Hugging Face's logo

qualcomm
/
Beit

Image Classification
PyTorch
backbone
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
081dcfe
·
verified ·
1 Parent(s): ae6ace0

v0.59.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.59.0 for changelog.

Files changed (2) hide show
  1. README.md +79 -79
  2. release_assets.json +15 -16
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: image-classification
15
  Beit 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 Beit found [here](https://github.com/microsoft/unilm/tree/master/beit).
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/v0.58.0/src/qai_hub_models/models/beit) 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
 
@@ -28,25 +28,25 @@ 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 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.58.0/beit-onnx-float.zip)
32
- | ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.58.0/beit-onnx-w8a16.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.58.0/beit-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.58.0/beit-qnn_dlc-w8a16.zip)
35
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.58.0/beit-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[Beit on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/beit)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/beit) Python library to compile and export the model with your own:
43
  - Custom weights (e.g., fine-tuned checkpoints)
44
  - Custom input shapes
45
  - Target device and runtime configurations
46
 
47
  This option is ideal if you need to customize the model beyond the default configuration provided here.
48
 
49
- See our repository for [Beit on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/beit) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -61,77 +61,77 @@ See our repository for [Beit on GitHub](https://github.com/qualcomm/ai-hub-model
61
  ## Performance Summary
62
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
63
  |---|---|---|---|---|---|---
64
- | Beit | ONNX | float | Snapdragon® X2 Elite | 7.441 ms | 2 - 2 MB | NPU
65
- | Beit | ONNX | float | Snapdragon® X Elite | 15.354 ms | 184 - 184 MB | NPU
66
- | Beit | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 10.47 ms | 0 - 449 MB | NPU
67
- | Beit | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 17.99 ms | 0 - 421 MB | NPU
68
- | Beit | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 14.888 ms | 0 - 63 MB | NPU
69
- | Beit | ONNX | float | Qualcomm® QCS8450 | 17.99 ms | 0 - 421 MB | NPU
70
- | Beit | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 17.934 ms | 0 - 4 MB | NPU
71
- | Beit | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.169 ms | 0 - 307 MB | NPU
72
- | Beit | ONNX | float | Snapdragon® 8 Elite Mobile | 8.582 ms | 1 - 305 MB | NPU
73
- | Beit | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 8.582 ms | 1 - 305 MB | NPU
74
- | Beit | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 15.354 ms | 184 - 184 MB | NPU
75
- | Beit | ONNX | w8a16 | Snapdragon® X2 Elite | 2.669 ms | 1 - 1 MB | NPU
76
- | Beit | ONNX | w8a16 | Snapdragon® X Elite | 6.898 ms | 95 - 95 MB | NPU
77
- | Beit | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.576 ms | 0 - 422 MB | NPU
78
- | Beit | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.678 ms | 0 - 99 MB | NPU
79
- | Beit | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 6.621 ms | 0 - 3 MB | NPU
80
- | Beit | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 9.054 ms | 0 - 412 MB | NPU
81
- | Beit | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.396 ms | 0 - 257 MB | NPU
82
- | Beit | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 109.293 ms | 0 - 443 MB | NPU
83
- | Beit | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 3.593 ms | 0 - 361 MB | NPU
84
- | Beit | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 9.054 ms | 0 - 412 MB | NPU
85
- | Beit | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.593 ms | 0 - 361 MB | NPU
86
- | Beit | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 6.898 ms | 95 - 95 MB | NPU
87
- | Beit | QNN_DLC | float | Snapdragon® X2 Elite | 7.853 ms | 1 - 1 MB | NPU
88
- | Beit | QNN_DLC | float | Snapdragon® X Elite | 15.165 ms | 1 - 1 MB | NPU
89
- | Beit | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 10.476 ms | 0 - 395 MB | NPU
90
- | Beit | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 17.553 ms | 0 - 380 MB | NPU
91
- | Beit | QNN_DLC | float | Qualcomm® QCS8275 | 48.01 ms | 1 - 295 MB | NPU
92
- | Beit | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 14.383 ms | 1 - 3 MB | NPU
93
- | Beit | QNN_DLC | float | Qualcomm® SA8775P | 17.18 ms | 1 - 295 MB | NPU
94
- | Beit | QNN_DLC | float | Qualcomm® SA8650P | 17.18 ms | 1 - 295 MB | NPU
95
- | Beit | QNN_DLC | float | Qualcomm® SA8255P | 17.18 ms | 1 - 295 MB | NPU
96
- | Beit | QNN_DLC | float | Qualcomm® QCS8450 | 17.553 ms | 0 - 380 MB | NPU
97
- | Beit | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 17.494 ms | 3 - 5 MB | NPU
98
- | Beit | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.184 ms | 1 - 301 MB | NPU
99
- | Beit | QNN_DLC | float | Qualcomm® SA7255P | 48.01 ms | 1 - 295 MB | NPU
100
- | Beit | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 8.576 ms | 1 - 301 MB | NPU
101
- | Beit | QNN_DLC | float | Qualcomm® SA8295P | 15.302 ms | 1 - 289 MB | NPU
102
- | Beit | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 8.576 ms | 1 - 301 MB | NPU
103
- | Beit | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 15.165 ms | 1 - 1 MB | NPU
104
- | Beit | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 3.19 ms | 0 - 0 MB | NPU
105
- | Beit | QNN_DLC | w8a16 | Snapdragon® X Elite | 7.332 ms | 0 - 0 MB | NPU
106
- | Beit | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.671 ms | 0 - 413 MB | NPU
107
- | Beit | QNN_DLC | w8a16 | Qualcomm® QCS8275 | 15.088 ms | 0 - 351 MB | NPU
108
- | Beit | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.773 ms | 0 - 2 MB | NPU
109
- | Beit | QNN_DLC | w8a16 | Qualcomm® SA8775P | 7.054 ms | 0 - 352 MB | NPU
110
- | Beit | QNN_DLC | w8a16 | Qualcomm® SA8650P | 7.054 ms | 0 - 352 MB | NPU
111
- | Beit | QNN_DLC | w8a16 | Qualcomm® SA8255P | 7.054 ms | 0 - 352 MB | NPU
112
- | Beit | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 7.12 ms | 0 - 2 MB | NPU
113
- | Beit | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 8.687 ms | 0 - 399 MB | NPU
114
- | Beit | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.559 ms | 0 - 245 MB | NPU
115
- | Beit | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 109.915 ms | 0 - 428 MB | NPU
116
- | Beit | QNN_DLC | w8a16 | Qualcomm® SA7255P | 15.088 ms | 0 - 351 MB | NPU
117
- | Beit | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 3.589 ms | 0 - 349 MB | NPU
118
- | Beit | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 8.687 ms | 0 - 399 MB | NPU
119
- | Beit | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.589 ms | 0 - 349 MB | NPU
120
- | Beit | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 7.332 ms | 0 - 0 MB | NPU
121
- | Beit | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 10.515 ms | 0 - 406 MB | NPU
122
- | Beit | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 17.546 ms | 0 - 371 MB | NPU
123
- | Beit | TFLITE | float | Qualcomm® QCS8275 | 48.061 ms | 0 - 300 MB | NPU
124
- | Beit | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 14.002 ms | 0 - 3 MB | NPU
125
- | Beit | TFLITE | float | Qualcomm® SA8775P | 17.189 ms | 0 - 301 MB | NPU
126
- | Beit | TFLITE | float | Qualcomm® SA8650P | 17.189 ms | 0 - 301 MB | NPU
127
- | Beit | TFLITE | float | Qualcomm® SA8255P | 17.189 ms | 0 - 301 MB | NPU
128
- | Beit | TFLITE | float | Qualcomm® QCS8450 | 17.546 ms | 0 - 371 MB | NPU
129
- | Beit | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 17.528 ms | 0 - 186 MB | NPU
130
- | Beit | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.18 ms | 0 - 311 MB | NPU
131
- | Beit | TFLITE | float | Qualcomm® SA7255P | 48.061 ms | 0 - 300 MB | NPU
132
- | Beit | TFLITE | float | Snapdragon® 8 Elite Mobile | 8.573 ms | 0 - 311 MB | NPU
133
- | Beit | TFLITE | float | Qualcomm® SA8295P | 15.345 ms | 0 - 293 MB | NPU
134
- | Beit | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 8.573 ms | 0 - 311 MB | NPU
135
 
136
  ## License
137
  * The license for the original implementation of Beit can be found
 
15
  Beit 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 Beit found [here](https://github.com/microsoft/unilm/tree/master/beit).
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/beit) 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/beit/releases/v0.59.0/beit-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/beit/releases/v0.59.0/beit-onnx-w8a16.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.59.0/beit-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.59.0/beit-qnn_dlc-w8a16.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.59.0/beit-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[Beit on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/beit)**.
38
 
39
 
40
  ### Option 2: Export with Custom Configurations
41
 
42
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/beit) Python library to compile and export the model with your own:
43
  - Custom weights (e.g., fine-tuned checkpoints)
44
  - Custom input shapes
45
  - Target device and runtime configurations
46
 
47
  This option is ideal if you need to customize the model beyond the default configuration provided here.
48
 
49
+ See our repository for [Beit on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/beit) for usage instructions.
50
 
51
  ## Model Details
52
 
 
61
  ## Performance Summary
62
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
63
  |---|---|---|---|---|---|---
64
+ | Beit | ONNX | float | Snapdragon® X2 Elite | 7.436 ms | 2 - 2 MB | NPU
65
+ | Beit | ONNX | float | Snapdragon® X Elite | 15.305 ms | 184 - 184 MB | NPU
66
+ | Beit | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 10.496 ms | 0 - 449 MB | NPU
67
+ | Beit | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 17.894 ms | 1 - 422 MB | NPU
68
+ | Beit | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 14.88 ms | 0 - 194 MB | NPU
69
+ | Beit | ONNX | float | Qualcomm® QCS8450 | 17.894 ms | 1 - 422 MB | NPU
70
+ | Beit | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 17.267 ms | 0 - 4 MB | NPU
71
+ | Beit | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 15.305 ms | 184 - 184 MB | NPU
72
+ | Beit | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 8.532 ms | 1 - 305 MB | NPU
73
+ | Beit | ONNX | float | Snapdragon® 8 Elite Mobile | 8.532 ms | 1 - 305 MB | NPU
74
+ | Beit | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.161 ms | 0 - 305 MB | NPU
75
+ | Beit | ONNX | w8a16 | Snapdragon® X2 Elite | 2.67 ms | 1 - 1 MB | NPU
76
+ | Beit | ONNX | w8a16 | Snapdragon® X Elite | 6.899 ms | 96 - 96 MB | NPU
77
+ | Beit | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.572 ms | 0 - 422 MB | NPU
78
+ | Beit | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 11.152 ms | 0 - 423 MB | NPU
79
+ | Beit | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 36.169 ms | 0 - 3 MB | NPU
80
+ | Beit | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.695 ms | 0 - 3 MB | NPU
81
+ | Beit | ONNX | w8a16 | Qualcomm® QCS8450 | 11.152 ms | 0 - 423 MB | NPU
82
+ | Beit | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 6.624 ms | 0 - 3 MB | NPU
83
+ | Beit | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 6.899 ms | 96 - 96 MB | NPU
84
+ | Beit | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.578 ms | 0 - 362 MB | NPU
85
+ | Beit | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 3.578 ms | 0 - 362 MB | NPU
86
+ | Beit | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.398 ms | 0 - 257 MB | NPU
87
+ | Beit | QNN_DLC | float | Snapdragon® X2 Elite | 7.849 ms | 1 - 1 MB | NPU
88
+ | Beit | QNN_DLC | float | Snapdragon® X Elite | 15.125 ms | 1 - 1 MB | NPU
89
+ | Beit | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 10.498 ms | 0 - 392 MB | NPU
90
+ | Beit | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 17.579 ms | 0 - 380 MB | NPU
91
+ | Beit | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 47.915 ms | 1 - 295 MB | NPU
92
+ | Beit | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 14.39 ms | 1 - 415 MB | NPU
93
+ | Beit | QNN_DLC | float | Qualcomm® SA8775P | 17.197 ms | 1 - 296 MB | NPU
94
+ | Beit | QNN_DLC | float | Qualcomm® SA8650P | 17.197 ms | 1 - 296 MB | NPU
95
+ | Beit | QNN_DLC | float | Qualcomm® SA8255P | 17.197 ms | 1 - 296 MB | NPU
96
+ | Beit | QNN_DLC | float | Qualcomm® QCS8450 | 17.579 ms | 0 - 380 MB | NPU
97
+ | Beit | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 20.102 ms | 1 - 3 MB | NPU
98
+ | Beit | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 15.125 ms | 1 - 1 MB | NPU
99
+ | Beit | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 8.541 ms | 1 - 301 MB | NPU
100
+ | Beit | QNN_DLC | float | Qualcomm® SA7255P | 47.915 ms | 1 - 295 MB | NPU
101
+ | Beit | QNN_DLC | float | Qualcomm® SA8295P | 15.339 ms | 1 - 289 MB | NPU
102
+ | Beit | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 8.541 ms | 1 - 301 MB | NPU
103
+ | Beit | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.181 ms | 1 - 301 MB | NPU
104
+ | Beit | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 3.156 ms | 0 - 0 MB | NPU
105
+ | Beit | QNN_DLC | w8a16 | Snapdragon® X Elite | 7.302 ms | 0 - 0 MB | NPU
106
+ | Beit | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.65 ms | 0 - 409 MB | NPU
107
+ | Beit | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8275 | 15.087 ms | 0 - 350 MB | NPU
108
+ | Beit | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.776 ms | 0 - 266 MB | NPU
109
+ | Beit | QNN_DLC | w8a16 | Qualcomm® SA8775P | 7.041 ms | 0 - 351 MB | NPU
110
+ | Beit | QNN_DLC | w8a16 | Qualcomm® SA8650P | 7.041 ms | 0 - 351 MB | NPU
111
+ | Beit | QNN_DLC | w8a16 | Qualcomm® SA8255P | 7.041 ms | 0 - 351 MB | NPU
112
+ | Beit | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 6.843 ms | 0 - 2 MB | NPU
113
+ | Beit | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 7.302 ms | 0 - 0 MB | NPU
114
+ | Beit | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 65.256 ms | 0 - 428 MB | NPU
115
+ | Beit | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 8.652 ms | 0 - 400 MB | NPU
116
+ | Beit | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.557 ms | 0 - 351 MB | NPU
117
+ | Beit | QNN_DLC | w8a16 | Qualcomm® SA7255P | 15.087 ms | 0 - 350 MB | NPU
118
+ | Beit | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 3.557 ms | 0 - 351 MB | NPU
119
+ | Beit | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.554 ms | 0 - 244 MB | NPU
120
+ | Beit | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 8.652 ms | 0 - 400 MB | NPU
121
+ | Beit | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 10.452 ms | 0 - 404 MB | NPU
122
+ | Beit | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 17.698 ms | 0 - 371 MB | NPU
123
+ | Beit | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 47.98 ms | 0 - 300 MB | NPU
124
+ | Beit | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 14.039 ms | 0 - 2 MB | NPU
125
+ | Beit | TFLITE | float | Qualcomm® SA8775P | 17.172 ms | 0 - 302 MB | NPU
126
+ | Beit | TFLITE | float | Qualcomm® SA8650P | 17.172 ms | 0 - 302 MB | NPU
127
+ | Beit | TFLITE | float | Qualcomm® SA8255P | 17.172 ms | 0 - 302 MB | NPU
128
+ | Beit | TFLITE | float | Qualcomm® QCS8450 | 17.698 ms | 0 - 371 MB | NPU
129
+ | Beit | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 17.569 ms | 0 - 186 MB | NPU
130
+ | Beit | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 8.545 ms | 0 - 309 MB | NPU
131
+ | Beit | TFLITE | float | Qualcomm® SA7255P | 47.98 ms | 0 - 300 MB | NPU
132
+ | Beit | TFLITE | float | Qualcomm® SA8295P | 15.33 ms | 0 - 293 MB | NPU
133
+ | Beit | TFLITE | float | Snapdragon® 8 Elite Mobile | 8.545 ms | 0 - 309 MB | NPU
134
+ | Beit | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.181 ms | 0 - 312 MB | NPU
135
 
136
  ## License
137
  * The license for the original implementation of Beit can be found
release_assets.json CHANGED
@@ -1,44 +1,43 @@
1
  {
2
- "version": "0.58.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
- "tflite": {
7
  "tool_versions": {
8
  "qairt": "2.45.0.260326154327",
9
- "litert": "1.4.4"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.58.0/beit-tflite-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/beit/releases/v0.58.0/beit-qnn_dlc-float.zip"
18
  },
19
- "onnx": {
20
  "tool_versions": {
21
- "qairt": "2.45.0.260326154327",
22
- "onnx_runtime": "1.25.0"
23
  },
24
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.58.0/beit-onnx-float.zip"
25
  }
26
  }
27
  },
28
  "w8a16": {
29
  "universal_assets": {
30
- "qnn_dlc": {
31
  "tool_versions": {
32
- "qairt": "2.45.0.260326154327"
 
33
  },
34
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.58.0/beit-qnn_dlc-w8a16.zip"
35
  },
36
- "onnx": {
37
  "tool_versions": {
38
- "qairt": "2.45.0.260326154327",
39
- "onnx_runtime": "1.25.0"
40
  },
41
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.58.0/beit-onnx-w8a16.zip"
42
  }
43
  }
44
  }
 
1
  {
2
+ "version": "0.59.0",
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/beit/releases/v0.59.0/beit-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/beit/releases/v0.59.0/beit-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/beit/releases/v0.59.0/beit-tflite-float.zip"
24
  }
25
  }
26
  },
27
  "w8a16": {
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/beit/releases/v0.59.0/beit-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/beit/releases/v0.59.0/beit-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  }