Hugging Face's logo

qualcomm
/
Swin-Tiny

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
6bf8979
·
verified ·
1 Parent(s): 0664cb8

v0.58.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.58.0 for changelog.

Files changed (2) hide show
  1. README.md +79 -73
  2. release_assets.json +6 -6
README.md CHANGED
@@ -16,7 +16,7 @@ pipeline_tag: image-classification
16
  SwinTiny 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-Tiny 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/v0.57.3/src/qai_hub_models/models/swin_tiny) 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 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.57.3/swin_tiny-onnx-float.zip)
33
- | 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/swin_tiny/releases/v0.57.3/swin_tiny-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_tiny/releases/v0.57.3/swin_tiny-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_tiny/releases/v0.57.3/swin_tiny-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_tiny/releases/v0.57.3/swin_tiny-tflite-float.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[Swin-Tiny on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/swin_tiny)**.
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/v0.57.3/src/qai_hub_models/models/swin_tiny) 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-Tiny on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.57.3/src/qai_hub_models/models/swin_tiny) for usage instructions.
51
 
52
  ## Model Details
53
 
@@ -63,71 +63,77 @@ See our repository for [Swin-Tiny 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-Tiny | ONNX | float | Snapdragon® X2 Elite | 3.973 ms | 212 - 212 MB | NPU
67
- | Swin-Tiny | ONNX | float | Snapdragon® X Elite | 9.602 ms | 148 - 148 MB | NPU
68
- | Swin-Tiny | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.968 ms | 1 - 242 MB | NPU
69
- | Swin-Tiny | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 14.193 ms | 1 - 235 MB | NPU
70
- | Swin-Tiny | ONNX | float | Qualcomm® QCS8550 (Proxy) | 9.105 ms | 0 - 67 MB | NPU
71
- | Swin-Tiny | ONNX | float | Qualcomm® QCS8450 | 14.193 ms | 1 - 235 MB | NPU
72
- | Swin-Tiny | ONNX | float | Snapdragon® 8 Elite Mobile | 4.584 ms | 0 - 435 MB | NPU
73
- | Swin-Tiny | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.767 ms | 1 - 429 MB | NPU
74
- | Swin-Tiny | ONNX | float | Qualcomm® QCS9075 | 10.99 ms | 1 - 46 MB | NPU
75
- | Swin-Tiny | ONNX | float | Qualcomm® QCS8750 | 4.584 ms | 0 - 435 MB | NPU
76
- | Swin-Tiny | ONNX | float | Qualcomm® QCS7181 | 9.602 ms | 148 - 148 MB | NPU
77
- | Swin-Tiny | ONNX | w8a16 | Snapdragon® X2 Elite | 3.471 ms | 212 - 212 MB | NPU
78
- | Swin-Tiny | ONNX | w8a16 | Snapdragon® X Elite | 8.23 ms | 149 - 149 MB | NPU
79
- | Swin-Tiny | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.164 ms | 0 - 323 MB | NPU
80
- | Swin-Tiny | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 7.82 ms | 0 - 36 MB | NPU
81
- | Swin-Tiny | ONNX | w8a16 | Qualcomm® QCS9075 | 9.363 ms | 0 - 45 MB | NPU
82
- | Swin-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.263 ms | 0 - 271 MB | NPU
83
- | Swin-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 3.979 ms | 0 - 267 MB | NPU
84
- | Swin-Tiny | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 8.254 ms | 0 - 234 MB | NPU
85
- | Swin-Tiny | ONNX | w8a16 | Qualcomm® QCM6690 | 35.976 ms | 0 - 383 MB | NPU
86
- | Swin-Tiny | ONNX | w8a16 | Qualcomm® QCS7790 | 8.254 ms | 0 - 234 MB | NPU
87
- | Swin-Tiny | ONNX | w8a16 | Qualcomm® QCS8750 | 3.979 ms | 0 - 267 MB | NPU
88
- | Swin-Tiny | ONNX | w8a16 | Qualcomm® QCS7181 | 8.23 ms | 149 - 149 MB | NPU
89
- | Swin-Tiny | QNN_DLC | float | Snapdragon® X2 Elite | 4.259 ms | 1 - 1 MB | NPU
90
- | Swin-Tiny | QNN_DLC | float | Snapdragon® X Elite | 9.885 ms | 1 - 1 MB | NPU
91
- | Swin-Tiny | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.97 ms | 0 - 245 MB | NPU
92
- | Swin-Tiny | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 14.538 ms | 0 - 242 MB | NPU
93
- | Swin-Tiny | QNN_DLC | float | Qualcomm® QCS8275 | 21.241 ms | 1 - 176 MB | NPU
94
- | Swin-Tiny | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 9.049 ms | 1 - 3 MB | NPU
95
- | Swin-Tiny | QNN_DLC | float | Qualcomm® QCS8450 | 14.538 ms | 0 - 242 MB | NPU
96
- | Swin-Tiny | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 4.529 ms | 0 - 414 MB | NPU
97
- | Swin-Tiny | QNN_DLC | float | Qualcomm® SA8295P | 13.797 ms | 0 - 433 MB | NPU
98
- | Swin-Tiny | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.762 ms | 1 - 414 MB | NPU
99
- | Swin-Tiny | QNN_DLC | float | Qualcomm® SA7255P | 21.241 ms | 1 - 176 MB | NPU
100
- | Swin-Tiny | QNN_DLC | float | Qualcomm® QCS9075 | 11.446 ms | 1 - 3 MB | NPU
101
- | Swin-Tiny | QNN_DLC | float | Qualcomm® QCS8750 | 4.529 ms | 0 - 414 MB | NPU
102
- | Swin-Tiny | QNN_DLC | float | Qualcomm® QCS7181 | 9.885 ms | 1 - 1 MB | NPU
103
- | Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 4.429 ms | 0 - 0 MB | NPU
104
- | Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® X Elite | 10.91 ms | 0 - 0 MB | NPU
105
- | Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.59 ms | 0 - 506 MB | NPU
106
- | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8275 | 17.761 ms | 0 - 436 MB | NPU
107
- | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 10.192 ms | 0 - 31 MB | NPU
108
- | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 11.509 ms | 0 - 2 MB | NPU
109
- | Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.885 ms | 0 - 438 MB | NPU
110
- | Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 4.859 ms | 0 - 428 MB | NPU
111
- | Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.563 ms | 0 - 436 MB | NPU
112
- | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 43.878 ms | 0 - 424 MB | NPU
113
- | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® SA7255P | 17.761 ms | 0 - 436 MB | NPU
114
- | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS7790 | 10.563 ms | 0 - 436 MB | NPU
115
- | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8750 | 4.859 ms | 0 - 428 MB | NPU
116
- | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS7181 | 10.91 ms | 0 - 0 MB | NPU
117
- | Swin-Tiny | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 6.024 ms | 0 - 272 MB | NPU
118
- | Swin-Tiny | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 14.301 ms | 0 - 258 MB | NPU
119
- | Swin-Tiny | TFLITE | float | Qualcomm® QCS8275 | 21.21 ms | 0 - 201 MB | NPU
120
- | Swin-Tiny | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 9.261 ms | 0 - 3 MB | NPU
121
- | Swin-Tiny | TFLITE | float | Qualcomm® SA8775P | 38.271 ms | 0 - 30 MB | GPU
122
- | Swin-Tiny | TFLITE | float | Qualcomm® SA8650P | 38.271 ms | 0 - 30 MB | GPU
123
- | Swin-Tiny | TFLITE | float | Qualcomm® SA8255P | 38.271 ms | 0 - 30 MB | GPU
124
- | Swin-Tiny | TFLITE | float | Qualcomm® QCS8450 | 14.301 ms | 0 - 258 MB | NPU
125
- | Swin-Tiny | TFLITE | float | Snapdragon® 8 Elite Mobile | 4.639 ms | 0 - 196 MB | NPU
126
- | Swin-Tiny | TFLITE | float | Qualcomm® SA8295P | 13.905 ms | 0 - 198 MB | NPU
127
- | Swin-Tiny | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.83 ms | 0 - 214 MB | NPU
128
- | Swin-Tiny | TFLITE | float | Qualcomm® SA7255P | 21.21 ms | 0 - 201 MB | NPU
129
- | Swin-Tiny | TFLITE | float | Qualcomm® QCS9075 | 11.387 ms | 0 - 60 MB | NPU
130
- | Swin-Tiny | TFLITE | float | Qualcomm® QCS8750 | 4.639 ms | 0 - 196 MB | NPU
 
 
 
 
 
 
131
 
132
  ## License
133
  * The license for the original implementation of Swin-Tiny can be found
 
16
  SwinTiny 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-Tiny 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/v0.58.0/src/qai_hub_models/models/swin_tiny) 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 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.58.0/swin_tiny-onnx-float.zip)
33
+ | 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/swin_tiny/releases/v0.58.0/swin_tiny-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_tiny/releases/v0.58.0/swin_tiny-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_tiny/releases/v0.58.0/swin_tiny-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_tiny/releases/v0.58.0/swin_tiny-tflite-float.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[Swin-Tiny on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/swin_tiny)**.
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/v0.58.0/src/qai_hub_models/models/swin_tiny) 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-Tiny on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/swin_tiny) 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-Tiny | ONNX | float | Snapdragon® X2 Elite | 3.972 ms | 2 - 2 MB | NPU
67
+ | Swin-Tiny | ONNX | float | Snapdragon® X Elite | 9.65 ms | 58 - 58 MB | NPU
68
+ | Swin-Tiny | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.995 ms | 0 - 252 MB | NPU
69
+ | Swin-Tiny | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 14.245 ms | 1 - 247 MB | NPU
70
+ | Swin-Tiny | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.112 ms | 0 - 66 MB | NPU
71
+ | Swin-Tiny | ONNX | float | Qualcomm® QCS8450 | 14.245 ms | 1 - 247 MB | NPU
72
+ | Swin-Tiny | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 10.187 ms | 1 - 4 MB | NPU
73
+ | Swin-Tiny | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.775 ms | 0 - 433 MB | NPU
74
+ | Swin-Tiny | ONNX | float | Snapdragon® 8 Elite Mobile | 4.578 ms | 0 - 434 MB | NPU
75
+ | Swin-Tiny | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.578 ms | 0 - 434 MB | NPU
76
+ | Swin-Tiny | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 9.65 ms | 58 - 58 MB | NPU
77
+ | Swin-Tiny | ONNX | w8a16 | Snapdragon® X2 Elite | 3.476 ms | 1 - 1 MB | NPU
78
+ | Swin-Tiny | ONNX | w8a16 | Snapdragon® X Elite | 8.287 ms | 31 - 31 MB | NPU
79
+ | Swin-Tiny | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.163 ms | 0 - 333 MB | NPU
80
+ | Swin-Tiny | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.81 ms | 0 - 36 MB | NPU
81
+ | Swin-Tiny | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 8.116 ms | 0 - 3 MB | NPU
82
+ | Swin-Tiny | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 8.241 ms | 0 - 237 MB | NPU
83
+ | Swin-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.273 ms | 0 - 275 MB | NPU
84
+ | Swin-Tiny | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 34.435 ms | 0 - 394 MB | NPU
85
+ | Swin-Tiny | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 3.973 ms | 0 - 267 MB | NPU
86
+ | Swin-Tiny | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 8.241 ms | 0 - 237 MB | NPU
87
+ | Swin-Tiny | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 3.973 ms | 0 - 267 MB | NPU
88
+ | Swin-Tiny | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 8.287 ms | 31 - 31 MB | NPU
89
+ | Swin-Tiny | QNN_DLC | float | Snapdragon® X2 Elite | 4.285 ms | 1 - 1 MB | NPU
90
+ | Swin-Tiny | QNN_DLC | float | Snapdragon® X Elite | 9.862 ms | 1 - 1 MB | NPU
91
+ | Swin-Tiny | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.945 ms | 0 - 246 MB | NPU
92
+ | Swin-Tiny | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 14.509 ms | 0 - 240 MB | NPU
93
+ | Swin-Tiny | QNN_DLC | float | Qualcomm® QCS8275 | 21.257 ms | 1 - 176 MB | NPU
94
+ | Swin-Tiny | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.12 ms | 1 - 2 MB | NPU
95
+ | Swin-Tiny | QNN_DLC | float | Qualcomm® SA8775P | 10.453 ms | 1 - 436 MB | NPU
96
+ | Swin-Tiny | QNN_DLC | float | Qualcomm® SA8650P | 10.453 ms | 1 - 436 MB | NPU
97
+ | Swin-Tiny | QNN_DLC | float | Qualcomm® SA8255P | 10.453 ms | 1 - 436 MB | NPU
98
+ | Swin-Tiny | QNN_DLC | float | Qualcomm® QCS8450 | 14.509 ms | 0 - 240 MB | NPU
99
+ | Swin-Tiny | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 10.243 ms | 1 - 3 MB | NPU
100
+ | Swin-Tiny | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.773 ms | 1 - 414 MB | NPU
101
+ | Swin-Tiny | QNN_DLC | float | Qualcomm® SA7255P | 21.257 ms | 1 - 176 MB | NPU
102
+ | Swin-Tiny | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 4.493 ms | 0 - 414 MB | NPU
103
+ | Swin-Tiny | QNN_DLC | float | Qualcomm® SA8295P | 13.817 ms | 0 - 432 MB | NPU
104
+ | Swin-Tiny | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 4.493 ms | 0 - 414 MB | NPU
105
+ | Swin-Tiny | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 9.862 ms | 1 - 1 MB | NPU
106
+ | Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 4.416 ms | 0 - 0 MB | NPU
107
+ | Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® X Elite | 11.025 ms | 0 - 0 MB | NPU
108
+ | Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.652 ms | 0 - 508 MB | NPU
109
+ | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® QCS8275 | 17.763 ms | 0 - 436 MB | NPU
110
+ | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 10.171 ms | 0 - 9 MB | NPU
111
+ | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® SA8775P | 10.663 ms | 0 - 444 MB | NPU
112
+ | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® SA8650P | 10.663 ms | 0 - 444 MB | NPU
113
+ | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® SA8255P | 10.663 ms | 0 - 444 MB | NPU
114
+ | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 10.445 ms | 2 - 4 MB | NPU
115
+ | Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 10.633 ms | 0 - 437 MB | NPU
116
+ | Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.892 ms | 0 - 439 MB | NPU
117
+ | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 42.42 ms | 0 - 430 MB | NPU
118
+ | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® SA7255P | 17.763 ms | 0 - 436 MB | NPU
119
+ | Swin-Tiny | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 4.843 ms | 0 - 428 MB | NPU
120
+ | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 10.633 ms | 0 - 437 MB | NPU
121
+ | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 4.843 ms | 0 - 428 MB | NPU
122
+ | Swin-Tiny | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 11.025 ms | 0 - 0 MB | NPU
123
+ | Swin-Tiny | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 6.008 ms | 0 - 258 MB | NPU
124
+ | Swin-Tiny | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 14.318 ms | 0 - 256 MB | NPU
125
+ | Swin-Tiny | TFLITE | float | Qualcomm® QCS8275 | 21.269 ms | 0 - 200 MB | NPU
126
+ | Swin-Tiny | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 9.243 ms | 0 - 4 MB | NPU
127
+ | Swin-Tiny | TFLITE | float | Qualcomm® SA8775P | 10.403 ms | 0 - 201 MB | NPU
128
+ | Swin-Tiny | TFLITE | float | Qualcomm® SA8650P | 10.403 ms | 0 - 201 MB | NPU
129
+ | Swin-Tiny | TFLITE | float | Qualcomm® SA8255P | 10.403 ms | 0 - 201 MB | NPU
130
+ | Swin-Tiny | TFLITE | float | Qualcomm® QCS8450 | 14.318 ms | 0 - 256 MB | NPU
131
+ | Swin-Tiny | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 10.161 ms | 0 - 60 MB | NPU
132
+ | Swin-Tiny | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.824 ms | 0 - 214 MB | NPU
133
+ | Swin-Tiny | TFLITE | float | Qualcomm® SA7255P | 21.269 ms | 0 - 200 MB | NPU
134
+ | Swin-Tiny | TFLITE | float | Snapdragon® 8 Elite Mobile | 4.64 ms | 0 - 205 MB | NPU
135
+ | Swin-Tiny | TFLITE | float | Qualcomm® SA8295P | 13.889 ms | 0 - 199 MB | NPU
136
+ | Swin-Tiny | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 4.64 ms | 0 - 205 MB | NPU
137
 
138
  ## License
139
  * The license for the original implementation of Swin-Tiny can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.57.3",
3
  "precisions": {
4
  "w8a16": {
5
  "universal_assets": {
@@ -7,14 +7,14 @@
7
  "tool_versions": {
8
  "qairt": "2.45.0.260326154327"
9
  },
10
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.57.3/swin_tiny-qnn_dlc-w8a16.zip"
11
  },
12
  "onnx": {
13
  "tool_versions": {
14
  "qairt": "2.45.0.260326154327",
15
  "onnx_runtime": "1.25.0"
16
  },
17
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.57.3/swin_tiny-onnx-w8a16.zip"
18
  }
19
  }
20
  },
@@ -25,20 +25,20 @@
25
  "qairt": "2.45.0.260326154327",
26
  "litert": "1.4.4"
27
  },
28
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.57.3/swin_tiny-tflite-float.zip"
29
  },
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/swin_tiny/releases/v0.57.3/swin_tiny-qnn_dlc-float.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/swin_tiny/releases/v0.57.3/swin_tiny-onnx-float.zip"
42
  }
43
  }
44
  }
 
1
  {
2
+ "version": "0.58.0",
3
  "precisions": {
4
  "w8a16": {
5
  "universal_assets": {
 
7
  "tool_versions": {
8
  "qairt": "2.45.0.260326154327"
9
  },
10
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.58.0/swin_tiny-qnn_dlc-w8a16.zip"
11
  },
12
  "onnx": {
13
  "tool_versions": {
14
  "qairt": "2.45.0.260326154327",
15
  "onnx_runtime": "1.25.0"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.58.0/swin_tiny-onnx-w8a16.zip"
18
  }
19
  }
20
  },
 
25
  "qairt": "2.45.0.260326154327",
26
  "litert": "1.4.4"
27
  },
28
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/swin_tiny/releases/v0.58.0/swin_tiny-tflite-float.zip"
29
  },
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/swin_tiny/releases/v0.58.0/swin_tiny-qnn_dlc-float.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/swin_tiny/releases/v0.58.0/swin_tiny-onnx-float.zip"
42
  }
43
  }
44
  }