
 
44
 
45
  ### Option 2: Export with Custom Configurations
46
 
47
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/vit) Python library to compile and export the model with your own:
48
  - Custom weights (e.g., fine-tuned checkpoints)
49
  - Custom input shapes
50
  - Target device and runtime configurations
51
 
52
  This option is ideal if you need to customize the model beyond the default configuration provided here.
53
 
54
- See our repository for [VIT on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/vit) for usage instructions.
55
 
56
  ## Model Details
57
 
@@ -68,166 +68,156 @@ See our repository for [VIT on GitHub](https://github.com/qualcomm/ai-hub-models
68
  ## Performance Summary
69
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
70
  |---|---|---|---|---|---|---
71
- | VIT | ONNX | float | Snapdragon® X2 Elite | 3.86 ms | 2 - 2 MB | NPU
72
- | VIT | ONNX | float | Snapdragon® X Elite | 9.709 ms | 170 - 170 MB | NPU
73
- | VIT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 6.469 ms | 0 - 300 MB | NPU
74
- | VIT | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 14.097 ms | 0 - 297 MB | NPU
75
- | VIT | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 12.78 ms | 0 - 4 MB | NPU
76
- | VIT | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.245 ms | 0 - 193 MB | NPU
77
- | VIT | ONNX | float | Qualcomm® QCS8450 | 14.097 ms | 0 - 297 MB | NPU
78
- | VIT | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 11.949 ms | 1 - 4 MB | NPU
79
- | VIT | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 9.709 ms | 170 - 170 MB | NPU
80
- | VIT | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.592 ms | 0 - 170 MB | NPU
81
- | VIT | ONNX | float | Snapdragon® 8 Elite Mobile | 4.592 ms | 0 - 170 MB | NPU
82
- | VIT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.544 ms | 0 - 158 MB | NPU
83
- | VIT | ONNX | w8a16 | Snapdragon® X2 Elite | 3.572 ms | 1 - 1 MB | NPU
84
- | VIT | ONNX | w8a16 | Snapdragon® X Elite | 8.19 ms | 86 - 86 MB | NPU
85
- | VIT | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.343 ms | 0 - 320 MB | NPU
86
- | VIT | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 9.332 ms | 0 - 322 MB | NPU
87
- | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 38.497 ms | 0 - 3 MB | NPU
88
- | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 7.445 ms | 0 - 4 MB | NPU
89
- | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.795 ms | 0 - 3 MB | NPU
90
- | VIT | ONNX | w8a16 | Qualcomm® QCS8450 | 9.332 ms | 0 - 322 MB | NPU
91
- | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 7.927 ms | 0 - 3 MB | NPU
92
- | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 8.19 ms | 86 - 86 MB | NPU
93
- | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 112.719 ms | 0 - 464 MB | NPU
94
- | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 9.696 ms | 0 - 403 MB | NPU
95
- | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 4.081 ms | 0 - 263 MB | NPU
96
- | VIT | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 4.081 ms | 0 - 263 MB | NPU
97
- | VIT | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.091 ms | 0 - 267 MB | NPU
98
- | VIT | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 9.696 ms | 0 - 403 MB | NPU
99
- | VIT | ONNX | w8a8 | Snapdragon® X2 Elite | 15.354 ms | 1 - 1 MB | NPU
100
- | VIT | ONNX | w8a8 | Snapdragon® X Elite | 10.946 ms | 86 - 86 MB | NPU
101
- | VIT | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 7.055 ms | 0 - 335 MB | NPU
102
- | VIT | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 14.568 ms | 0 - 342 MB | NPU
103
- | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 74.031 ms | 0 - 3 MB | NPU
104
- | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 10.17 ms | 0 - 4 MB | NPU
105
- | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.468 ms | 0 - 98 MB | NPU
106
- | VIT | ONNX | w8a8 | Qualcomm® QCS8450 | 14.568 ms | 0 - 342 MB | NPU
107
- | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 9.903 ms | 0 - 3 MB | NPU
108
- | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 10.946 ms | 86 - 86 MB | NPU
109
- | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 212.002 ms | 0 - 505 MB | NPU
110
- | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 18.888 ms | 0 - 338 MB | NPU
111
- | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 5.957 ms | 0 - 211 MB | NPU
112
- | VIT | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 5.957 ms | 0 - 211 MB | NPU
113
- | VIT | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 4.297 ms | 0 - 220 MB | NPU
114
- | VIT | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 18.888 ms | 0 - 338 MB | NPU
115
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® X2 Elite | 10.713 ms | 22 - 22 MB | NPU
116
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® X Elite | 19.714 ms | 83 - 83 MB | NPU
117
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 14.923 ms | 16 - 518 MB | NPU
118
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Gen 1 Mobile | 31.574 ms | 16 - 485 MB | NPU
119
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ IQ-8275 | 22.533 ms | 14 - 17 MB | NPU
120
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 20.342 ms | 14 - 18 MB | NPU
121
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCS8450 | 31.574 ms | 16 - 485 MB | NPU
122
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ IQ-9075 | 22.113 ms | 16 - 18 MB | NPU
123
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ IQ-X7181 | 19.714 ms | 83 - 83 MB | NPU
124
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ Q-8750 | 11.764 ms | 16 - 386 MB | NPU
125
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite Mobile | 11.764 ms | 16 - 386 MB | NPU
126
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 9.625 ms | 16 - 399 MB | NPU
127
- | VIT | QNN_DLC | float | Snapdragon® X2 Elite | 6.978 ms | 1 - 1 MB | NPU
128
- | VIT | QNN_DLC | float | Snapdragon® X Elite | 12.669 ms | 1 - 1 MB | NPU
129
- | VIT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.268 ms | 0 - 303 MB | NPU
130
- | VIT | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 15.455 ms | 0 - 303 MB | NPU
131
- | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 14.939 ms | 1 - 4 MB | NPU
132
- | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.846 ms | 1 - 2 MB | NPU
133
- | VIT | QNN_DLC | float | Qualcomm® SA8775P | 14.649 ms | 1 - 169 MB | NPU
134
- | VIT | QNN_DLC | float | Qualcomm® SA8650P | 14.649 ms | 1 - 169 MB | NPU
135
- | VIT | QNN_DLC | float | Qualcomm® SA8255P | 14.649 ms | 1 - 169 MB | NPU
136
- | VIT | QNN_DLC | float | Qualcomm® QCS8450 | 15.455 ms | 0 - 303 MB | NPU
137
- | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 14.892 ms | 1 - 3 MB | NPU
138
- | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 12.669 ms | 1 - 1 MB | NPU
139
- | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 6.204 ms | 1 - 173 MB | NPU
140
- | VIT | QNN_DLC | float | Qualcomm® SA7255P | 42.295 ms | 1 - 168 MB | NPU
141
- | VIT | QNN_DLC | float | Qualcomm® SA8295P | 16.197 ms | 1 - 164 MB | NPU
142
- | VIT | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 6.204 ms | 1 - 173 MB | NPU
143
- | VIT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 5.178 ms | 1 - 158 MB | NPU
144
- | VIT | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 5.744 ms | 0 - 0 MB | NPU
145
- | VIT | QNN_DLC | w8a16 | Snapdragon® X Elite | 13.235 ms | 0 - 0 MB | NPU
146
- | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 8.698 ms | 0 - 338 MB | NPU
147
- | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 11.779 ms | 0 - 3 MB | NPU
148
- | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 12.392 ms | 0 - 2 MB | NPU
149
- | VIT | QNN_DLC | w8a16 | Qualcomm® SA8775P | 12.776 ms | 0 - 277 MB | NPU
150
  | VIT | QNN_DLC | w8a16 | Qualcomm® SA8650P | 12.776 ms | 0 - 277 MB | NPU
151
  | VIT | QNN_DLC | w8a16 | Qualcomm® SA8255P | 12.776 ms | 0 - 277 MB | NPU
152
- | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 12.858 ms | 0 - 2 MB | NPU
153
- | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 13.235 ms | 0 - 0 MB | NPU
154
- | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 154.402 ms | 0 - 477 MB | NPU
155
- | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 18.368 ms | 0 - 429 MB | NPU
156
- | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 6.319 ms | 0 - 277 MB | NPU
157
- | VIT | QNN_DLC | w8a16 | Qualcomm® SA7255P | 28.685 ms | 0 - 276 MB | NPU
158
- | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 6.319 ms | 0 - 277 MB | NPU
159
- | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 4.782 ms | 0 - 281 MB | NPU
160
- | VIT | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 18.368 ms | 0 - 429 MB | NPU
161
- | VIT | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 5.366 ms | 0 - 0 MB | NPU
162
- | VIT | QNN_DLC | w8a8 | Snapdragon® X Elite | 11.333 ms | 0 - 0 MB | NPU
163
- | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 7.075 ms | 0 - 323 MB | NPU
164
- | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 14.532 ms | 0 - 333 MB | NPU
165
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 74.196 ms | 0 - 2 MB | NPU
166
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 10.161 ms | 0 - 3 MB | NPU
167
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.585 ms | 0 - 2 MB | NPU
168
- | VIT | QNN_DLC | w8a8 | Qualcomm® SA8775P | 10.361 ms | 0 - 201 MB | NPU
169
- | VIT | QNN_DLC | w8a8 | Qualcomm® SA8650P | 10.361 ms | 0 - 201 MB | NPU
170
- | VIT | QNN_DLC | w8a8 | Qualcomm® SA8255P | 10.361 ms | 0 - 201 MB | NPU
171
- | VIT | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 14.532 ms | 0 - 333 MB | NPU
172
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 10.035 ms | 0 - 2 MB | NPU
173
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 11.333 ms | 0 - 0 MB | NPU
174
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 265.268 ms | 0 - 512 MB | NPU
175
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 18.618 ms | 0 - 332 MB | NPU
176
- | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 6.068 ms | 0 - 203 MB | NPU
177
- | VIT | QNN_DLC | w8a8 | Qualcomm® SA7255P | 31.183 ms | 0 - 202 MB | NPU
178
- | VIT | QNN_DLC | w8a8 | Qualcomm® SA8295P | 17.423 ms | 0 - 211 MB | NPU
179
- | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 6.068 ms | 0 - 203 MB | NPU
180
- | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 4.334 ms | 0 - 210 MB | NPU
181
- | VIT | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 18.618 ms | 0 - 332 MB | NPU
182
- | VIT | QNN_DLC | w8a8_mixed_int16 | Snapdragon® X2 Elite | 5.571 ms | 0 - 0 MB | NPU
183
- | VIT | QNN_DLC | w8a8_mixed_int16 | Snapdragon® X Elite | 12.75 ms | 1 - 1 MB | NPU
184
- | VIT | QNN_DLC | w8a8_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 8.139 ms | 0 - 478 MB | NPU
185
- | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® Dragonwing™ IQ-8275 | 11.452 ms | 0 - 3 MB | NPU
186
- | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 12.059 ms | 0 - 258 MB | NPU
187
- | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® SA8775P | 11.521 ms | 0 - 349 MB | NPU
188
  | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® SA8650P | 11.521 ms | 0 - 349 MB | NPU
189
  | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® SA8255P | 11.521 ms | 0 - 349 MB | NPU
190
- | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® Dragonwing™ IQ-9075 | 11.292 ms | 2 - 4 MB | NPU
191
- | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® Dragonwing™ IQ-X7181 | 12.75 ms | 1 - 1 MB | NPU
192
- | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® Dragonwing™ Q-6690 | 220.717 ms | 0 - 538 MB | NPU
193
- | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® Dragonwing™ Q-7790 | 19.558 ms | 0 - 372 MB | NPU
194
- | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® Dragonwing™ Q-8750 | 6.723 ms | 0 - 347 MB | NPU
195
- | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® SA7255P | 32.512 ms | 0 - 348 MB | NPU
196
- | VIT | QNN_DLC | w8a8_mixed_int16 | Snapdragon® 8 Elite Mobile | 6.723 ms | 0 - 347 MB | NPU
197
- | VIT | QNN_DLC | w8a8_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 4.717 ms | 0 - 343 MB | NPU
198
- | VIT | QNN_DLC | w8a8_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 19.558 ms | 0 - 372 MB | NPU
199
- | VIT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 6.802 ms | 0 - 308 MB | NPU
200
- | VIT | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 15.279 ms | 0 - 298 MB | NPU
201
- | VIT | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 13.271 ms | 0 - 173 MB | NPU
202
- | VIT | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.325 ms | 0 - 2 MB | NPU
203
- | VIT | TFLITE | float | Qualcomm® SA8775P | 12.577 ms | 0 - 170 MB | NPU
204
- | VIT | TFLITE | float | Qualcomm® SA8650P | 12.577 ms | 0 - 170 MB | NPU
205
- | VIT | TFLITE | float | Qualcomm® SA8255P | 12.577 ms | 0 - 170 MB | NPU
206
- | VIT | TFLITE | float | Qualcomm® QCS8450 | 15.279 ms | 0 - 298 MB | NPU
207
- | VIT | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 12.595 ms | 0 - 173 MB | NPU
208
- | VIT | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.871 ms | 0 - 180 MB | NPU
209
- | VIT | TFLITE | float | Qualcomm® SA7255P | 38.55 ms | 0 - 169 MB | NPU
210
- | VIT | TFLITE | float | Qualcomm® SA8295P | 15.705 ms | 0 - 164 MB | NPU
211
- | VIT | TFLITE | float | Snapdragon® 8 Elite Mobile | 4.871 ms | 0 - 180 MB | NPU
212
- | VIT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.741 ms | 0 - 166 MB | NPU
213
- | VIT | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 9.524 ms | 0 - 473 MB | NPU
214
- | VIT | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 21.784 ms | 0 - 464 MB | NPU
215
- | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 136.865 ms | 1 - 100 MB | NPU
216
- | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 13.742 ms | 0 - 87 MB | NPU
217
- | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 13.793 ms | 0 - 2 MB | NPU
218
- | VIT | TFLITE | w8a8 | Qualcomm® SA8775P | 13.761 ms | 0 - 342 MB | NPU
219
- | VIT | TFLITE | w8a8 | Qualcomm® SA8650P | 13.761 ms | 0 - 342 MB | NPU
220
- | VIT | TFLITE | w8a8 | Qualcomm® SA8255P | 13.761 ms | 0 - 342 MB | NPU
221
- | VIT | TFLITE | w8a8 | Qualcomm® QCS8450 | 21.784 ms | 0 - 464 MB | NPU
222
- | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 13.65 ms | 0 - 87 MB | NPU
223
- | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 202.274 ms | 1 - 259 MB | NPU
224
- | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 30.833 ms | 1 - 188 MB | NPU
225
- | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 7.775 ms | 0 - 341 MB | NPU
226
- | VIT | TFLITE | w8a8 | Qualcomm® SA7255P | 37.333 ms | 0 - 341 MB | NPU
227
- | VIT | TFLITE | w8a8 | Qualcomm® SA8295P | 21.362 ms | 0 - 333 MB | NPU
228
- | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 7.775 ms | 0 - 341 MB | NPU
229
- | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 5.553 ms | 0 - 349 MB | NPU
230
- | VIT | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 30.833 ms | 1 - 188 MB | NPU
231
 
232
  ## License
233
  * 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/v0.63.0/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 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-onnx-float.zip)
32
+ | ONNX | w8a16 | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-onnx-w8a16.zip)
33
+ | ONNX | w8a8 | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-onnx-w8a8.zip)
34
+ | ONNX | w8a8_mixed_int16 | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-onnx-w8a8_mixed_int16.zip)
35
+ | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-qnn_dlc-float.zip)
36
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-qnn_dlc-w8a16.zip)
37
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-qnn_dlc-w8a8.zip)
38
+ | QNN_DLC | w8a8_mixed_int16 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-qnn_dlc-w8a8_mixed_int16.zip)
39
+ | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-tflite-float.zip)
40
+ | TFLITE | w8a8 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-tflite-w8a8.zip)
41
 
42
  For more device-specific assets and performance metrics, visit **[VIT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/vit)**.
43
 
44
 
45
  ### Option 2: Export with Custom Configurations
46
 
47
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/vit) Python library to compile and export the model with your own:
48
  - Custom weights (e.g., fine-tuned checkpoints)
49
  - Custom input shapes
50
  - Target device and runtime configurations
51
 
52
  This option is ideal if you need to customize the model beyond the default configuration provided here.
53
 
54
+ See our repository for [VIT on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/vit) for usage instructions.
55
 
56
  ## Model Details
57
 
 
68
  ## Performance Summary
69
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
70
  |---|---|---|---|---|---|---
71
+ | VIT | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.457 ms | 0 - 160 MB | NPU
72
+ | VIT | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.576 ms | 0 - 159 MB | NPU
73
+ | VIT | ONNX | float | Snapdragon® X2 Elite | 3.836 ms | 2 - 2 MB | NPU
74
+ | VIT | ONNX | float | Snapdragon® X Elite | 9.652 ms | 171 - 171 MB | NPU
75
+ | VIT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 6.449 ms | 0 - 287 MB | NPU
76
+ | VIT | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 13.632 ms | 1 - 285 MB | NPU
77
+ | VIT | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 12.761 ms | 0 - 5 MB | NPU
78
+ | VIT | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.175 ms | 0 - 194 MB | NPU
79
+ | VIT | ONNX | float | Qualcomm® QCS8450 | 13.632 ms | 1 - 285 MB | NPU
80
+ | VIT | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 12.108 ms | 1 - 4 MB | NPU
81
+ | VIT | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 9.652 ms | 171 - 171 MB | NPU
82
+ | VIT | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.576 ms | 0 - 159 MB | NPU
83
+ | VIT | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 2.981 ms | 0 - 224 MB | NPU
84
+ | VIT | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.124 ms | 0 - 222 MB | NPU
85
+ | VIT | ONNX | w8a16 | Snapdragon® X2 Elite | 3.467 ms | 1 - 1 MB | NPU
86
+ | VIT | ONNX | w8a16 | Snapdragon® X Elite | 8.062 ms | 86 - 86 MB | NPU
87
+ | VIT | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.518 ms | 0 - 325 MB | NPU
88
+ | VIT | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 8.687 ms | 0 - 327 MB | NPU
89
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 30.519 ms | 0 - 4 MB | NPU
90
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 7.604 ms | 0 - 5 MB | NPU
91
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.69 ms | 0 - 98 MB | NPU
92
+ | VIT | ONNX | w8a16 | Qualcomm® QCS8450 | 8.687 ms | 0 - 327 MB | NPU
93
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 7.799 ms | 0 - 4 MB | NPU
94
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 8.062 ms | 86 - 86 MB | NPU
95
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 82.973 ms | 0 - 438 MB | NPU
96
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 9.645 ms | 0 - 394 MB | NPU
97
+ | VIT | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 4.124 ms | 0 - 222 MB | NPU
98
+ | VIT | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 9.645 ms | 0 - 394 MB | NPU
99
+ | VIT | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 4.254 ms | 0 - 221 MB | NPU
100
+ | VIT | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 5.836 ms | 0 - 214 MB | NPU
101
+ | VIT | ONNX | w8a8 | Snapdragon® X2 Elite | 4.889 ms | 1 - 1 MB | NPU
102
+ | VIT | ONNX | w8a8 | Snapdragon® X Elite | 10.877 ms | 86 - 86 MB | NPU
103
+ | VIT | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.944 ms | 0 - 334 MB | NPU
104
+ | VIT | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 13.743 ms | 0 - 345 MB | NPU
105
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 57.56 ms | 0 - 3 MB | NPU
106
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 10.119 ms | 0 - 4 MB | NPU
107
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.394 ms | 0 - 99 MB | NPU
108
+ | VIT | ONNX | w8a8 | Qualcomm® QCS8450 | 13.743 ms | 0 - 345 MB | NPU
109
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 9.84 ms | 0 - 4 MB | NPU
110
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 10.877 ms | 86 - 86 MB | NPU
111
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 215.695 ms | 0 - 458 MB | NPU
112
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 19.893 ms | 0 - 330 MB | NPU
113
+ | VIT | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 5.836 ms | 0 - 214 MB | NPU
114
+ | VIT | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 19.893 ms | 0 - 330 MB | NPU
115
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 11.533 ms | 40 - 391 MB | NPU
116
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite For Galaxy Mobile | 13.807 ms | 43 - 379 MB | NPU
117
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® X2 Elite | 13.15 ms | 67 - 67 MB | NPU
118
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® X Elite | 23.304 ms | 82 - 82 MB | NPU
119
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 17.443 ms | 41 - 503 MB | NPU
120
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Gen 1 Mobile | 30.349 ms | 42 - 497 MB | NPU
121
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ IQ-8275 | 27.841 ms | 38 - 46 MB | NPU
122
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 24.301 ms | 38 - 41 MB | NPU
123
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCS8450 | 30.349 ms | 42 - 497 MB | NPU
124
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ IQ-9075 | 26.692 ms | 42 - 48 MB | NPU
125
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ IQ-X7181 | 23.304 ms | 82 - 82 MB | NPU
126
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® Dragonwing™ Q-8750 | 13.807 ms | 43 - 379 MB | NPU
127
+ | VIT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 5.141 ms | 0 - 161 MB | NPU
128
+ | VIT | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 6.118 ms | 0 - 159 MB | NPU
129
+ | VIT | QNN_DLC | float | Snapdragon® X2 Elite | 5.674 ms | 1 - 1 MB | NPU
130
+ | VIT | QNN_DLC | float | Snapdragon® X Elite | 12.622 ms | 1 - 1 MB | NPU
131
+ | VIT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.204 ms | 0 - 289 MB | NPU
132
+ | VIT | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 14.858 ms | 1 - 288 MB | NPU
133
+ | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 14.81 ms | 1 - 4 MB | NPU
134
+ | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.765 ms | 1 - 2 MB | NPU
135
+ | VIT | QNN_DLC | float | Qualcomm® QCS8450 | 14.858 ms | 1 - 288 MB | NPU
136
+ | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 14.734 ms | 1 - 3 MB | NPU
137
+ | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 12.622 ms | 1 - 1 MB | NPU
138
+ | VIT | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 6.118 ms | 0 - 159 MB | NPU
139
+ | VIT | QNN_DLC | float | Qualcomm® SA7255P | 42.14 ms | 1 - 157 MB | NPU
140
+ | VIT | QNN_DLC | float | Qualcomm® SA8295P | 16.025 ms | 1 - 154 MB | NPU
141
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.567 ms | 0 - 213 MB | NPU
142
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.917 ms | 0 - 209 MB | NPU
143
+ | VIT | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 4.447 ms | 0 - 0 MB | NPU
144
+ | VIT | QNN_DLC | w8a16 | Snapdragon® X Elite | 10.075 ms | 0 - 0 MB | NPU
145
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.632 ms | 0 - 316 MB | NPU
146
+ | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 9.066 ms | 0 - 3 MB | NPU
147
+ | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.38 ms | 0 - 2 MB | NPU
 
 
148
  | VIT | QNN_DLC | w8a16 | Qualcomm® SA8650P | 12.776 ms | 0 - 277 MB | NPU
149
  | VIT | QNN_DLC | w8a16 | Qualcomm® SA8255P | 12.776 ms | 0 - 277 MB | NPU
150
+ | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 9.503 ms | 0 - 3 MB | NPU
151
+ | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 10.075 ms | 0 - 0 MB | NPU
152
+ | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 117.44 ms | 2 - 432 MB | NPU
153
+ | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 11.808 ms | 0 - 380 MB | NPU
154
+ | VIT | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 4.917 ms | 0 - 209 MB | NPU
155
+ | VIT | QNN_DLC | w8a16 | Qualcomm® SA7255P | 22.853 ms | 0 - 253 MB | NPU
156
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 11.808 ms | 0 - 380 MB | NPU
157
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 4.279 ms | 0 - 212 MB | NPU
158
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 5.876 ms | 0 - 205 MB | NPU
159
+ | VIT | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 5.257 ms | 0 - 0 MB | NPU
160
+ | VIT | QNN_DLC | w8a8 | Snapdragon® X Elite | 11.227 ms | 0 - 0 MB | NPU
161
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 7.037 ms | 0 - 327 MB | NPU
162
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 13.628 ms | 0 - 335 MB | NPU
163
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 57.965 ms | 0 - 2 MB | NPU
164
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 10.164 ms | 0 - 3 MB | NPU
165
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.565 ms | 0 - 2 MB | NPU
166
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 13.628 ms | 0 - 335 MB | NPU
167
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 10.005 ms | 0 - 2 MB | NPU
168
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 11.227 ms | 0 - 0 MB | NPU
169
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 229.388 ms | 0 - 463 MB | NPU
170
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 19.963 ms | 0 - 322 MB | NPU
171
+ | VIT | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 5.876 ms | 0 - 205 MB | NPU
172
+ | VIT | QNN_DLC | w8a8 | Qualcomm® SA8295P | 17.349 ms | 0 - 211 MB | NPU
173
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 19.963 ms | 0 - 322 MB | NPU
174
+ | VIT | QNN_DLC | w8a8_mixed_int16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 4.664 ms | 0 - 324 MB | NPU
175
+ | VIT | QNN_DLC | w8a8_mixed_int16 | Snapdragon® 8 Elite For Galaxy Mobile | 6.249 ms | 0 - 316 MB | NPU
176
+ | VIT | QNN_DLC | w8a8_mixed_int16 | Snapdragon® X2 Elite | 5.57 ms | 0 - 0 MB | NPU
177
+ | VIT | QNN_DLC | w8a8_mixed_int16 | Snapdragon® X Elite | 11.703 ms | 0 - 0 MB | NPU
178
+ | VIT | QNN_DLC | w8a8_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 7.433 ms | 0 - 438 MB | NPU
179
+ | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® Dragonwing™ IQ-8275 | 10.638 ms | 0 - 3 MB | NPU
180
+ | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 11.044 ms | 0 - 2 MB | NPU
 
 
 
 
 
181
  | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® SA8650P | 11.521 ms | 0 - 349 MB | NPU
182
  | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® SA8255P | 11.521 ms | 0 - 349 MB | NPU
183
+ | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® Dragonwing™ IQ-9075 | 10.499 ms | 0 - 2 MB | NPU
184
+ | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® Dragonwing™ IQ-X7181 | 11.703 ms | 0 - 0 MB | NPU
185
+ | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® Dragonwing™ Q-6690 | 225.416 ms | 0 - 490 MB | NPU
186
+ | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® Dragonwing™ Q-7790 | 21.333 ms | 0 - 334 MB | NPU
187
+ | VIT | QNN_DLC | w8a8_mixed_int16 | Qualcomm® Dragonwing™ Q-8750 | 6.249 ms | 0 - 316 MB | NPU
188
+ | VIT | QNN_DLC | w8a8_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 21.333 ms | 0 - 334 MB | NPU
189
+ | VIT | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 3.612 ms | 0 - 163 MB | NPU
190
+ | VIT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.759 ms | 0 - 161 MB | NPU
191
+ | VIT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 6.745 ms | 0 - 290 MB | NPU
192
+ | VIT | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 14.368 ms | 0 - 284 MB | NPU
193
+ | VIT | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 12.998 ms | 0 - 174 MB | NPU
194
+ | VIT | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.257 ms | 0 - 3 MB | NPU
195
+ | VIT | TFLITE | float | Qualcomm® SA8775P | 12.461 ms | 0 - 158 MB | NPU
196
+ | VIT | TFLITE | float | Qualcomm® SA8650P | 12.461 ms | 0 - 158 MB | NPU
197
+ | VIT | TFLITE | float | Qualcomm® SA8255P | 12.461 ms | 0 - 158 MB | NPU
198
+ | VIT | TFLITE | float | Qualcomm® QCS8450 | 14.368 ms | 0 - 284 MB | NPU
199
+ | VIT | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 12.573 ms | 0 - 173 MB | NPU
200
+ | VIT | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.759 ms | 0 - 161 MB | NPU
201
+ | VIT | TFLITE | float | Qualcomm® SA7255P | 38.489 ms | 0 - 157 MB | NPU
202
+ | VIT | TFLITE | float | Qualcomm® SA8295P | 15.505 ms | 0 - 151 MB | NPU
203
+ | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 5.213 ms | 0 - 317 MB | NPU
204
+ | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 7.462 ms | 0 - 310 MB | NPU
205
+ | VIT | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 9.229 ms | 0 - 444 MB | NPU
206
+ | VIT | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 18.407 ms | 0 - 453 MB | NPU
207
+ | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 148.614 ms | 1 - 101 MB | NPU
208
+ | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 13.1 ms | 0 - 88 MB | NPU
209
+ | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 13.12 ms | 0 - 2 MB | NPU
210
+ | VIT | TFLITE | w8a8 | Qualcomm® SA8775P | 13.123 ms | 0 - 311 MB | NPU
211
+ | VIT | TFLITE | w8a8 | Qualcomm® SA8650P | 13.123 ms | 0 - 311 MB | NPU
212
+ | VIT | TFLITE | w8a8 | Qualcomm® SA8255P | 13.123 ms | 0 - 311 MB | NPU
213
+ | VIT | TFLITE | w8a8 | Qualcomm® QCS8450 | 18.407 ms | 0 - 453 MB | NPU
214
+ | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 13.246 ms | 0 - 87 MB | NPU
215
+ | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 197.898 ms | 2 - 246 MB | NPU
216
+ | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 31.272 ms | 2 - 177 MB | NPU
217
+ | VIT | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 7.462 ms | 0 - 310 MB | NPU
218
+ | VIT | TFLITE | w8a8 | Qualcomm® SA7255P | 36.481 ms | 0 - 311 MB | NPU
219
+ | VIT | TFLITE | w8a8 | Qualcomm® SA8295P | 20.924 ms | 0 - 319 MB | NPU
220
+ | VIT | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 31.272 ms | 2 - 177 MB | NPU
 
 
 
221
 
222
  ## License
223
  * The license for the original implementation of VIT can be found
release_assets.json CHANGED
@@ -1,26 +1,26 @@
1
  {
2
- "version": "0.62.2",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
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/v0.62.2/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/v0.62.2/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/v0.62.2/vit-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -28,16 +28,16 @@
28
  "universal_assets": {
29
  "onnx": {
30
  "tool_versions": {
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/v0.62.2/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/v0.62.2/vit-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  },
@@ -45,22 +45,22 @@
45
  "universal_assets": {
46
  "onnx": {
47
  "tool_versions": {
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/v0.62.2/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/v0.62.2/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/v0.62.2/vit-tflite-w8a8.zip"
64
  }
65
  }
66
  },
@@ -68,16 +68,16 @@
68
  "universal_assets": {
69
  "onnx": {
70
  "tool_versions": {
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/v0.62.2/vit-onnx-w8a8_mixed_int16.zip"
75
  },
76
  "qnn_dlc": {
77
  "tool_versions": {
78
- "qairt": "2.45.0.260326154327"
79
  },
80
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.62.2/vit-qnn_dlc-w8a8_mixed_int16.zip"
81
  }
82
  }
83
  }
 
1
  {
2
+ "version": "0.63.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
8
+ "qairt": "2.50.0.260828221209",
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/v0.63.0/vit-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
+ "qairt": "2.50.0.260828221209"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
+ "qairt": "2.50.0.260828221209"
22
  },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-tflite-float.zip"
24
  }
25
  }
26
  },
 
28
  "universal_assets": {
29
  "onnx": {
30
  "tool_versions": {
31
+ "qairt": "2.50.0.260828221209",
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/v0.63.0/vit-onnx-w8a16.zip"
35
  },
36
  "qnn_dlc": {
37
  "tool_versions": {
38
+ "qairt": "2.50.0.260828221209"
39
  },
40
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  },
 
45
  "universal_assets": {
46
  "onnx": {
47
  "tool_versions": {
48
+ "qairt": "2.50.0.260828221209",
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/v0.63.0/vit-onnx-w8a8.zip"
52
  },
53
  "qnn_dlc": {
54
  "tool_versions": {
55
+ "qairt": "2.50.0.260828221209"
56
  },
57
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-qnn_dlc-w8a8.zip"
58
  },
59
  "tflite": {
60
  "tool_versions": {
61
+ "qairt": "2.50.0.260828221209"
62
  },
63
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-tflite-w8a8.zip"
64
  }
65
  }
66
  },
 
68
  "universal_assets": {
69
  "onnx": {
70
  "tool_versions": {
71
+ "qairt": "2.50.0.260828221209",
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/v0.63.0/vit-onnx-w8a8_mixed_int16.zip"
75
  },
76
  "qnn_dlc": {
77
  "tool_versions": {
78
+ "qairt": "2.50.0.260828221209"
79
  },
80
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.63.0/vit-qnn_dlc-w8a8_mixed_int16.zip"
81
  }
82
  }
83
  }