Hugging Face's logo

qualcomm
/
Swin-Base

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
8c8929a
·
verified ·
1 Parent(s): 03eccee

v0.61.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.61.0 for changelog.

Files changed (2) hide show
  1. README.md +88 -86
  2. release_assets.json +6 -6
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: pytorch
3
- license: other
4
  tags:
5
  - backbone
6
  - bu_auto
@@ -16,7 +16,7 @@ pipeline_tag: image-classification
16
  SwinBase 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.
17
 
18
  This is based on the implementation of Swin-Base found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/swin_transformer.py).
19
- 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/swin_base) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
20
 
21
  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.
22
 
@@ -29,25 +29,25 @@ Below are pre-exported model assets ready for deployment.
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
- | 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/swin_base/releases/v0.60.0/swin_base-onnx-float.zip)
33
- | 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/swin_base/releases/v0.60.0/swin_base-onnx-w8a16.zip)
34
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_base/releases/v0.60.0/swin_base-qnn_dlc-float.zip)
35
- | QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_base/releases/v0.60.0/swin_base-qnn_dlc-w8a16.zip)
36
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_base/releases/v0.60.0/swin_base-tflite-float.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[Swin-Base on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/swin_base)**.
39
 
40
 
41
  ### Option 2: Export with Custom Configurations
42
 
43
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/swin_base) Python library to compile and export the model with your own:
44
  - Custom weights (e.g., fine-tuned checkpoints)
45
  - Custom input shapes
46
  - Target device and runtime configurations
47
 
48
  This option is ideal if you need to customize the model beyond the default configuration provided here.
49
 
50
- See our repository for [Swin-Base on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/swin_base) for usage instructions.
51
 
52
  ## Model Details
53
 
@@ -63,83 +63,85 @@ See our repository for [Swin-Base on GitHub](https://github.com/qualcomm/ai-hub-
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
- | Swin-Base | ONNX | float | Snapdragon® X2 Elite | 8.372 ms | 2 - 2 MB | NPU
67
- | Swin-Base | ONNX | float | Snapdragon® X Elite | 19.959 ms | 175 - 175 MB | NPU
68
- | Swin-Base | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 13.114 ms | 0 - 548 MB | NPU
69
- | Swin-Base | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 29.299 ms | 1 - 1066 MB | NPU
70
- | Swin-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 21.296 ms | 0 - 4 MB | NPU
71
- | Swin-Base | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 19.268 ms | 0 - 194 MB | NPU
72
- | Swin-Base | ONNX | float | Qualcomm® QCS8450 | 29.299 ms | 1 - 1066 MB | NPU
73
- | Swin-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 22.641 ms | 1 - 4 MB | NPU
74
- | Swin-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 19.959 ms | 175 - 175 MB | NPU
75
- | Swin-Base | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 9.914 ms | 0 - 400 MB | NPU
76
- | Swin-Base | ONNX | float | Snapdragon® 8 Elite Mobile | 9.914 ms | 0 - 400 MB | NPU
77
- | Swin-Base | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.974 ms | 0 - 420 MB | NPU
78
- | Swin-Base | ONNX | w8a16 | Snapdragon® X2 Elite | 6.988 ms | 1 - 1 MB | NPU
79
- | Swin-Base | ONNX | w8a16 | Snapdragon® X Elite | 16.28 ms | 92 - 92 MB | NPU
80
- | Swin-Base | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 10.428 ms | 0 - 535 MB | NPU
81
- | Swin-Base | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 20.604 ms | 0 - 535 MB | NPU
82
- | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 57.993 ms | 0 - 3 MB | NPU
83
- | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 14.414 ms | 0 - 4 MB | NPU
84
- | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 15.388 ms | 0 - 99 MB | NPU
85
- | Swin-Base | ONNX | w8a16 | Qualcomm® QCS8450 | 20.604 ms | 0 - 535 MB | NPU
86
- | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 16.144 ms | 0 - 3 MB | NPU
87
- | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 16.28 ms | 92 - 92 MB | NPU
88
- | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 114.631 ms | 0 - 689 MB | NPU
89
- | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 17.805 ms | 0 - 621 MB | NPU
90
- | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 8.236 ms | 0 - 418 MB | NPU
91
- | Swin-Base | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 8.236 ms | 0 - 418 MB | NPU
92
- | Swin-Base | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 6.541 ms | 0 - 432 MB | NPU
93
- | Swin-Base | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 17.805 ms | 0 - 621 MB | NPU
94
- | Swin-Base | QNN_DLC | float | Snapdragon® X2 Elite | 8.501 ms | 1 - 1 MB | NPU
95
- | Swin-Base | QNN_DLC | float | Snapdragon® X Elite | 19.314 ms | 1 - 1 MB | NPU
96
- | Swin-Base | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 12.535 ms | 0 - 516 MB | NPU
97
- | Swin-Base | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 29.092 ms | 0 - 503 MB | NPU
98
- | Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 20.321 ms | 1 - 4 MB | NPU
99
- | Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 53.584 ms | 1 - 363 MB | NPU
100
- | Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 18.415 ms | 1 - 3 MB | NPU
101
- | Swin-Base | QNN_DLC | float | Qualcomm® SA8775P | 21.397 ms | 1 - 363 MB | NPU
102
- | Swin-Base | QNN_DLC | float | Qualcomm® SA8650P | 21.397 ms | 1 - 363 MB | NPU
103
- | Swin-Base | QNN_DLC | float | Qualcomm® SA8255P | 21.397 ms | 1 - 363 MB | NPU
104
- | Swin-Base | QNN_DLC | float | Qualcomm® QCS8450 | 29.092 ms | 0 - 503 MB | NPU
105
- | Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 22.02 ms | 1 - 3 MB | NPU
106
- | Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 19.314 ms | 1 - 1 MB | NPU
107
- | Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 9.393 ms | 1 - 365 MB | NPU
108
- | Swin-Base | QNN_DLC | float | Qualcomm® SA7255P | 53.584 ms | 1 - 363 MB | NPU
109
- | Swin-Base | QNN_DLC | float | Qualcomm® SA8295P | 27.607 ms | 1 - 353 MB | NPU
110
- | Swin-Base | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 9.393 ms | 1 - 365 MB | NPU
111
- | Swin-Base | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.531 ms | 0 - 385 MB | NPU
112
- | Swin-Base | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 9.186 ms | 0 - 0 MB | NPU
113
- | Swin-Base | QNN_DLC | w8a16 | Snapdragon® X Elite | 20.471 ms | 0 - 0 MB | NPU
114
- | Swin-Base | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 12.755 ms | 0 - 509 MB | NPU
115
- | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 17.008 ms | 0 - 3 MB | NPU
116
- | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 35.403 ms | 0 - 413 MB | NPU
117
- | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 19.102 ms | 0 - 313 MB | NPU
118
- | Swin-Base | QNN_DLC | w8a16 | Qualcomm® SA8775P | 19.566 ms | 0 - 412 MB | NPU
119
- | Swin-Base | QNN_DLC | w8a16 | Qualcomm® SA8650P | 19.566 ms | 0 - 412 MB | NPU
120
- | Swin-Base | QNN_DLC | w8a16 | Qualcomm® SA8255P | 19.566 ms | 0 - 412 MB | NPU
121
- | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 20.284 ms | 0 - 2 MB | NPU
122
- | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 20.471 ms | 0 - 0 MB | NPU
123
- | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 123.34 ms | 0 - 933 MB | NPU
124
- | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 21.572 ms | 0 - 605 MB | NPU
125
- | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 9.531 ms | 0 - 408 MB | NPU
126
- | Swin-Base | QNN_DLC | w8a16 | Qualcomm® SA7255P | 35.403 ms | 0 - 413 MB | NPU
127
- | Swin-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 9.531 ms | 0 - 408 MB | NPU
128
- | Swin-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 7.609 ms | 0 - 422 MB | NPU
129
- | Swin-Base | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 21.572 ms | 0 - 605 MB | NPU
130
- | Swin-Base | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 12.8 ms | 0 - 1057 MB | NPU
131
- | Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 20.905 ms | 0 - 179 MB | NPU
132
- | Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 53.467 ms | 0 - 710 MB | NPU
133
- | Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 19.092 ms | 0 - 4 MB | NPU
134
- | Swin-Base | TFLITE | float | Qualcomm® SA8775P | 21.943 ms | 0 - 375 MB | NPU
135
- | Swin-Base | TFLITE | float | Qualcomm® SA8650P | 21.943 ms | 0 - 375 MB | NPU
136
- | Swin-Base | TFLITE | float | Qualcomm® SA8255P | 21.943 ms | 0 - 375 MB | NPU
137
- | Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 22.066 ms | 0 - 178 MB | NPU
138
- | Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 9.65 ms | 0 - 380 MB | NPU
139
- | Swin-Base | TFLITE | float | Qualcomm® SA7255P | 53.467 ms | 0 - 710 MB | NPU
140
- | Swin-Base | TFLITE | float | Qualcomm® SA8295P | 28.376 ms | 0 - 371 MB | NPU
141
- | Swin-Base | TFLITE | float | Snapdragon® 8 Elite Mobile | 9.65 ms | 0 - 380 MB | NPU
142
- | Swin-Base | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.946 ms | 0 - 399 MB | NPU
 
 
143
 
144
  ## License
145
  * The license for the original implementation of Swin-Base can be found
 
1
  ---
2
  library_name: pytorch
3
+ license: bsd-3-clause
4
  tags:
5
  - backbone
6
  - bu_auto
 
16
  SwinBase 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.
17
 
18
  This is based on the implementation of Swin-Base found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/swin_transformer.py).
19
+ 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/v0.61.0/src/qai_hub_models/models/swin_base) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
20
 
21
  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.
22
 
 
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
+ | 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/swin_base/releases/v0.61.0/swin_base-onnx-float.zip)
33
+ | 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/swin_base/releases/v0.61.0/swin_base-onnx-w8a16.zip)
34
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_base/releases/v0.61.0/swin_base-qnn_dlc-float.zip)
35
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_base/releases/v0.61.0/swin_base-qnn_dlc-w8a16.zip)
36
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_base/releases/v0.61.0/swin_base-tflite-float.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[Swin-Base on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/swin_base)**.
39
 
40
 
41
  ### Option 2: Export with Custom Configurations
42
 
43
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/swin_base) Python library to compile and export the model with your own:
44
  - Custom weights (e.g., fine-tuned checkpoints)
45
  - Custom input shapes
46
  - Target device and runtime configurations
47
 
48
  This option is ideal if you need to customize the model beyond the default configuration provided here.
49
 
50
+ See our repository for [Swin-Base on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.61.0/src/qai_hub_models/models/swin_base) for usage instructions.
51
 
52
  ## Model Details
53
 
 
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
+ | Swin-Base | ONNX | float | Snapdragon® X2 Elite | 8.375 ms | 2 - 2 MB | NPU
67
+ | Swin-Base | ONNX | float | Snapdragon® X Elite | 19.953 ms | 175 - 175 MB | NPU
68
+ | Swin-Base | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 13.224 ms | 0 - 548 MB | NPU
69
+ | Swin-Base | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 29.344 ms | 1 - 1066 MB | NPU
70
+ | Swin-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 21.348 ms | 0 - 4 MB | NPU
71
+ | Swin-Base | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 19.297 ms | 0 - 195 MB | NPU
72
+ | Swin-Base | ONNX | float | Qualcomm® QCS8450 | 29.344 ms | 1 - 1066 MB | NPU
73
+ | Swin-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 22.606 ms | 1 - 4 MB | NPU
74
+ | Swin-Base | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 19.953 ms | 175 - 175 MB | NPU
75
+ | Swin-Base | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 9.91 ms | 0 - 401 MB | NPU
76
+ | Swin-Base | ONNX | float | Snapdragon® 8 Elite Mobile | 9.91 ms | 0 - 401 MB | NPU
77
+ | Swin-Base | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 8.179 ms | 1 - 423 MB | NPU
78
+ | Swin-Base | ONNX | w8a16 | Snapdragon® X2 Elite | 7.001 ms | 1 - 1 MB | NPU
79
+ | Swin-Base | ONNX | w8a16 | Snapdragon® X Elite | 16.263 ms | 92 - 92 MB | NPU
80
+ | Swin-Base | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 10.468 ms | 0 - 537 MB | NPU
81
+ | Swin-Base | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 20.772 ms | 0 - 536 MB | NPU
82
+ | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 58.018 ms | 0 - 3 MB | NPU
83
+ | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 14.352 ms | 0 - 4 MB | NPU
84
+ | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 15.395 ms | 0 - 99 MB | NPU
85
+ | Swin-Base | ONNX | w8a16 | Qualcomm® QCS8450 | 20.772 ms | 0 - 536 MB | NPU
86
+ | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 16.13 ms | 0 - 3 MB | NPU
87
+ | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 16.263 ms | 92 - 92 MB | NPU
88
+ | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 107.798 ms | 0 - 690 MB | NPU
89
+ | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 17.738 ms | 0 - 620 MB | NPU
90
+ | Swin-Base | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 8.144 ms | 0 - 417 MB | NPU
91
+ | Swin-Base | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 8.144 ms | 0 - 417 MB | NPU
92
+ | Swin-Base | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 6.538 ms | 0 - 431 MB | NPU
93
+ | Swin-Base | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 17.738 ms | 0 - 620 MB | NPU
94
+ | Swin-Base | QNN_DLC | float | Snapdragon® X2 Elite | 8.443 ms | 1 - 1 MB | NPU
95
+ | Swin-Base | QNN_DLC | float | Snapdragon® X Elite | 19.307 ms | 1 - 1 MB | NPU
96
+ | Swin-Base | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 12.414 ms | 0 - 515 MB | NPU
97
+ | Swin-Base | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 28.86 ms | 0 - 502 MB | NPU
98
+ | Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 20.32 ms | 1 - 4 MB | NPU
99
+ | Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 53.605 ms | 1 - 363 MB | NPU
100
+ | Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 18.378 ms | 1 - 419 MB | NPU
101
+ | Swin-Base | QNN_DLC | float | Qualcomm® SA8775P | 21.415 ms | 1 - 362 MB | NPU
102
+ | Swin-Base | QNN_DLC | float | Qualcomm® SA8650P | 21.415 ms | 1 - 362 MB | NPU
103
+ | Swin-Base | QNN_DLC | float | Qualcomm® SA8255P | 21.415 ms | 1 - 362 MB | NPU
104
+ | Swin-Base | QNN_DLC | float | Qualcomm® QCS8450 | 28.86 ms | 0 - 502 MB | NPU
105
+ | Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 21.549 ms | 3 - 5 MB | NPU
106
+ | Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 19.307 ms | 1 - 1 MB | NPU
107
+ | Swin-Base | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 9.29 ms | 1 - 367 MB | NPU
108
+ | Swin-Base | QNN_DLC | float | Qualcomm® SA7255P | 53.605 ms | 1 - 363 MB | NPU
109
+ | Swin-Base | QNN_DLC | float | Qualcomm® SA8295P | 27.595 ms | 1 - 353 MB | NPU
110
+ | Swin-Base | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 9.29 ms | 1 - 367 MB | NPU
111
+ | Swin-Base | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.549 ms | 0 - 385 MB | NPU
112
+ | Swin-Base | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 8.513 ms | 0 - 0 MB | NPU
113
+ | Swin-Base | QNN_DLC | w8a16 | Snapdragon® X Elite | 20.547 ms | 0 - 0 MB | NPU
114
+ | Swin-Base | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 12.763 ms | 0 - 508 MB | NPU
115
+ | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 17.37 ms | 0 - 3 MB | NPU
116
+ | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 35.41 ms | 0 - 412 MB | NPU
117
+ | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 19.157 ms | 0 - 2 MB | NPU
118
+ | Swin-Base | QNN_DLC | w8a16 | Qualcomm® SA8775P | 19.602 ms | 0 - 412 MB | NPU
119
+ | Swin-Base | QNN_DLC | w8a16 | Qualcomm® SA8650P | 19.602 ms | 0 - 412 MB | NPU
120
+ | Swin-Base | QNN_DLC | w8a16 | Qualcomm® SA8255P | 19.602 ms | 0 - 412 MB | NPU
121
+ | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 24.464 ms | 0 - 2 MB | NPU
122
+ | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 20.547 ms | 0 - 0 MB | NPU
123
+ | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 123.253 ms | 0 - 934 MB | NPU
124
+ | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 21.646 ms | 0 - 603 MB | NPU
125
+ | Swin-Base | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 9.537 ms | 0 - 404 MB | NPU
126
+ | Swin-Base | QNN_DLC | w8a16 | Qualcomm® SA7255P | 35.41 ms | 0 - 412 MB | NPU
127
+ | Swin-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 9.537 ms | 0 - 404 MB | NPU
128
+ | Swin-Base | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 7.608 ms | 0 - 423 MB | NPU
129
+ | Swin-Base | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 21.646 ms | 0 - 603 MB | NPU
130
+ | Swin-Base | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 12.73 ms | 0 - 1052 MB | NPU
131
+ | Swin-Base | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 28.87 ms | 0 - 512 MB | NPU
132
+ | Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 20.923 ms | 0 - 179 MB | NPU
133
+ | Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 53.494 ms | 0 - 709 MB | NPU
134
+ | Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 18.814 ms | 0 - 4 MB | NPU
135
+ | Swin-Base | TFLITE | float | Qualcomm® SA8775P | 21.931 ms | 0 - 375 MB | NPU
136
+ | Swin-Base | TFLITE | float | Qualcomm® SA8650P | 21.931 ms | 0 - 375 MB | NPU
137
+ | Swin-Base | TFLITE | float | Qualcomm® SA8255P | 21.931 ms | 0 - 375 MB | NPU
138
+ | Swin-Base | TFLITE | float | Qualcomm® QCS8450 | 28.87 ms | 0 - 512 MB | NPU
139
+ | Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 27.028 ms | 0 - 178 MB | NPU
140
+ | Swin-Base | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 9.644 ms | 0 - 378 MB | NPU
141
+ | Swin-Base | TFLITE | float | Qualcomm® SA7255P | 53.494 ms | 0 - 709 MB | NPU
142
+ | Swin-Base | TFLITE | float | Qualcomm® SA8295P | 28.394 ms | 0 - 371 MB | NPU
143
+ | Swin-Base | TFLITE | float | Snapdragon® 8 Elite Mobile | 9.644 ms | 0 - 378 MB | NPU
144
+ | Swin-Base | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 7.942 ms | 0 - 399 MB | NPU
145
 
146
  ## License
147
  * The license for the original implementation of Swin-Base can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.60.0",
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/swin_base/releases/v0.60.0/swin_base-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/swin_base/releases/v0.60.0/swin_base-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/swin_base/releases/v0.60.0/swin_base-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/swin_base/releases/v0.60.0/swin_base-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/swin_base/releases/v0.60.0/swin_base-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  }
 
1
  {
2
+ "version": "0.61.0",
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/swin_base/releases/v0.61.0/swin_base-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/swin_base/releases/v0.61.0/swin_base-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/swin_base/releases/v0.61.0/swin_base-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/swin_base/releases/v0.61.0/swin_base-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/swin_base/releases/v0.61.0/swin_base-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  }