Hugging Face's logo

qualcomm
/
EfficientViT-b2-cls

Image Classification
PyTorch
backbone
bu_auto
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
eb61464
·
verified ·
1 Parent(s): bb246f5

v0.60.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.60.0 for changelog.

Files changed (2) hide show
  1. README.md +89 -50
  2. release_assets.json +21 -4
README.md CHANGED
@@ -17,7 +17,7 @@ pipeline_tag: image-classification
17
  EfficientViT 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.
18
 
19
  This is based on the implementation of EfficientViT-b2-cls found [here](https://github.com/CVHub520/efficientvit).
20
- 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/v0.59.0/src/qai_hub_models/models/efficientvit_b2_cls) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
21
 
22
  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.
23
 
@@ -30,79 +30,118 @@ Below are pre-exported model assets ready for deployment.
30
 
31
  | Runtime | Precision | Chipset | SDK Versions | Download |
32
  |---|---|---|---|---|
33
- | 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/efficientvit_b2_cls/releases/v0.59.0/efficientvit_b2_cls-onnx-float.zip)
34
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientvit_b2_cls/releases/v0.59.0/efficientvit_b2_cls-qnn_dlc-float.zip)
35
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientvit_b2_cls/releases/v0.59.0/efficientvit_b2_cls-tflite-float.zip)
 
 
36
 
37
  For more device-specific assets and performance metrics, visit **[EfficientViT-b2-cls on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientvit_b2_cls)**.
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/v0.59.0/src/qai_hub_models/models/efficientvit_b2_cls) 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 [EfficientViT-b2-cls on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/efficientvit_b2_cls) for usage instructions.
50
 
51
  ## Model Details
52
 
53
  **Model Type:** Model_use_case.image_classification
54
 
55
  **Model Stats:**
56
- - Model checkpoint: Imagenet
57
  - Input resolution: 224x224
58
- - Number of parameters: 24.3M
59
  - Model size (float): 92.9 MB
 
60
 
61
  ## Performance Summary
62
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
63
  |---|---|---|---|---|---|---
64
- | EfficientViT-b2-cls | ONNX | float | Snapdragon® X2 Elite | 2.492 ms | 2 - 2 MB | NPU
65
- | EfficientViT-b2-cls | ONNX | float | Snapdragon® X Elite | 5.011 ms | 49 - 49 MB | NPU
66
- | EfficientViT-b2-cls | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.194 ms | 0 - 138 MB | NPU
67
- | EfficientViT-b2-cls | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 6.337 ms | 1 - 143 MB | NPU
68
- | EfficientViT-b2-cls | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.844 ms | 0 - 74 MB | NPU
69
- | EfficientViT-b2-cls | ONNX | float | Qualcomm® QCS8450 | 6.337 ms | 1 - 143 MB | NPU
70
- | EfficientViT-b2-cls | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 5.482 ms | 1 - 4 MB | NPU
71
- | EfficientViT-b2-cls | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.011 ms | 49 - 49 MB | NPU
72
- | EfficientViT-b2-cls | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.661 ms | 0 - 69 MB | NPU
73
- | EfficientViT-b2-cls | ONNX | float | Snapdragon® 8 Elite Mobile | 2.661 ms | 0 - 69 MB | NPU
74
- | EfficientViT-b2-cls | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.408 ms | 1 - 70 MB | NPU
75
- | EfficientViT-b2-cls | QNN_DLC | float | Snapdragon® X2 Elite | 2.962 ms | 1 - 1 MB | NPU
76
- | EfficientViT-b2-cls | QNN_DLC | float | Snapdragon® X Elite | 6.271 ms | 1 - 1 MB | NPU
77
- | EfficientViT-b2-cls | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.709 ms | 0 - 143 MB | NPU
78
- | EfficientViT-b2-cls | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 7.225 ms | 0 - 143 MB | NPU
79
- | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 12.82 ms | 1 - 67 MB | NPU
80
- | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.39 ms | 1 - 2 MB | NPU
81
- | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® SA8775P | 6.734 ms | 1 - 70 MB | NPU
82
- | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® SA8650P | 6.734 ms | 1 - 70 MB | NPU
83
- | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® SA8255P | 6.734 ms | 1 - 70 MB | NPU
84
- | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® QCS8450 | 7.225 ms | 0 - 143 MB | NPU
85
- | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 6.546 ms | 1 - 3 MB | NPU
86
- | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 6.271 ms | 1 - 1 MB | NPU
87
- | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.767 ms | 0 - 68 MB | NPU
88
- | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® SA7255P | 12.82 ms | 1 - 67 MB | NPU
89
- | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® SA8295P | 7.366 ms | 1 - 72 MB | NPU
90
- | EfficientViT-b2-cls | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.767 ms | 0 - 68 MB | NPU
91
- | EfficientViT-b2-cls | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.32 ms | 1 - 74 MB | NPU
92
- | EfficientViT-b2-cls | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.706 ms | 0 - 182 MB | NPU
93
- | EfficientViT-b2-cls | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 7.161 ms | 0 - 185 MB | NPU
94
- | EfficientViT-b2-cls | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 12.838 ms | 0 - 109 MB | NPU
95
- | EfficientViT-b2-cls | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.416 ms | 0 - 3 MB | NPU
96
- | EfficientViT-b2-cls | TFLITE | float | Qualcomm® SA8775P | 6.738 ms | 0 - 111 MB | NPU
97
- | EfficientViT-b2-cls | TFLITE | float | Qualcomm® SA8650P | 6.738 ms | 0 - 111 MB | NPU
98
- | EfficientViT-b2-cls | TFLITE | float | Qualcomm® SA8255P | 6.738 ms | 0 - 111 MB | NPU
99
- | EfficientViT-b2-cls | TFLITE | float | Qualcomm® QCS8450 | 7.161 ms | 0 - 185 MB | NPU
100
- | EfficientViT-b2-cls | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 6.516 ms | 0 - 52 MB | NPU
101
- | EfficientViT-b2-cls | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.775 ms | 0 - 114 MB | NPU
102
- | EfficientViT-b2-cls | TFLITE | float | Qualcomm® SA7255P | 12.838 ms | 0 - 109 MB | NPU
103
- | EfficientViT-b2-cls | TFLITE | float | Qualcomm® SA8295P | 7.396 ms | 0 - 114 MB | NPU
104
- | EfficientViT-b2-cls | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.775 ms | 0 - 114 MB | NPU
105
- | EfficientViT-b2-cls | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.333 ms | 0 - 119 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
106
 
107
  ## License
108
  * The license for the original implementation of EfficientViT-b2-cls can be found
 
17
  EfficientViT 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.
18
 
19
  This is based on the implementation of EfficientViT-b2-cls found [here](https://github.com/CVHub520/efficientvit).
20
+ 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/efficientvit_b2_cls) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
21
 
22
  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.
23
 
 
30
 
31
  | Runtime | Precision | Chipset | SDK Versions | Download |
32
  |---|---|---|---|---|
33
+ | 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/efficientvit_b2_cls/releases/v0.60.0/efficientvit_b2_cls-onnx-float.zip)
34
+ | 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/efficientvit_b2_cls/releases/v0.60.0/efficientvit_b2_cls-onnx-w8a16.zip)
35
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientvit_b2_cls/releases/v0.60.0/efficientvit_b2_cls-qnn_dlc-float.zip)
36
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientvit_b2_cls/releases/v0.60.0/efficientvit_b2_cls-qnn_dlc-w8a16.zip)
37
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientvit_b2_cls/releases/v0.60.0/efficientvit_b2_cls-tflite-float.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[EfficientViT-b2-cls on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientvit_b2_cls)**.
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/v0.60.0/src/qai_hub_models/models/efficientvit_b2_cls) 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 [EfficientViT-b2-cls on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/efficientvit_b2_cls) for usage instructions.
52
 
53
  ## Model Details
54
 
55
  **Model Type:** Model_use_case.image_classification
56
 
57
  **Model Stats:**
 
58
  - Input resolution: 224x224
59
+ - Model checkpoint: Imagenet
60
  - Model size (float): 92.9 MB
61
+ - Number of parameters: 24.3M
62
 
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
+ | EfficientViT-b2-cls | ONNX | float | Snapdragon® X2 Elite | 2.526 ms | 2 - 2 MB | NPU
67
+ | EfficientViT-b2-cls | ONNX | float | Snapdragon® X Elite | 5.057 ms | 49 - 49 MB | NPU
68
+ | EfficientViT-b2-cls | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.235 ms | 0 - 140 MB | NPU
69
+ | EfficientViT-b2-cls | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 6.326 ms | 1 - 143 MB | NPU
70
+ | EfficientViT-b2-cls | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 5.066 ms | 0 - 4 MB | NPU
71
+ | EfficientViT-b2-cls | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.894 ms | 0 - 63 MB | NPU
72
+ | EfficientViT-b2-cls | ONNX | float | Qualcomm® QCS8450 | 6.326 ms | 1 - 143 MB | NPU
73
+ | EfficientViT-b2-cls | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 5.527 ms | 0 - 4 MB | NPU
74
+ | EfficientViT-b2-cls | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.057 ms | 49 - 49 MB | NPU
75
+ | EfficientViT-b2-cls | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.695 ms | 0 - 70 MB | NPU
76
+ | EfficientViT-b2-cls | ONNX | float | Snapdragon® 8 Elite Mobile | 2.695 ms | 0 - 70 MB | NPU
77
+ | EfficientViT-b2-cls | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.444 ms | 0 - 71 MB | NPU
78
+ | EfficientViT-b2-cls | ONNX | w8a16 | Snapdragon® X2 Elite | 2.607 ms | 1 - 1 MB | NPU
79
+ | EfficientViT-b2-cls | ONNX | w8a16 | Snapdragon® X Elite | 4.854 ms | 27 - 27 MB | NPU
80
+ | EfficientViT-b2-cls | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.081 ms | 0 - 157 MB | NPU
81
+ | EfficientViT-b2-cls | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 5.773 ms | 0 - 169 MB | NPU
82
+ | EfficientViT-b2-cls | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 15.321 ms | 0 - 3 MB | NPU
83
+ | EfficientViT-b2-cls | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 4.228 ms | 0 - 4 MB | NPU
84
+ | EfficientViT-b2-cls | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.617 ms | 0 - 34 MB | NPU
85
+ | EfficientViT-b2-cls | ONNX | w8a16 | Qualcomm® QCS8450 | 5.773 ms | 0 - 169 MB | NPU
86
+ | EfficientViT-b2-cls | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 4.911 ms | 0 - 3 MB | NPU
87
+ | EfficientViT-b2-cls | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 4.854 ms | 27 - 27 MB | NPU
88
+ | EfficientViT-b2-cls | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 22.184 ms | 0 - 256 MB | NPU
89
+ | EfficientViT-b2-cls | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 4.997 ms | 0 - 116 MB | NPU
90
+ | EfficientViT-b2-cls | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.522 ms | 0 - 114 MB | NPU
91
+ | EfficientViT-b2-cls | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 2.522 ms | 0 - 114 MB | NPU
92
+ | EfficientViT-b2-cls | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.169 ms | 0 - 115 MB | NPU
93
+ | EfficientViT-b2-cls | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 4.997 ms | 0 - 116 MB | NPU
94
+ | EfficientViT-b2-cls | QNN_DLC | float | Snapdragon® X2 Elite | 2.956 ms | 1 - 1 MB | NPU
95
+ | EfficientViT-b2-cls | QNN_DLC | float | Snapdragon® X Elite | 6.186 ms | 1 - 1 MB | NPU
96
+ | EfficientViT-b2-cls | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.71 ms | 0 - 141 MB | NPU
97
+ | EfficientViT-b2-cls | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 7.141 ms | 0 - 144 MB | NPU
98
+ | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 6.186 ms | 1 - 4 MB | NPU
99
+ | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 12.826 ms | 1 - 67 MB | NPU
100
+ | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.431 ms | 1 - 2 MB | NPU
101
+ | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® SA8775P | 6.8 ms | 1 - 69 MB | NPU
102
+ | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® SA8650P | 6.8 ms | 1 - 69 MB | NPU
103
+ | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® SA8255P | 6.8 ms | 1 - 69 MB | NPU
104
+ | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® QCS8450 | 7.141 ms | 0 - 144 MB | NPU
105
+ | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 6.537 ms | 1 - 3 MB | NPU
106
+ | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 6.186 ms | 1 - 1 MB | NPU
107
+ | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.82 ms | 1 - 70 MB | NPU
108
+ | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® SA7255P | 12.826 ms | 1 - 67 MB | NPU
109
+ | EfficientViT-b2-cls | QNN_DLC | float | Qualcomm® SA8295P | 7.419 ms | 1 - 73 MB | NPU
110
+ | EfficientViT-b2-cls | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.82 ms | 1 - 70 MB | NPU
111
+ | EfficientViT-b2-cls | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.341 ms | 1 - 74 MB | NPU
112
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 2.597 ms | 0 - 0 MB | NPU
113
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Snapdragon® X Elite | 5.478 ms | 0 - 0 MB | NPU
114
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.285 ms | 0 - 143 MB | NPU
115
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 4.424 ms | 0 - 3 MB | NPU
116
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 9.237 ms | 0 - 104 MB | NPU
117
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.956 ms | 0 - 2 MB | NPU
118
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Qualcomm® SA8775P | 5.459 ms | 0 - 106 MB | NPU
119
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Qualcomm® SA8650P | 5.459 ms | 0 - 106 MB | NPU
120
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Qualcomm® SA8255P | 5.459 ms | 0 - 106 MB | NPU
121
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 5.286 ms | 2 - 4 MB | NPU
122
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.478 ms | 0 - 0 MB | NPU
123
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 21.447 ms | 0 - 229 MB | NPU
124
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 5.18 ms | 0 - 102 MB | NPU
125
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.52 ms | 0 - 107 MB | NPU
126
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Qualcomm® SA7255P | 9.237 ms | 0 - 104 MB | NPU
127
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 2.52 ms | 0 - 107 MB | NPU
128
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.119 ms | 0 - 106 MB | NPU
129
+ | EfficientViT-b2-cls | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 5.18 ms | 0 - 102 MB | NPU
130
+ | EfficientViT-b2-cls | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.728 ms | 0 - 184 MB | NPU
131
+ | EfficientViT-b2-cls | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 7.148 ms | 0 - 186 MB | NPU
132
+ | EfficientViT-b2-cls | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 6.199 ms | 0 - 52 MB | NPU
133
+ | EfficientViT-b2-cls | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 13.009 ms | 0 - 110 MB | NPU
134
+ | EfficientViT-b2-cls | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.451 ms | 0 - 3 MB | NPU
135
+ | EfficientViT-b2-cls | TFLITE | float | Qualcomm® SA8775P | 6.79 ms | 0 - 112 MB | NPU
136
+ | EfficientViT-b2-cls | TFLITE | float | Qualcomm® SA8650P | 6.79 ms | 0 - 112 MB | NPU
137
+ | EfficientViT-b2-cls | TFLITE | float | Qualcomm® SA8255P | 6.79 ms | 0 - 112 MB | NPU
138
+ | EfficientViT-b2-cls | TFLITE | float | Qualcomm® QCS8450 | 7.148 ms | 0 - 186 MB | NPU
139
+ | EfficientViT-b2-cls | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 6.49 ms | 0 - 52 MB | NPU
140
+ | EfficientViT-b2-cls | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.785 ms | 0 - 114 MB | NPU
141
+ | EfficientViT-b2-cls | TFLITE | float | Qualcomm® SA7255P | 13.009 ms | 0 - 110 MB | NPU
142
+ | EfficientViT-b2-cls | TFLITE | float | Qualcomm® SA8295P | 7.495 ms | 0 - 115 MB | NPU
143
+ | EfficientViT-b2-cls | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.785 ms | 0 - 114 MB | NPU
144
+ | EfficientViT-b2-cls | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.359 ms | 0 - 118 MB | NPU
145
 
146
  ## License
147
  * The license for the original implementation of EfficientViT-b2-cls can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.59.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
@@ -8,19 +8,36 @@
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/efficientvit_b2_cls/releases/v0.59.0/efficientvit_b2_cls-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/efficientvit_b2_cls/releases/v0.59.0/efficientvit_b2_cls-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/efficientvit_b2_cls/releases/v0.59.0/efficientvit_b2_cls-tflite-float.zip"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  }
25
  }
26
  }
 
1
  {
2
+ "version": "0.60.0",
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/efficientvit_b2_cls/releases/v0.60.0/efficientvit_b2_cls-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/efficientvit_b2_cls/releases/v0.60.0/efficientvit_b2_cls-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/efficientvit_b2_cls/releases/v0.60.0/efficientvit_b2_cls-tflite-float.zip"
24
+ }
25
+ }
26
+ },
27
+ "w8a16": {
28
+ "universal_assets": {
29
+ "onnx": {
30
+ "tool_versions": {
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/efficientvit_b2_cls/releases/v0.60.0/efficientvit_b2_cls-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/efficientvit_b2_cls/releases/v0.60.0/efficientvit_b2_cls-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  }