Hugging Face's logo

qualcomm
/
Beit

Image Classification
PyTorch
backbone
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
b4a088d
·
verified ·
1 Parent(s): 00e91ba

v0.49.1

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.49.1 for changelog.

Files changed (1) hide show
  1. README.md +46 -46
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/main/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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.48.0/beit-onnx-float.zip)
32
- | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.48.0/beit-onnx-w8a16.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.48.0/beit-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.48.0/beit-qnn_dlc-w8a16.zip)
35
- | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.48.0/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/main/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/main/qai_hub_models/models/beit) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -61,45 +61,45 @@ 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 | 5.944 ms | 185 - 185 MB | NPU
65
- | Beit | ONNX | float | Snapdragon® X Elite | 13.666 ms | 185 - 185 MB | NPU
66
- | Beit | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 9.284 ms | 0 - 532 MB | NPU
67
- | Beit | ONNX | float | Qualcomm® QCS8550 (Proxy) | 12.909 ms | 0 - 195 MB | NPU
68
- | Beit | ONNX | float | Qualcomm® QCS9075 | 17.775 ms | 0 - 4 MB | NPU
69
- | Beit | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 6.604 ms | 0 - 482 MB | NPU
70
- | Beit | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.236 ms | 1 - 487 MB | NPU
71
- | Beit | ONNX | w8a16 | Snapdragon® X2 Elite | 4.367 ms | 96 - 96 MB | NPU
72
- | Beit | ONNX | w8a16 | Snapdragon® X Elite | 12.501 ms | 96 - 96 MB | NPU
73
- | Beit | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 7.962 ms | 0 - 495 MB | NPU
74
- | Beit | ONNX | w8a16 | Qualcomm® QCS6490 | 1069.347 ms | 51 - 68 MB | CPU
75
- | Beit | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 11.726 ms | 0 - 116 MB | NPU
76
- | Beit | ONNX | w8a16 | Qualcomm® QCS9075 | 14.685 ms | 0 - 3 MB | NPU
77
- | Beit | ONNX | w8a16 | Qualcomm® QCM6690 | 601.942 ms | 67 - 78 MB | CPU
78
- | Beit | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 6.119 ms | 0 - 407 MB | NPU
79
- | Beit | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 582.238 ms | 114 - 127 MB | CPU
80
  | Beit | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 4.182 ms | 0 - 407 MB | NPU
81
- | Beit | QNN_DLC | float | Snapdragon® X2 Elite | 6.976 ms | 1 - 1 MB | NPU
82
- | Beit | QNN_DLC | float | Snapdragon® X Elite | 13.417 ms | 1 - 1 MB | NPU
83
- | Beit | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.724 ms | 0 - 531 MB | NPU
84
- | Beit | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 44.941 ms | 1 - 485 MB | NPU
85
- | Beit | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 12.659 ms | 1 - 4 MB | NPU
86
- | Beit | QNN_DLC | float | Qualcomm® SA8775P | 16.408 ms | 1 - 485 MB | NPU
87
- | Beit | QNN_DLC | float | Qualcomm® QCS9075 | 17.052 ms | 3 - 5 MB | NPU
88
- | Beit | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 23.058 ms | 0 - 507 MB | NPU
89
- | Beit | QNN_DLC | float | Qualcomm® SA7255P | 44.941 ms | 1 - 485 MB | NPU
90
- | Beit | QNN_DLC | float | Qualcomm® SA8295P | 19.086 ms | 1 - 468 MB | NPU
91
- | Beit | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 6.867 ms | 1 - 478 MB | NPU
92
- | Beit | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.57 ms | 1 - 481 MB | NPU
93
- | Beit | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 6.664 ms | 0 - 348 MB | NPU
94
- | Beit | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 38.588 ms | 0 - 298 MB | NPU
95
- | Beit | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 9.321 ms | 0 - 3 MB | NPU
96
- | Beit | TFLITE | float | Qualcomm® SA8775P | 12.146 ms | 0 - 306 MB | NPU
97
- | Beit | TFLITE | float | Qualcomm® QCS9075 | 13.563 ms | 0 - 187 MB | NPU
98
- | Beit | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 19.275 ms | 0 - 431 MB | NPU
99
- | Beit | TFLITE | float | Qualcomm® SA7255P | 38.588 ms | 0 - 298 MB | NPU
100
- | Beit | TFLITE | float | Qualcomm® SA8295P | 15.994 ms | 0 - 405 MB | NPU
101
- | Beit | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.764 ms | 0 - 300 MB | NPU
102
- | Beit | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.967 ms | 0 - 297 MB | NPU
 
 
 
 
 
 
 
 
 
103
 
104
  ## License
105
  * 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/tree/v0.49.1/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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.49.1/beit-onnx-float.zip)
32
+ | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.49.1/beit-onnx-w8a16.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.49.1/beit-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.49.1/beit-qnn_dlc-w8a16.zip)
35
+ | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/beit/releases/v0.49.1/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/tree/v0.49.1/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/tree/v0.49.1/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® 8 Elite Gen 5 Mobile | 6.237 ms | 1 - 486 MB | NPU
65
+ | Beit | ONNX | float | Snapdragon® X2 Elite | 6.019 ms | 185 - 185 MB | NPU
66
+ | Beit | ONNX | float | Snapdragon® X Elite | 13.686 ms | 185 - 185 MB | NPU
67
+ | Beit | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 9.267 ms | 0 - 527 MB | NPU
68
+ | Beit | ONNX | float | Qualcomm® QCS8550 (Proxy) | 12.928 ms | 0 - 195 MB | NPU
69
+ | Beit | ONNX | float | Qualcomm® QCS9075 | 17.598 ms | 0 - 4 MB | NPU
70
+ | Beit | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 6.65 ms | 1 - 493 MB | NPU
 
 
 
 
 
 
 
 
 
71
  | Beit | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 4.182 ms | 0 - 407 MB | NPU
72
+ | Beit | ONNX | w8a16 | Snapdragon® X2 Elite | 4.371 ms | 96 - 96 MB | NPU
73
+ | Beit | ONNX | w8a16 | Snapdragon® X Elite | 12.511 ms | 96 - 96 MB | NPU
74
+ | Beit | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 7.927 ms | 0 - 492 MB | NPU
75
+ | Beit | ONNX | w8a16 | Qualcomm® QCS6490 | 1060.589 ms | 53 - 70 MB | CPU
76
+ | Beit | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 11.769 ms | 0 - 6 MB | NPU
77
+ | Beit | ONNX | w8a16 | Qualcomm® QCS9075 | 14.665 ms | 0 - 3 MB | NPU
78
+ | Beit | ONNX | w8a16 | Qualcomm® QCM6690 | 599.901 ms | 112 - 128 MB | CPU
79
+ | Beit | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 6.102 ms | 0 - 408 MB | NPU
80
+ | Beit | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 582.769 ms | 73 - 87 MB | CPU
81
+ | Beit | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.571 ms | 1 - 481 MB | NPU
82
+ | Beit | QNN_DLC | float | Snapdragon® X2 Elite | 6.925 ms | 1 - 1 MB | NPU
83
+ | Beit | QNN_DLC | float | Snapdragon® X Elite | 13.429 ms | 1 - 1 MB | NPU
84
+ | Beit | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 8.695 ms | 0 - 535 MB | NPU
85
+ | Beit | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 44.932 ms | 1 - 485 MB | NPU
86
+ | Beit | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 12.588 ms | 1 - 3 MB | NPU
87
+ | Beit | QNN_DLC | float | Qualcomm® SA8775P | 16.39 ms | 1 - 485 MB | NPU
88
+ | Beit | QNN_DLC | float | Qualcomm® QCS9075 | 16.723 ms | 1 - 3 MB | NPU
89
+ | Beit | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 22.928 ms | 1 - 509 MB | NPU
90
+ | Beit | QNN_DLC | float | Qualcomm® SA7255P | 44.932 ms | 1 - 485 MB | NPU
91
+ | Beit | QNN_DLC | float | Qualcomm® SA8295P | 19.07 ms | 1 - 468 MB | NPU
92
+ | Beit | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 6.965 ms | 1 - 480 MB | NPU
93
+ | Beit | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.971 ms | 0 - 297 MB | NPU
94
+ | Beit | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 6.668 ms | 0 - 343 MB | NPU
95
+ | Beit | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 38.591 ms | 0 - 297 MB | NPU
96
+ | Beit | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 9.334 ms | 0 - 3 MB | NPU
97
+ | Beit | TFLITE | float | Qualcomm® SA8775P | 55.63 ms | 0 - 305 MB | NPU
98
+ | Beit | TFLITE | float | Qualcomm® QCS9075 | 13.213 ms | 0 - 187 MB | NPU
99
+ | Beit | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 19.184 ms | 0 - 430 MB | NPU
100
+ | Beit | TFLITE | float | Qualcomm® SA7255P | 38.591 ms | 0 - 297 MB | NPU
101
+ | Beit | TFLITE | float | Qualcomm® SA8295P | 16.061 ms | 0 - 405 MB | NPU
102
+ | Beit | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.721 ms | 0 - 297 MB | NPU
103
 
104
  ## License
105
  * The license for the original implementation of Beit can be found