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
ab5a577
·
verified ·
1 Parent(s): ba8107c

v0.48.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.48.0 for changelog.

Files changed (1) hide show
  1. README.md +53 -53
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/quic/ai-hub-models/blob/main/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
 
@@ -29,25 +29,25 @@ Below are pre-exported model assets ready for deployment.
29
 
30
  | Runtime | Precision | Chipset | SDK Versions | Download |
31
  |---|---|---|---|---|
32
- | 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/efficientnet_v2_s/releases/v0.47.0/efficientnet_v2_s-onnx-float.zip)
33
- | 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/efficientnet_v2_s/releases/v0.47.0/efficientnet_v2_s-onnx-w8a16.zip)
34
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_v2_s/releases/v0.47.0/efficientnet_v2_s-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/efficientnet_v2_s/releases/v0.47.0/efficientnet_v2_s-qnn_dlc-w8a16.zip)
36
- | 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/efficientnet_v2_s/releases/v0.47.0/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/quic/ai-hub-models/blob/main/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/quic/ai-hub-models/blob/main/qai_hub_models/models/efficientnet_v2_s) for usage instructions.
51
 
52
  ## Model Details
53
 
@@ -63,51 +63,51 @@ See our repository for [EfficientNet-V2-s on GitHub](https://github.com/quic/ai-
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® X Elite | 2.696 ms | 46 - 46 MB | NPU
67
- | EfficientNet-V2-s | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.831 ms | 0 - 155 MB | NPU
68
- | EfficientNet-V2-s | ONNX | float | Qualcomm® QCS8550 (Proxy) | 2.433 ms | 0 - 50 MB | NPU
69
- | EfficientNet-V2-s | ONNX | float | Qualcomm® QCS9075 | 3.452 ms | 1 - 4 MB | NPU
70
- | EfficientNet-V2-s | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.427 ms | 0 - 77 MB | NPU
71
- | EfficientNet-V2-s | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.181 ms | 0 - 77 MB | NPU
72
- | EfficientNet-V2-s | ONNX | float | Snapdragon® X2 Elite | 1.327 ms | 47 - 47 MB | NPU
73
- | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® X Elite | 2.674 ms | 24 - 24 MB | NPU
74
- | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.575 ms | 0 - 179 MB | NPU
75
- | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® QCS6490 | 277.999 ms | 26 - 31 MB | CPU
76
- | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 2.379 ms | 0 - 32 MB | NPU
77
- | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® QCS9075 | 2.675 ms | 0 - 3 MB | NPU
78
- | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® QCM6690 | 125.041 ms | 14 - 28 MB | CPU
79
- | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.163 ms | 0 - 126 MB | NPU
80
- | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 114.755 ms | 25 - 38 MB | CPU
81
- | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.927 ms | 0 - 127 MB | NPU
82
- | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® X2 Elite | 1.089 ms | 24 - 24 MB | NPU
83
- | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® X Elite | 2.92 ms | 1 - 1 MB | NPU
84
- | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.909 ms | 0 - 143 MB | NPU
85
- | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 10.809 ms | 1 - 66 MB | NPU
86
- | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 2.627 ms | 1 - 2 MB | NPU
87
- | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® QCS9075 | 3.681 ms | 3 - 5 MB | NPU
88
- | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 5.632 ms | 0 - 155 MB | NPU
89
- | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.504 ms | 1 - 71 MB | NPU
90
- | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.203 ms | 1 - 69 MB | NPU
91
- | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® X2 Elite | 1.595 ms | 1 - 1 MB | NPU
92
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® X Elite | 2.923 ms | 0 - 0 MB | NPU
93
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.785 ms | 0 - 148 MB | NPU
94
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 6.702 ms | 0 - 2 MB | NPU
95
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 5.343 ms | 0 - 105 MB | NPU
96
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 2.62 ms | 0 - 2 MB | NPU
97
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 2.945 ms | 2 - 4 MB | NPU
98
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 14.079 ms | 0 - 226 MB | NPU
99
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 3.226 ms | 0 - 151 MB | NPU
100
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.254 ms | 0 - 106 MB | NPU
101
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 2.864 ms | 0 - 107 MB | NPU
102
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.991 ms | 0 - 108 MB | NPU
103
- | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 1.418 ms | 0 - 0 MB | NPU
104
- | EfficientNet-V2-s | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.904 ms | 0 - 190 MB | NPU
105
- | EfficientNet-V2-s | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 10.839 ms | 0 - 111 MB | NPU
106
- | EfficientNet-V2-s | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.603 ms | 0 - 2 MB | NPU
107
- | EfficientNet-V2-s | TFLITE | float | Qualcomm® QCS9075 | 3.689 ms | 0 - 50 MB | NPU
108
- | EfficientNet-V2-s | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5.686 ms | 0 - 206 MB | NPU
109
- | EfficientNet-V2-s | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.486 ms | 0 - 114 MB | NPU
110
- | EfficientNet-V2-s | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.206 ms | 0 - 112 MB | NPU
111
 
112
  ## License
113
  * 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/main/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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_v2_s/releases/v0.48.0/efficientnet_v2_s-onnx-float.zip)
33
+ | 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/efficientnet_v2_s/releases/v0.48.0/efficientnet_v2_s-onnx-w8a16.zip)
34
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_v2_s/releases/v0.48.0/efficientnet_v2_s-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/efficientnet_v2_s/releases/v0.48.0/efficientnet_v2_s-qnn_dlc-w8a16.zip)
36
+ | 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/efficientnet_v2_s/releases/v0.48.0/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/main/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/main/qai_hub_models/models/efficientnet_v2_s) for usage instructions.
51
 
52
  ## Model Details
53
 
 
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 | 1.322 ms | 47 - 47 MB | NPU
67
+ | EfficientNet-V2-s | ONNX | float | Snapdragon® X Elite | 2.689 ms | 46 - 46 MB | NPU
68
+ | EfficientNet-V2-s | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.831 ms | 0 - 156 MB | NPU
69
+ | EfficientNet-V2-s | ONNX | float | Qualcomm® QCS8550 (Proxy) | 2.428 ms | 0 - 50 MB | NPU
70
+ | EfficientNet-V2-s | ONNX | float | Qualcomm® QCS9075 | 3.451 ms | 1 - 4 MB | NPU
71
+ | EfficientNet-V2-s | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.43 ms | 0 - 70 MB | NPU
72
+ | EfficientNet-V2-s | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.184 ms | 0 - 76 MB | NPU
73
+ | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® X2 Elite | 1.091 ms | 24 - 24 MB | NPU
74
+ | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® X Elite | 2.667 ms | 24 - 24 MB | NPU
75
+ | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.593 ms | 0 - 178 MB | NPU
76
+ | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® QCS6490 | 281.17 ms | 26 - 30 MB | CPU
77
+ | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 2.367 ms | 0 - 32 MB | NPU
78
+ | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® QCS9075 | 2.671 ms | 0 - 3 MB | NPU
79
+ | EfficientNet-V2-s | ONNX | w8a16 | Qualcomm® QCM6690 | 124.358 ms | 14 - 27 MB | CPU
80
+ | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.148 ms | 0 - 126 MB | NPU
81
+ | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 114.091 ms | 27 - 41 MB | CPU
82
+ | EfficientNet-V2-s | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.93 ms | 0 - 128 MB | NPU
83
+ | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® X2 Elite | 1.586 ms | 1 - 1 MB | NPU
84
+ | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® X Elite | 2.93 ms | 1 - 1 MB | NPU
85
+ | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.929 ms | 0 - 144 MB | NPU
86
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 10.806 ms | 1 - 66 MB | NPU
87
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 2.613 ms | 1 - 2 MB | NPU
88
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® QCS9075 | 3.678 ms | 1 - 3 MB | NPU
89
+ | EfficientNet-V2-s | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 5.717 ms | 0 - 155 MB | NPU
90
+ | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.53 ms | 0 - 68 MB | NPU
91
+ | EfficientNet-V2-s | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.209 ms | 1 - 70 MB | NPU
92
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 1.416 ms | 0 - 0 MB | NPU
93
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® X Elite | 2.927 ms | 0 - 0 MB | NPU
94
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.784 ms | 0 - 146 MB | NPU
95
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 6.663 ms | 0 - 2 MB | NPU
96
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 5.367 ms | 0 - 105 MB | NPU
97
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 2.606 ms | 0 - 2 MB | NPU
98
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 2.944 ms | 0 - 2 MB | NPU
99
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 14.112 ms | 0 - 226 MB | NPU
100
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 3.168 ms | 0 - 151 MB | NPU
101
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 1.246 ms | 0 - 106 MB | NPU
102
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 2.988 ms | 0 - 106 MB | NPU
103
+ | EfficientNet-V2-s | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.994 ms | 0 - 109 MB | NPU
104
+ | EfficientNet-V2-s | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.921 ms | 0 - 196 MB | NPU
105
+ | EfficientNet-V2-s | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 10.793 ms | 0 - 111 MB | NPU
106
+ | EfficientNet-V2-s | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 2.621 ms | 0 - 3 MB | NPU
107
+ | EfficientNet-V2-s | TFLITE | float | Qualcomm® QCS9075 | 3.687 ms | 0 - 50 MB | NPU
108
+ | EfficientNet-V2-s | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5.619 ms | 0 - 205 MB | NPU
109
+ | EfficientNet-V2-s | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.495 ms | 0 - 113 MB | NPU
110
+ | EfficientNet-V2-s | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.203 ms | 0 - 113 MB | NPU
111
 
112
  ## License
113
  * The license for the original implementation of EfficientNet-V2-s can be found