Hugging Face's logo

qualcomm
/
Mobile-VIT

Image Classification
PyTorch
backbone
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
a913089
·
verified ·
1 Parent(s): 53fb451

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
  MobileVit 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 Mobile-VIT found [here](https://github.com/apple/ml-cvnets).
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/mobile_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
 
@@ -28,25 +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/mobile_vit/releases/v0.48.0/mobile_vit-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/mobile_vit/releases/v0.48.0/mobile_vit-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/mobile_vit/releases/v0.48.0/mobile_vit-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/mobile_vit/releases/v0.48.0/mobile_vit-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/mobile_vit/releases/v0.48.0/mobile_vit-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[Mobile-VIT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/mobile_vit)**.
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/mobile_vit) 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 [Mobile-VIT on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/mobile_vit) for usage instructions.
50
 
51
  ## Model Details
52
 
@@ -62,45 +62,45 @@ See our repository for [Mobile-VIT on GitHub](https://github.com/qualcomm/ai-hub
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
- | Mobile-VIT | ONNX | float | Snapdragon® X2 Elite | 1.89 ms | 12 - 12 MB | NPU
66
- | Mobile-VIT | ONNX | float | Snapdragon® X Elite | 3.956 ms | 12 - 12 MB | NPU
67
- | Mobile-VIT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.523 ms | 0 - 110 MB | NPU
68
- | Mobile-VIT | ONNX | float | Qualcomm® QCS8550 (Proxy) | 3.597 ms | 0 - 16 MB | NPU
 
69
  | Mobile-VIT | ONNX | float | Qualcomm® QCS9075 | 4.693 ms | 1 - 4 MB | NPU
70
- | Mobile-VIT | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.979 ms | 0 - 89 MB | NPU
71
- | Mobile-VIT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.668 ms | 0 - 102 MB | NPU
72
- | Mobile-VIT | ONNX | w8a16 | Snapdragon® X2 Elite | 2.076 ms | 7 - 7 MB | NPU
73
- | Mobile-VIT | ONNX | w8a16 | Snapdragon® X Elite | 5.091 ms | 8 - 8 MB | NPU
74
- | Mobile-VIT | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.128 ms | 0 - 144 MB | NPU
75
- | Mobile-VIT | ONNX | w8a16 | Qualcomm® QCS6490 | 325.906 ms | 65 - 69 MB | CPU
76
- | Mobile-VIT | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 4.64 ms | 0 - 10 MB | NPU
77
- | Mobile-VIT | ONNX | w8a16 | Qualcomm® QCS9075 | 5.094 ms | 0 - 3 MB | NPU
78
- | Mobile-VIT | ONNX | w8a16 | Qualcomm® QCM6690 | 141.041 ms | 63 - 73 MB | CPU
79
- | Mobile-VIT | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 2.336 ms | 0 - 80 MB | NPU
80
- | Mobile-VIT | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 122.873 ms | 65 - 76 MB | CPU
81
- | Mobile-VIT | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.918 ms | 0 - 115 MB | NPU
82
- | Mobile-VIT | QNN_DLC | float | Snapdragon® X2 Elite | 2.125 ms | 1 - 1 MB | NPU
83
- | Mobile-VIT | QNN_DLC | float | Snapdragon® X Elite | 3.851 ms | 1 - 1 MB | NPU
84
- | Mobile-VIT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.457 ms | 0 - 99 MB | NPU
85
- | Mobile-VIT | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 9.916 ms | 1 - 68 MB | NPU
86
- | Mobile-VIT | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 3.494 ms | 1 - 3 MB | NPU
87
- | Mobile-VIT | QNN_DLC | float | Qualcomm® SA8775P | 4.271 ms | 1 - 70 MB | NPU
88
- | Mobile-VIT | QNN_DLC | float | Qualcomm® QCS9075 | 4.485 ms | 3 - 5 MB | NPU
89
- | Mobile-VIT | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 5.641 ms | 0 - 94 MB | NPU
90
- | Mobile-VIT | QNN_DLC | float | Qualcomm® SA7255P | 9.916 ms | 1 - 68 MB | NPU
91
- | Mobile-VIT | QNN_DLC | float | Qualcomm® SA8295P | 6.47 ms | 1 - 62 MB | NPU
92
- | Mobile-VIT | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.925 ms | 0 - 73 MB | NPU
93
- | Mobile-VIT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.603 ms | 1 - 72 MB | NPU
94
- | Mobile-VIT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.586 ms | 0 - 108 MB | NPU
95
- | Mobile-VIT | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 10.216 ms | 0 - 81 MB | NPU
96
- | Mobile-VIT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 3.672 ms | 0 - 13 MB | NPU
97
- | Mobile-VIT | TFLITE | float | Qualcomm® SA8775P | 4.517 ms | 0 - 83 MB | NPU
98
- | Mobile-VIT | TFLITE | float | Qualcomm® QCS9075 | 4.575 ms | 0 - 15 MB | NPU
99
- | Mobile-VIT | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 6.002 ms | 0 - 93 MB | NPU
100
- | Mobile-VIT | TFLITE | float | Qualcomm® SA7255P | 10.216 ms | 0 - 81 MB | NPU
101
- | Mobile-VIT | TFLITE | float | Qualcomm® SA8295P | 6.691 ms | 0 - 69 MB | NPU
102
- | Mobile-VIT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.022 ms | 0 - 81 MB | NPU
103
- | Mobile-VIT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.654 ms | 0 - 86 MB | NPU
104
 
105
  ## License
106
  * The license for the original implementation of Mobile-VIT can be found
 
15
  MobileVit 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 Mobile-VIT found [here](https://github.com/apple/ml-cvnets).
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/mobile_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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobile_vit/releases/v0.49.1/mobile_vit-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/mobile_vit/releases/v0.49.1/mobile_vit-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/mobile_vit/releases/v0.49.1/mobile_vit-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/mobile_vit/releases/v0.49.1/mobile_vit-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/mobile_vit/releases/v0.49.1/mobile_vit-tflite-float.zip)
36
 
37
  For more device-specific assets and performance metrics, visit **[Mobile-VIT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/mobile_vit)**.
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/mobile_vit) 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 [Mobile-VIT on GitHub](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/mobile_vit) for usage instructions.
50
 
51
  ## Model Details
52
 
 
62
  ## Performance Summary
63
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
64
  |---|---|---|---|---|---|---
65
+ | Mobile-VIT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.665 ms | 1 - 102 MB | NPU
66
+ | Mobile-VIT | ONNX | float | Snapdragon® X2 Elite | 1.894 ms | 12 - 12 MB | NPU
67
+ | Mobile-VIT | ONNX | float | Snapdragon® X Elite | 3.952 ms | 12 - 12 MB | NPU
68
+ | Mobile-VIT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 2.526 ms | 0 - 109 MB | NPU
69
+ | Mobile-VIT | ONNX | float | Qualcomm® QCS8550 (Proxy) | 3.591 ms | 0 - 17 MB | NPU
70
  | Mobile-VIT | ONNX | float | Qualcomm® QCS9075 | 4.693 ms | 1 - 4 MB | NPU
71
+ | Mobile-VIT | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.976 ms | 0 - 88 MB | NPU
72
+ | Mobile-VIT | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.919 ms | 0 - 114 MB | NPU
73
+ | Mobile-VIT | ONNX | w8a16 | Snapdragon® X2 Elite | 2.068 ms | 7 - 7 MB | NPU
74
+ | Mobile-VIT | ONNX | w8a16 | Snapdragon® X Elite | 5.06 ms | 8 - 8 MB | NPU
75
+ | Mobile-VIT | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.118 ms | 0 - 131 MB | NPU
76
+ | Mobile-VIT | ONNX | w8a16 | Qualcomm® QCS6490 | 313.39 ms | 63 - 67 MB | CPU
77
+ | Mobile-VIT | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 4.636 ms | 0 - 10 MB | NPU
78
+ | Mobile-VIT | ONNX | w8a16 | Qualcomm® QCS9075 | 5.087 ms | 0 - 3 MB | NPU
79
+ | Mobile-VIT | ONNX | w8a16 | Qualcomm® QCM6690 | 141.953 ms | 65 - 75 MB | CPU
80
+ | Mobile-VIT | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 2.336 ms | 0 - 83 MB | NPU
81
+ | Mobile-VIT | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 122.831 ms | 65 - 76 MB | CPU
82
+ | Mobile-VIT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.608 ms | 1 - 72 MB | NPU
83
+ | Mobile-VIT | QNN_DLC | float | Snapdragon® X2 Elite | 2.136 ms | 1 - 1 MB | NPU
84
+ | Mobile-VIT | QNN_DLC | float | Snapdragon® X Elite | 3.849 ms | 1 - 1 MB | NPU
85
+ | Mobile-VIT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 2.462 ms | 0 - 99 MB | NPU
86
+ | Mobile-VIT | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 9.92 ms | 1 - 68 MB | NPU
87
+ | Mobile-VIT | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 3.491 ms | 1 - 2 MB | NPU
88
+ | Mobile-VIT | QNN_DLC | float | Qualcomm® SA8775P | 4.269 ms | 1 - 70 MB | NPU
89
+ | Mobile-VIT | QNN_DLC | float | Qualcomm® QCS9075 | 4.486 ms | 3 - 5 MB | NPU
90
+ | Mobile-VIT | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 5.664 ms | 0 - 92 MB | NPU
91
+ | Mobile-VIT | QNN_DLC | float | Qualcomm® SA7255P | 9.92 ms | 1 - 68 MB | NPU
92
+ | Mobile-VIT | QNN_DLC | float | Qualcomm® SA8295P | 6.477 ms | 1 - 62 MB | NPU
93
+ | Mobile-VIT | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.925 ms | 1 - 72 MB | NPU
94
+ | Mobile-VIT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.653 ms | 0 - 86 MB | NPU
95
+ | Mobile-VIT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.579 ms | 0 - 107 MB | NPU
96
+ | Mobile-VIT | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 10.232 ms | 0 - 81 MB | NPU
97
+ | Mobile-VIT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 3.682 ms | 0 - 7 MB | NPU
98
+ | Mobile-VIT | TFLITE | float | Qualcomm® SA8775P | 4.47 ms | 0 - 83 MB | NPU
99
+ | Mobile-VIT | TFLITE | float | Qualcomm® QCS9075 | 4.581 ms | 0 - 15 MB | NPU
100
+ | Mobile-VIT | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 6.039 ms | 0 - 103 MB | NPU
101
+ | Mobile-VIT | TFLITE | float | Qualcomm® SA7255P | 10.232 ms | 0 - 81 MB | NPU
102
+ | Mobile-VIT | TFLITE | float | Qualcomm® SA8295P | 6.699 ms | 0 - 84 MB | NPU
103
+ | Mobile-VIT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.022 ms | 0 - 78 MB | NPU
 
104
 
105
  ## License
106
  * The license for the original implementation of Mobile-VIT can be found