Hugging Face's logo

qualcomm
/
LeViT

Image Classification
PyTorch
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
f4a9931
·
verified ·
1 Parent(s): 25be77e

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 +73 -53
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: image-classification
15
  LeViT is a vision transformer model that can classify images from the Imagenet dataset.
16
 
17
  This is based on the implementation of LeViT found [here](https://github.com/facebookresearch/LeViT).
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/levit) 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
 
@@ -28,27 +28,27 @@ 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/levit/releases/v0.48.0/levit-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/levit/releases/v0.48.0/levit-onnx-w8a16.zip)
33
- | ONNX | w8a16_mixed_int16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/levit/releases/v0.48.0/levit-onnx-w8a16_mixed_int16.zip)
34
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/levit/releases/v0.48.0/levit-qnn_dlc-float.zip)
35
- | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/levit/releases/v0.48.0/levit-qnn_dlc-w8a16.zip)
36
- | QNN_DLC | w8a16_mixed_int16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/levit/releases/v0.48.0/levit-qnn_dlc-w8a16_mixed_int16.zip)
37
- | 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/levit/releases/v0.48.0/levit-tflite-float.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[LeViT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/levit)**.
40
 
41
 
42
  ### Option 2: Export with Custom Configurations
43
 
44
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/levit) Python library to compile and export the model with your own:
45
  - Custom weights (e.g., fine-tuned checkpoints)
46
  - Custom input shapes
47
  - Target device and runtime configurations
48
 
49
  This option is ideal if you need to customize the model beyond the default configuration provided here.
50
 
51
- See our repository for [LeViT on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/levit) for usage instructions.
52
 
53
  ## Model Details
54
 
@@ -64,49 +64,69 @@ See our repository for [LeViT on GitHub](https://github.com/qualcomm/ai-hub-mode
64
  ## Performance Summary
65
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
66
  |---|---|---|---|---|---|---
67
- | LeViT | ONNX | float | Snapdragon® X2 Elite | 0.69 ms | 16 - 16 MB | NPU
68
- | LeViT | ONNX | float | Snapdragon® X Elite | 1.462 ms | 16 - 16 MB | NPU
69
- | LeViT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.877 ms | 0 - 101 MB | NPU
70
- | LeViT | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.252 ms | 0 - 22 MB | NPU
71
- | LeViT | ONNX | float | Qualcomm® QCS9075 | 1.65 ms | 1 - 3 MB | NPU
72
- | LeViT | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.704 ms | 0 - 67 MB | NPU
73
- | LeViT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.653 ms | 1 - 76 MB | NPU
74
- | LeViT | QNN_DLC | float | Snapdragon® X2 Elite | 1.009 ms | 1 - 1 MB | NPU
75
- | LeViT | QNN_DLC | float | Snapdragon® X Elite | 1.824 ms | 1 - 1 MB | NPU
76
- | LeViT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.084 ms | 0 - 83 MB | NPU
77
- | LeViT | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 3.833 ms | 1 - 58 MB | NPU
78
- | LeViT | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.595 ms | 1 - 2 MB | NPU
79
- | LeViT | QNN_DLC | float | Qualcomm® QCS9075 | 1.882 ms | 3 - 5 MB | NPU
80
- | LeViT | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 2.374 ms | 0 - 80 MB | NPU
81
- | LeViT | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.847 ms | 0 - 62 MB | NPU
82
- | LeViT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.75 ms | 1 - 62 MB | NPU
83
- | LeViT | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.865 ms | 0 - 0 MB | NPU
84
- | LeViT | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.673 ms | 0 - 0 MB | NPU
85
- | LeViT | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.016 ms | 0 - 61 MB | NPU
86
- | LeViT | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 2.98 ms | 0 - 40 MB | NPU
87
- | LeViT | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 1.452 ms | 0 - 26 MB | NPU
88
- | LeViT | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 1.727 ms | 0 - 2 MB | NPU
89
- | LeViT | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 5.836 ms | 0 - 164 MB | NPU
90
- | LeViT | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.747 ms | 0 - 41 MB | NPU
91
- | LeViT | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.47 ms | 0 - 39 MB | NPU
92
- | LeViT | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.639 ms | 0 - 42 MB | NPU
93
- | LeViT | QNN_DLC | w8a16_mixed_int16 | Snapdragon® X2 Elite | 0.903 ms | 0 - 0 MB | NPU
94
- | LeViT | QNN_DLC | w8a16_mixed_int16 | Snapdragon® X Elite | 1.7 ms | 0 - 0 MB | NPU
95
- | LeViT | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 1.046 ms | 0 - 63 MB | NPU
96
- | LeViT | QNN_DLC | w8a16_mixed_int16 | Qualcomm® QCS8275 (Proxy) | 3.027 ms | 0 - 40 MB | NPU
97
- | LeViT | QNN_DLC | w8a16_mixed_int16 | Qualcomm® QCS8550 (Proxy) | 1.485 ms | 0 - 2 MB | NPU
98
- | LeViT | QNN_DLC | w8a16_mixed_int16 | Qualcomm® QCS9075 | 1.738 ms | 0 - 2 MB | NPU
99
- | LeViT | QNN_DLC | w8a16_mixed_int16 | Qualcomm® QCM6690 | 6.101 ms | 0 - 166 MB | NPU
100
- | LeViT | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.753 ms | 0 - 42 MB | NPU
101
- | LeViT | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 1.507 ms | 0 - 39 MB | NPU
102
- | LeViT | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.649 ms | 0 - 41 MB | NPU
103
- | LeViT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.058 ms | 0 - 96 MB | NPU
104
- | LeViT | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 4.059 ms | 0 - 66 MB | NPU
105
- | LeViT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.556 ms | 0 - 2 MB | NPU
106
- | LeViT | TFLITE | float | Qualcomm® QCS9075 | 1.869 ms | 0 - 19 MB | NPU
107
- | LeViT | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 2.356 ms | 0 - 83 MB | NPU
108
- | LeViT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.807 ms | 0 - 66 MB | NPU
109
- | LeViT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.679 ms | 0 - 72 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
110
 
111
  ## License
112
  * The license for the original implementation of LeViT can be found
 
15
  LeViT is a vision transformer model that can classify images from the Imagenet dataset.
16
 
17
  This is based on the implementation of LeViT found [here](https://github.com/facebookresearch/LeViT).
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/levit) 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/levit/releases/v0.49.1/levit-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/levit/releases/v0.49.1/levit-onnx-w8a16.zip)
33
+ | ONNX | w8a16_mixed_int16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/levit/releases/v0.49.1/levit-onnx-w8a16_mixed_int16.zip)
34
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/levit/releases/v0.49.1/levit-qnn_dlc-float.zip)
35
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/levit/releases/v0.49.1/levit-qnn_dlc-w8a16.zip)
36
+ | QNN_DLC | w8a16_mixed_int16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/levit/releases/v0.49.1/levit-qnn_dlc-w8a16_mixed_int16.zip)
37
+ | 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/levit/releases/v0.49.1/levit-tflite-float.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[LeViT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/levit)**.
40
 
41
 
42
  ### Option 2: Export with Custom Configurations
43
 
44
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/levit) Python library to compile and export the model with your own:
45
  - Custom weights (e.g., fine-tuned checkpoints)
46
  - Custom input shapes
47
  - Target device and runtime configurations
48
 
49
  This option is ideal if you need to customize the model beyond the default configuration provided here.
50
 
51
+ See our repository for [LeViT on GitHub](https://github.com/qualcomm/ai-hub-models/tree/v0.49.1/qai_hub_models/models/levit) for usage instructions.
52
 
53
  ## Model Details
54
 
 
64
  ## Performance Summary
65
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
66
  |---|---|---|---|---|---|---
67
+ | LeViT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.655 ms | 1 - 77 MB | NPU
68
+ | LeViT | ONNX | float | Snapdragon® X2 Elite | 0.692 ms | 16 - 16 MB | NPU
69
+ | LeViT | ONNX | float | Snapdragon® X Elite | 1.464 ms | 16 - 16 MB | NPU
70
+ | LeViT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.861 ms | 0 - 93 MB | NPU
71
+ | LeViT | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.252 ms | 0 - 25 MB | NPU
72
+ | LeViT | ONNX | float | Qualcomm® QCS9075 | 1.656 ms | 1 - 3 MB | NPU
73
+ | LeViT | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.707 ms | 0 - 67 MB | NPU
74
+ | LeViT | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.469 ms | 0 - 62 MB | NPU
75
+ | LeViT | ONNX | w8a16 | Snapdragon® X2 Elite | 0.5 ms | 8 - 8 MB | NPU
76
+ | LeViT | ONNX | w8a16 | Snapdragon® X Elite | 1.239 ms | 8 - 8 MB | NPU
77
+ | LeViT | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.713 ms | 0 - 88 MB | NPU
78
+ | LeViT | ONNX | w8a16 | Qualcomm® QCS6490 | 46.135 ms | 11 - 16 MB | CPU
79
+ | LeViT | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 1.039 ms | 0 - 13 MB | NPU
80
+ | LeViT | ONNX | w8a16 | Qualcomm® QCS9075 | 1.262 ms | 0 - 3 MB | NPU
81
+ | LeViT | ONNX | w8a16 | Qualcomm® QCM6690 | 18.543 ms | 2 - 12 MB | CPU
82
+ | LeViT | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.538 ms | 0 - 60 MB | NPU
83
+ | LeViT | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 14.66 ms | 11 - 20 MB | CPU
84
+ | LeViT | ONNX | w8a16_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.485 ms | 0 - 61 MB | NPU
85
+ | LeViT | ONNX | w8a16_mixed_int16 | Snapdragon® X2 Elite | 0.509 ms | 10 - 10 MB | NPU
86
+ | LeViT | ONNX | w8a16_mixed_int16 | Snapdragon® X Elite | 1.277 ms | 10 - 10 MB | NPU
87
+ | LeViT | ONNX | w8a16_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 0.737 ms | 0 - 84 MB | NPU
88
+ | LeViT | ONNX | w8a16_mixed_int16 | Qualcomm® QCS6490 | 44.528 ms | 11 - 17 MB | CPU
89
+ | LeViT | ONNX | w8a16_mixed_int16 | Qualcomm® QCS8550 (Proxy) | 1.063 ms | 0 - 13 MB | NPU
90
+ | LeViT | ONNX | w8a16_mixed_int16 | Qualcomm® QCS9075 | 1.311 ms | 0 - 3 MB | NPU
91
+ | LeViT | ONNX | w8a16_mixed_int16 | Qualcomm® QCM6690 | 18.63 ms | 25 - 35 MB | CPU
92
+ | LeViT | ONNX | w8a16_mixed_int16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.546 ms | 0 - 59 MB | NPU
93
+ | LeViT | ONNX | w8a16_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 15.893 ms | 11 - 22 MB | CPU
94
+ | LeViT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.743 ms | 1 - 61 MB | NPU
95
+ | LeViT | QNN_DLC | float | Snapdragon® X2 Elite | 0.999 ms | 1 - 1 MB | NPU
96
+ | LeViT | QNN_DLC | float | Snapdragon® X Elite | 1.802 ms | 1 - 1 MB | NPU
97
+ | LeViT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.082 ms | 1 - 88 MB | NPU
98
+ | LeViT | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 3.843 ms | 1 - 58 MB | NPU
99
+ | LeViT | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 1.593 ms | 1 - 47 MB | NPU
100
+ | LeViT | QNN_DLC | float | Qualcomm® QCS9075 | 1.884 ms | 1 - 3 MB | NPU
101
+ | LeViT | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 2.363 ms | 0 - 81 MB | NPU
102
+ | LeViT | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.849 ms | 1 - 59 MB | NPU
103
+ | LeViT | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.633 ms | 0 - 41 MB | NPU
104
+ | LeViT | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.851 ms | 0 - 0 MB | NPU
105
+ | LeViT | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.669 ms | 0 - 0 MB | NPU
106
+ | LeViT | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.017 ms | 0 - 61 MB | NPU
107
+ | LeViT | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 2.967 ms | 0 - 40 MB | NPU
108
+ | LeViT | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 1.46 ms | 0 - 3 MB | NPU
109
+ | LeViT | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 1.724 ms | 2 - 4 MB | NPU
110
+ | LeViT | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 5.673 ms | 0 - 164 MB | NPU
111
+ | LeViT | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.748 ms | 0 - 42 MB | NPU
112
+ | LeViT | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.473 ms | 0 - 39 MB | NPU
113
+ | LeViT | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.652 ms | 0 - 41 MB | NPU
114
+ | LeViT | QNN_DLC | w8a16_mixed_int16 | Snapdragon® X2 Elite | 0.858 ms | 0 - 0 MB | NPU
115
+ | LeViT | QNN_DLC | w8a16_mixed_int16 | Snapdragon® X Elite | 1.703 ms | 0 - 0 MB | NPU
116
+ | LeViT | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 1.037 ms | 0 - 66 MB | NPU
117
+ | LeViT | QNN_DLC | w8a16_mixed_int16 | Qualcomm® QCS8275 (Proxy) | 3.052 ms | 0 - 40 MB | NPU
118
+ | LeViT | QNN_DLC | w8a16_mixed_int16 | Qualcomm® QCS8550 (Proxy) | 1.493 ms | 0 - 12 MB | NPU
119
+ | LeViT | QNN_DLC | w8a16_mixed_int16 | Qualcomm® QCS9075 | 1.745 ms | 2 - 4 MB | NPU
120
+ | LeViT | QNN_DLC | w8a16_mixed_int16 | Qualcomm® QCM6690 | 6.08 ms | 0 - 166 MB | NPU
121
+ | LeViT | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.752 ms | 0 - 37 MB | NPU
122
+ | LeViT | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 1.506 ms | 0 - 39 MB | NPU
123
+ | LeViT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.68 ms | 0 - 72 MB | NPU
124
+ | LeViT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.051 ms | 0 - 90 MB | NPU
125
+ | LeViT | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 4.099 ms | 0 - 65 MB | NPU
126
+ | LeViT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.56 ms | 0 - 2 MB | NPU
127
+ | LeViT | TFLITE | float | Qualcomm® QCS9075 | 1.88 ms | 0 - 19 MB | NPU
128
+ | LeViT | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 2.399 ms | 0 - 83 MB | NPU
129
+ | LeViT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.802 ms | 0 - 72 MB | NPU
130
 
131
  ## License
132
  * The license for the original implementation of LeViT can be found