Hugging Face's logo

qualcomm
/
EfficientNet-V2-s

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
aedc958
·
verified ·
1 Parent(s): 3a3bc4b

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 +93 -85
  2. release_assets.json +6 -6
README.md CHANGED
@@ -16,7 +16,7 @@ pipeline_tag: image-classification
16
  EfficientNetV2-s 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 EfficientNet-V2-s found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/efficientnet.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/v0.59.0/src/qai_hub_models/models/efficientnet_v2_s) 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
 
@@ -29,115 +29,123 @@ 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 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_v2_s/releases/v0.59.0/efficientnet_v2_s-onnx-float.zip)
33
- | 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/efficientnet_v2_s/releases/v0.59.0/efficientnet_v2_s-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/efficientnet_v2_s/releases/v0.59.0/efficientnet_v2_s-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/efficientnet_v2_s/releases/v0.59.0/efficientnet_v2_s-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/efficientnet_v2_s/releases/v0.59.0/efficientnet_v2_s-tflite-float.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[EfficientNet-V2-s on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientnet_v2_s)**.
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/v0.59.0/src/qai_hub_models/models/efficientnet_v2_s) 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 [EfficientNet-V2-s on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/efficientnet_v2_s) for usage instructions.
51
 
52
  ## Model Details
53
 
54
  **Model Type:** Model_use_case.image_classification
55
 
56
  **Model Stats:**
57
- - Model checkpoint: Imagenet
58
  - Input resolution: 384x384
59
- - Number of parameters: 21.4M
60
  - Model size (float): 81.7 MB
61
  - Model size (w8a16): 27.2 MB
 
62
 
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
- | EfficientNet-V2-s | ONNX | float | Snapdragon® X2 Elite | 3.047 ms | 2 - 2 MB | NPU
67
- | EfficientNet-V2-s | ONNX | float | Snapdragon® X Elite | 5.603 ms | 46 - 46 MB | NPU
68
- | EfficientNet-V2-s | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.048 ms | 0 - 165 MB | NPU
69
- | EfficientNet-V2-s | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 11.615 ms | 0 - 194 MB | NPU
70
- | EfficientNet-V2-s | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.335 ms | 0 - 222 MB | NPU
71
- | EfficientNet-V2-s | ONNX | float | Qualcomm® QCS8450 | 11.615 ms | 0 - 194 MB | NPU
72
- | EfficientNet-V2-s | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 7.632 ms | 1 - 6 MB | NPU
73
- | EfficientNet-V2-s | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.603 ms | 46 - 46 MB | NPU
74
- | EfficientNet-V2-s | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 3.095 ms | 0 - 199 MB | NPU
75
- | EfficientNet-V2-s | ONNX | float | Snapdragon® 8 Elite Mobile | 3.095 ms | 0 - 199 MB | NPU
76
- | EfficientNet-V2-s | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.322 ms | 0 - 204 MB | NPU
77
- | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® X2 Elite | 2.368 ms | 2 - 2 MB | NPU
78
- | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® X Elite | 5.705 ms | 24 - 24 MB | NPU
79
- | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.64 ms | 0 - 210 MB | NPU
80
- | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 6.85 ms | 1 - 218 MB | NPU
81
- | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 20.177 ms | 1 - 4 MB | NPU
82
- | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.46 ms | 0 - 30 MB | NPU
83
- | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® QCS8450 | 6.85 ms | 1 - 218 MB | NPU
84
- | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 5.749 ms | 1 - 4 MB | NPU
85
- | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.705 ms | 24 - 24 MB | NPU
86
- | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.52 ms | 0 - 164 MB | NPU
87
- | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 2.52 ms | 0 - 164 MB | NPU
88
- | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.023 ms | 0 - 167 MB | NPU
89
- | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® X2 Elite | 3.492 ms | 2 - 2 MB | NPU
90
- | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® X Elite | 6.279 ms | 2 - 2 MB | NPU
91
- | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 4.336 ms | 2 - 162 MB | NPU
92
- | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 13.477 ms | 2 - 192 MB | NPU
93
- | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 25.722 ms | 2 - 75 MB | NPU
94
- | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.785 ms | 0 - 9 MB | NPU
95
- | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® SA8775P | 8.22 ms | 2 - 77 MB | NPU
96
- | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® SA8650P | 8.22 ms | 2 - 77 MB | NPU
97
- | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® SA8255P | 8.22 ms | 2 - 77 MB | NPU
98
- | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® QCS8450 | 13.477 ms | 2 - 192 MB | NPU
99
- | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 7.907 ms | 2 - 5 MB | NPU
100
- | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 6.279 ms | 2 - 2 MB | NPU
101
- | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 3.133 ms | 0 - 79 MB | NPU
102
- | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® SA7255P | 25.722 ms | 2 - 75 MB | NPU
103
- | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® SA8295P | 13.006 ms | 2 - 107 MB | NPU
104
- | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 3.133 ms | 0 - 79 MB | NPU
105
- | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.285 ms | 2 - 85 MB | NPU
106
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 2.91 ms | 1 - 1 MB | NPU
107
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® X Elite | 6.83 ms | 1 - 1 MB | NPU
108
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.201 ms | 1 - 175 MB | NPU
109
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 8.212 ms | 1 - 185 MB | NPU
110
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 21.506 ms | 3 - 5 MB | NPU
111
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8275 | 12.065 ms | 1 - 134 MB | NPU
112
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.233 ms | 1 - 3 MB | NPU
113
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® SA8775P | 6.716 ms | 1 - 136 MB | NPU
114
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® SA8650P | 6.716 ms | 1 - 136 MB | NPU
115
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® SA8255P | 6.716 ms | 1 - 136 MB | NPU
116
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 8.212 ms | 1 - 185 MB | NPU
117
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 6.464 ms | 1 - 3 MB | NPU
118
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 6.83 ms | 1 - 1 MB | NPU
119
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 41.3 ms | 1 - 255 MB | NPU
120
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 6.973 ms | 1 - 255 MB | NPU
121
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.809 ms | 1 - 146 MB | NPU
122
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® SA7255P | 12.065 ms | 1 - 134 MB | NPU
123
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® SA8295P | 8.384 ms | 1 - 134 MB | NPU
124
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 2.809 ms | 1 - 146 MB | NPU
125
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.243 ms | 1 - 145 MB | NPU
126
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 6.973 ms | 1 - 255 MB | NPU
127
- | EfficientNet-V2-s | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4.323 ms | 0 - 200 MB | NPU
128
- | EfficientNet-V2-s | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 13.412 ms | 0 - 229 MB | NPU
129
- | EfficientNet-V2-s | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 25.819 ms | 0 - 116 MB | NPU
130
- | EfficientNet-V2-s | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.732 ms | 0 - 51 MB | NPU
131
- | EfficientNet-V2-s | TFLITE | float | Qualcomm® SA8775P | 8.218 ms | 0 - 118 MB | NPU
132
- | EfficientNet-V2-s | TFLITE | float | Qualcomm® SA8650P | 8.218 ms | 0 - 118 MB | NPU
133
- | EfficientNet-V2-s | TFLITE | float | Qualcomm® SA8255P | 8.218 ms | 0 - 118 MB | NPU
134
- | EfficientNet-V2-s | TFLITE | float | Qualcomm® QCS8450 | 13.412 ms | 0 - 229 MB | NPU
135
- | EfficientNet-V2-s | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 7.918 ms | 0 - 51 MB | NPU
136
- | EfficientNet-V2-s | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 3.145 ms | 0 - 122 MB | NPU
137
- | EfficientNet-V2-s | TFLITE | float | Qualcomm® SA7255P | 25.819 ms | 0 - 116 MB | NPU
138
- | EfficientNet-V2-s | TFLITE | float | Qualcomm® SA8295P | 13.025 ms | 0 - 148 MB | NPU
139
- | EfficientNet-V2-s | TFLITE | float | Snapdragon® 8 Elite Mobile | 3.145 ms | 0 - 122 MB | NPU
140
- | EfficientNet-V2-s | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.338 ms | 0 - 120 MB | NPU
 
 
 
 
 
 
 
 
141
 
142
  ## License
143
  * The license for the original implementation of EfficientNet-V2-s can be found
 
16
  EfficientNetV2-s 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 EfficientNet-V2-s found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/efficientnet.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/v0.60.0/src/qai_hub_models/models/efficientnet_v2_s) 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 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_v2_s/releases/v0.60.0/efficientnet_v2_s-onnx-float.zip)
33
+ | 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/efficientnet_v2_s/releases/v0.60.0/efficientnet_v2_s-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/efficientnet_v2_s/releases/v0.60.0/efficientnet_v2_s-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/efficientnet_v2_s/releases/v0.60.0/efficientnet_v2_s-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/efficientnet_v2_s/releases/v0.60.0/efficientnet_v2_s-tflite-float.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[EfficientNet-V2-s on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientnet_v2_s)**.
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/v0.60.0/src/qai_hub_models/models/efficientnet_v2_s) 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 [EfficientNet-V2-s on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/efficientnet_v2_s) for usage instructions.
51
 
52
  ## Model Details
53
 
54
  **Model Type:** Model_use_case.image_classification
55
 
56
  **Model Stats:**
 
57
  - Input resolution: 384x384
58
+ - Model checkpoint: Imagenet
59
  - Model size (float): 81.7 MB
60
  - Model size (w8a16): 27.2 MB
61
+ - Number of parameters: 21.4M
62
 
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
+ | EfficientNet-V2-s | ONNX | float | Snapdragon® X2 Elite | 3.035 ms | 2 - 2 MB | NPU
67
+ | EfficientNet-V2-s | ONNX | float | Snapdragon® X Elite | 5.616 ms | 46 - 46 MB | NPU
68
+ | EfficientNet-V2-s | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.056 ms | 0 - 166 MB | NPU
69
+ | EfficientNet-V2-s | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 11.58 ms | 1 - 198 MB | NPU
70
+ | EfficientNet-V2-s | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 8.124 ms | 2 - 7 MB | NPU
71
+ | EfficientNet-V2-s | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.344 ms | 0 - 48 MB | NPU
72
+ | EfficientNet-V2-s | ONNX | float | Qualcomm® QCS8450 | 11.58 ms | 1 - 198 MB | NPU
73
+ | EfficientNet-V2-s | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 7.667 ms | 1 - 6 MB | NPU
74
+ | EfficientNet-V2-s | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.616 ms | 46 - 46 MB | NPU
75
+ | EfficientNet-V2-s | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 3.097 ms | 0 - 201 MB | NPU
76
+ | EfficientNet-V2-s | ONNX | float | Snapdragon® 8 Elite Mobile | 3.097 ms | 0 - 201 MB | NPU
77
+ | EfficientNet-V2-s | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.322 ms | 0 - 205 MB | NPU
78
+ | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® X2 Elite | 2.366 ms | 2 - 2 MB | NPU
79
+ | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® X Elite | 5.732 ms | 24 - 24 MB | NPU
80
+ | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.64 ms | 0 - 207 MB | NPU
81
+ | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 6.694 ms | 1 - 216 MB | NPU
82
+ | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 20.053 ms | 1 - 4 MB | NPU
83
+ | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 5.127 ms | 1 - 4 MB | NPU
84
+ | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.458 ms | 0 - 30 MB | NPU
85
+ | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® QCS8450 | 6.694 ms | 1 - 216 MB | NPU
86
+ | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 5.971 ms | 1 - 4 MB | NPU
87
+ | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 5.732 ms | 24 - 24 MB | NPU
88
+ | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 34.763 ms | 1 - 272 MB | NPU
89
+ | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 6.285 ms | 1 - 271 MB | NPU
90
+ | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.514 ms | 0 - 163 MB | NPU
91
+ | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 2.514 ms | 0 - 163 MB | NPU
92
+ | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.021 ms | 0 - 165 MB | NPU
93
+ | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 6.285 ms | 1 - 271 MB | NPU
94
+ | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® X2 Elite | 3.424 ms | 2 - 2 MB | NPU
95
+ | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® X Elite | 6.343 ms | 2 - 2 MB | NPU
96
+ | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 4.339 ms | 0 - 157 MB | NPU
97
+ | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 13.387 ms | 0 - 187 MB | NPU
98
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 8.205 ms | 2 - 6 MB | NPU
99
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 25.747 ms | 2 - 75 MB | NPU
100
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.796 ms | 2 - 173 MB | NPU
101
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® SA8775P | 8.238 ms | 2 - 77 MB | NPU
102
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® SA8650P | 8.238 ms | 2 - 77 MB | NPU
103
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® SA8255P | 8.238 ms | 2 - 77 MB | NPU
104
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® QCS8450 | 13.387 ms | 0 - 187 MB | NPU
105
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 7.922 ms | 4 - 7 MB | NPU
106
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 6.343 ms | 2 - 2 MB | NPU
107
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 3.142 ms | 0 - 78 MB | NPU
108
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® SA7255P | 25.747 ms | 2 - 75 MB | NPU
109
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® SA8295P | 13.013 ms | 0 - 105 MB | NPU
110
+ | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 3.142 ms | 0 - 78 MB | NPU
111
+ | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.359 ms | 2 - 85 MB | NPU
112
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 2.906 ms | 1 - 1 MB | NPU
113
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® X Elite | 6.806 ms | 1 - 1 MB | NPU
114
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 4.217 ms | 0 - 174 MB | NPU
115
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 8.199 ms | 1 - 185 MB | NPU
116
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 21.542 ms | 1 - 3 MB | NPU
117
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 5.799 ms | 1 - 4 MB | NPU
118
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 12.06 ms | 1 - 136 MB | NPU
119
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 6.247 ms | 1 - 2 MB | NPU
120
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® SA8775P | 6.721 ms | 1 - 136 MB | NPU
121
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® SA8650P | 6.721 ms | 1 - 136 MB | NPU
122
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® SA8255P | 6.721 ms | 1 - 136 MB | NPU
123
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 8.199 ms | 1 - 185 MB | NPU
124
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 6.682 ms | 1 - 3 MB | NPU
125
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 6.806 ms | 1 - 1 MB | NPU
126
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 42.008 ms | 1 - 255 MB | NPU
127
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 6.728 ms | 1 - 253 MB | NPU
128
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 2.808 ms | 0 - 145 MB | NPU
129
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® SA7255P | 12.06 ms | 1 - 136 MB | NPU
130
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® SA8295P | 8.334 ms | 1 - 134 MB | NPU
131
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 2.808 ms | 0 - 145 MB | NPU
132
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.227 ms | 1 - 146 MB | NPU
133
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 6.728 ms | 1 - 253 MB | NPU
134
+ | EfficientNet-V2-s | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4.329 ms | 0 - 199 MB | NPU
135
+ | EfficientNet-V2-s | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 13.39 ms | 0 - 228 MB | NPU
136
+ | EfficientNet-V2-s | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 8.212 ms | 0 - 52 MB | NPU
137
+ | EfficientNet-V2-s | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 25.845 ms | 0 - 116 MB | NPU
138
+ | EfficientNet-V2-s | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.739 ms | 0 - 2 MB | NPU
139
+ | EfficientNet-V2-s | TFLITE | float | Qualcomm® SA8775P | 8.241 ms | 0 - 118 MB | NPU
140
+ | EfficientNet-V2-s | TFLITE | float | Qualcomm® SA8650P | 8.241 ms | 0 - 118 MB | NPU
141
+ | EfficientNet-V2-s | TFLITE | float | Qualcomm® SA8255P | 8.241 ms | 0 - 118 MB | NPU
142
+ | EfficientNet-V2-s | TFLITE | float | Qualcomm® QCS8450 | 13.39 ms | 0 - 228 MB | NPU
143
+ | EfficientNet-V2-s | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 7.934 ms | 0 - 51 MB | NPU
144
+ | EfficientNet-V2-s | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 3.139 ms | 0 - 122 MB | NPU
145
+ | EfficientNet-V2-s | TFLITE | float | Qualcomm® SA7255P | 25.845 ms | 0 - 116 MB | NPU
146
+ | EfficientNet-V2-s | TFLITE | float | Qualcomm® SA8295P | 13.035 ms | 0 - 148 MB | NPU
147
+ | EfficientNet-V2-s | TFLITE | float | Snapdragon® 8 Elite Mobile | 3.139 ms | 0 - 122 MB | NPU
148
+ | EfficientNet-V2-s | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.344 ms | 0 - 120 MB | NPU
149
 
150
  ## License
151
  * The license for the original implementation of EfficientNet-V2-s 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 +8,19 @@
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/efficientnet_v2_s/releases/v0.59.0/efficientnet_v2_s-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/efficientnet_v2_s/releases/v0.59.0/efficientnet_v2_s-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/efficientnet_v2_s/releases/v0.59.0/efficientnet_v2_s-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -31,13 +31,13 @@
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/efficientnet_v2_s/releases/v0.59.0/efficientnet_v2_s-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/efficientnet_v2_s/releases/v0.59.0/efficientnet_v2_s-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  }
 
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/efficientnet_v2_s/releases/v0.60.0/efficientnet_v2_s-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/efficientnet_v2_s/releases/v0.60.0/efficientnet_v2_s-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/efficientnet_v2_s/releases/v0.60.0/efficientnet_v2_s-tflite-float.zip"
24
  }
25
  }
26
  },
 
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/efficientnet_v2_s/releases/v0.60.0/efficientnet_v2_s-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/efficientnet_v2_s/releases/v0.60.0/efficientnet_v2_s-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  }