Hugging Face's logo

qualcomm
/
EfficientNet-B0

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
efbc300
·
verified ·
1 Parent(s): de07a8e

v0.63.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.63.0 for changelog.

Files changed (2) hide show
  1. README.md +82 -85
  2. release_assets.json +13 -13
README.md CHANGED
@@ -16,7 +16,7 @@ pipeline_tag: image-classification
16
  EfficientNetB0 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-B0 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/v0.62.2/src/qai_hub_models/models/efficientnet_b0) 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
 
@@ -29,27 +29,27 @@ 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_b0/releases/v0.62.2/efficientnet_b0-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_b0/releases/v0.62.2/efficientnet_b0-onnx-w8a16.zip)
34
- | ONNX | w8a16_mixed_int16 | 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_b0/releases/v0.62.2/efficientnet_b0-onnx-w8a16_mixed_int16.zip)
35
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b0/releases/v0.62.2/efficientnet_b0-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/efficientnet_b0/releases/v0.62.2/efficientnet_b0-qnn_dlc-w8a16.zip)
37
- | QNN_DLC | w8a16_mixed_int16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b0/releases/v0.62.2/efficientnet_b0-qnn_dlc-w8a16_mixed_int16.zip)
38
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b0/releases/v0.62.2/efficientnet_b0-tflite-float.zip)
39
 
40
  For more device-specific assets and performance metrics, visit **[EfficientNet-B0 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientnet_b0)**.
41
 
42
 
43
  ### Option 2: Export with Custom Configurations
44
 
45
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/efficientnet_b0) Python library to compile and export the model with your own:
46
  - Custom weights (e.g., fine-tuned checkpoints)
47
  - Custom input shapes
48
  - Target device and runtime configurations
49
 
50
  This option is ideal if you need to customize the model beyond the default configuration provided here.
51
 
52
- See our repository for [EfficientNet-B0 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/efficientnet_b0) for usage instructions.
53
 
54
  ## Model Details
55
 
@@ -65,18 +65,20 @@ See our repository for [EfficientNet-B0 on GitHub](https://github.com/qualcomm/a
65
  ## Performance Summary
66
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
67
  |---|---|---|---|---|---|---
68
- | EfficientNet-B0 | ONNX | float | Snapdragon® X2 Elite | 0.656 ms | 2 - 2 MB | NPU
69
- | EfficientNet-B0 | ONNX | float | Snapdragon® X Elite | 1.315 ms | 14 - 14 MB | NPU
70
- | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.904 ms | 0 - 69 MB | NPU
71
- | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2.88 ms | 1 - 78 MB | NPU
72
- | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 1.605 ms | 1 - 4 MB | NPU
73
- | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.259 ms | 0 - 16 MB | NPU
74
- | EfficientNet-B0 | ONNX | float | Qualcomm® QCS8450 | 2.88 ms | 1 - 78 MB | NPU
75
- | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 1.628 ms | 1 - 3 MB | NPU
76
- | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.315 ms | 14 - 14 MB | NPU
77
- | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.697 ms | 0 - 38 MB | NPU
78
- | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Elite Mobile | 0.697 ms | 0 - 38 MB | NPU
79
- | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.552 ms | 0 - 43 MB | NPU
 
 
80
  | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® X2 Elite | 0.571 ms | 1 - 1 MB | NPU
81
  | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® X Elite | 1.486 ms | 6 - 6 MB | NPU
82
  | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.949 ms | 0 - 82 MB | NPU
@@ -90,39 +92,38 @@ See our repository for [EfficientNet-B0 on GitHub](https://github.com/qualcomm/a
90
  | EfficientNet-B0 | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 5.691 ms | 0 - 65 MB | NPU
91
  | EfficientNet-B0 | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 1.444 ms | 2 - 60 MB | NPU
92
  | EfficientNet-B0 | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.668 ms | 0 - 57 MB | NPU
93
- | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 0.668 ms | 0 - 57 MB | NPU
94
- | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.555 ms | 0 - 60 MB | NPU
95
  | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.444 ms | 2 - 60 MB | NPU
96
- | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® X2 Elite | 0.584 ms | 1 - 1 MB | NPU
97
- | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® X Elite | 1.491 ms | 6 - 6 MB | NPU
98
- | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 0.951 ms | 0 - 84 MB | NPU
99
- | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-8275 | 1.365 ms | 0 - 4 MB | NPU
100
- | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.432 ms | 0 - 9 MB | NPU
101
- | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-9075 | 1.574 ms | 0 - 3 MB | NPU
102
- | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-X7181 | 1.491 ms | 6 - 6 MB | NPU
103
- | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-6690 | 5.892 ms | 0 - 65 MB | NPU
104
- | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-7790 | 1.475 ms | 0 - 59 MB | NPU
105
- | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-8750 | 0.68 ms | 0 - 63 MB | NPU
106
- | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® 8 Elite Mobile | 0.68 ms | 0 - 63 MB | NPU
107
- | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.553 ms | 0 - 63 MB | NPU
108
- | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 1.475 ms | 0 - 59 MB | NPU
109
- | EfficientNet-B0 | QNN_DLC | float | Snapdragon® X2 Elite | 0.844 ms | 1 - 1 MB | NPU
110
- | EfficientNet-B0 | QNN_DLC | float | Snapdragon® X Elite | 1.753 ms | 1 - 1 MB | NPU
111
- | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.075 ms | 0 - 65 MB | NPU
112
- | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 3.614 ms | 0 - 74 MB | NPU
113
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 1.783 ms | 1 - 4 MB | NPU
114
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.562 ms | 0 - 7 MB | NPU
115
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8775P | 2.009 ms | 1 - 40 MB | NPU
116
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8650P | 2.009 ms | 1 - 40 MB | NPU
117
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8255P | 2.009 ms | 1 - 40 MB | NPU
118
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® QCS8450 | 3.614 ms | 0 - 74 MB | NPU
119
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.871 ms | 1 - 3 MB | NPU
120
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.753 ms | 1 - 1 MB | NPU
121
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.806 ms | 1 - 36 MB | NPU
122
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA7255P | 4.947 ms | 1 - 36 MB | NPU
123
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8295P | 3.618 ms | 0 - 43 MB | NPU
124
- | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.806 ms | 1 - 36 MB | NPU
125
- | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.613 ms | 1 - 42 MB | NPU
 
126
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.803 ms | 0 - 0 MB | NPU
127
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.862 ms | 0 - 0 MB | NPU
128
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.132 ms | 0 - 66 MB | NPU
@@ -141,40 +142,36 @@ See our repository for [EfficientNet-B0 on GitHub](https://github.com/qualcomm/a
141
  | EfficientNet-B0 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.773 ms | 0 - 46 MB | NPU
142
  | EfficientNet-B0 | QNN_DLC | w8a16 | Qualcomm® SA7255P | 3.281 ms | 0 - 47 MB | NPU
143
  | EfficientNet-B0 | QNN_DLC | w8a16 | Qualcomm® SA8295P | 2.375 ms | 0 - 46 MB | NPU
144
- | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 0.773 ms | 0 - 46 MB | NPU
145
- | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.645 ms | 0 - 47 MB | NPU
146
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.708 ms | 0 - 48 MB | NPU
147
- | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® X2 Elite | 0.816 ms | 0 - 0 MB | NPU
148
- | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® X Elite | 1.9 ms | 0 - 0 MB | NPU
149
- | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 1.134 ms | 0 - 66 MB | NPU
150
- | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-8275 | 1.586 ms | 0 - 3 MB | NPU
151
- | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.675 ms | 0 - 2 MB | NPU
152
- | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA8775P | 1.951 ms | 0 - 51 MB | NPU
 
153
  | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA8650P | 1.951 ms | 0 - 51 MB | NPU
154
  | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA8255P | 1.951 ms | 0 - 51 MB | NPU
155
- | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-9075 | 1.803 ms | 0 - 2 MB | NPU
156
- | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-X7181 | 1.9 ms | 0 - 0 MB | NPU
157
- | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-6690 | 6.742 ms | 0 - 169 MB | NPU
158
- | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-7790 | 1.718 ms | 0 - 48 MB | NPU
159
- | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-8750 | 0.779 ms | 0 - 47 MB | NPU
160
- | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA7255P | 3.3 ms | 0 - 48 MB | NPU
161
- | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Elite Mobile | 0.779 ms | 0 - 47 MB | NPU
162
- | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.634 ms | 0 - 47 MB | NPU
163
- | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 1.718 ms | 0 - 48 MB | NPU
164
- | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.068 ms | 0 - 65 MB | NPU
165
- | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 3.59 ms | 0 - 80 MB | NPU
166
- | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 1.795 ms | 0 - 17 MB | NPU
167
- | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.532 ms | 0 - 2 MB | NPU
168
- | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8775P | 2.025 ms | 0 - 45 MB | NPU
169
- | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8650P | 2.025 ms | 0 - 45 MB | NPU
170
- | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8255P | 2.025 ms | 0 - 45 MB | NPU
171
- | EfficientNet-B0 | TFLITE | float | Qualcomm® QCS8450 | 3.59 ms | 0 - 80 MB | NPU
172
- | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.882 ms | 0 - 16 MB | NPU
173
- | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.816 ms | 0 - 46 MB | NPU
174
- | EfficientNet-B0 | TFLITE | float | Qualcomm® SA7255P | 4.922 ms | 0 - 41 MB | NPU
175
- | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8295P | 3.634 ms | 0 - 48 MB | NPU
176
- | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.816 ms | 0 - 46 MB | NPU
177
- | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.611 ms | 0 - 41 MB | NPU
178
 
179
  ## License
180
  * The license for the original implementation of EfficientNet-B0 can be found
 
16
  EfficientNetB0 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-B0 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/v0.63.0/src/qai_hub_models/models/efficientnet_b0) 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 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b0/releases/v0.63.0/efficientnet_b0-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_b0/releases/v0.63.0/efficientnet_b0-onnx-w8a16.zip)
34
+ | ONNX | w8a16_mixed_int16 | Universal | QAIRT 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b0/releases/v0.63.0/efficientnet_b0-onnx-w8a16_mixed_int16.zip)
35
+ | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b0/releases/v0.63.0/efficientnet_b0-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/efficientnet_b0/releases/v0.63.0/efficientnet_b0-qnn_dlc-w8a16.zip)
37
+ | QNN_DLC | w8a16_mixed_int16 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b0/releases/v0.63.0/efficientnet_b0-qnn_dlc-w8a16_mixed_int16.zip)
38
+ | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b0/releases/v0.63.0/efficientnet_b0-tflite-float.zip)
39
 
40
  For more device-specific assets and performance metrics, visit **[EfficientNet-B0 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientnet_b0)**.
41
 
42
 
43
  ### Option 2: Export with Custom Configurations
44
 
45
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/efficientnet_b0) Python library to compile and export the model with your own:
46
  - Custom weights (e.g., fine-tuned checkpoints)
47
  - Custom input shapes
48
  - Target device and runtime configurations
49
 
50
  This option is ideal if you need to customize the model beyond the default configuration provided here.
51
 
52
+ See our repository for [EfficientNet-B0 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/efficientnet_b0) for usage instructions.
53
 
54
  ## Model Details
55
 
 
65
  ## Performance Summary
66
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
67
  |---|---|---|---|---|---|---
68
+ | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.544 ms | 0 - 46 MB | NPU
69
+ | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.701 ms | 0 - 46 MB | NPU
70
+ | EfficientNet-B0 | ONNX | float | Snapdragon® X2 Elite | 0.658 ms | 2 - 2 MB | NPU
71
+ | EfficientNet-B0 | ONNX | float | Snapdragon® X Elite | 1.301 ms | 13 - 13 MB | NPU
72
+ | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.896 ms | 0 - 71 MB | NPU
73
+ | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2.768 ms | 1 - 81 MB | NPU
74
+ | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 1.607 ms | 1 - 5 MB | NPU
75
+ | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.26 ms | 1 - 3 MB | NPU
76
+ | EfficientNet-B0 | ONNX | float | Qualcomm® QCS8450 | 2.768 ms | 1 - 81 MB | NPU
77
+ | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 1.608 ms | 1 - 4 MB | NPU
78
+ | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.301 ms | 13 - 13 MB | NPU
79
+ | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.701 ms | 0 - 46 MB | NPU
80
+ | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.555 ms | 0 - 60 MB | NPU
81
+ | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.668 ms | 0 - 57 MB | NPU
82
  | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® X2 Elite | 0.571 ms | 1 - 1 MB | NPU
83
  | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® X Elite | 1.486 ms | 6 - 6 MB | NPU
84
  | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.949 ms | 0 - 82 MB | NPU
 
92
  | EfficientNet-B0 | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 5.691 ms | 0 - 65 MB | NPU
93
  | EfficientNet-B0 | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 1.444 ms | 2 - 60 MB | NPU
94
  | EfficientNet-B0 | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.668 ms | 0 - 57 MB | NPU
 
 
95
  | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.444 ms | 2 - 60 MB | NPU
96
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.571 ms | 0 - 63 MB | NPU
97
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.671 ms | 0 - 63 MB | NPU
98
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® X2 Elite | 0.586 ms | 1 - 1 MB | NPU
99
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® X Elite | 1.513 ms | 7 - 7 MB | NPU
100
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 0.975 ms | 0 - 83 MB | NPU
101
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-8275 | 1.397 ms | 0 - 4 MB | NPU
102
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.451 ms | 0 - 2 MB | NPU
103
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-9075 | 1.608 ms | 0 - 3 MB | NPU
104
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-X7181 | 1.513 ms | 7 - 7 MB | NPU
105
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-6690 | 6.127 ms | 0 - 178 MB | NPU
106
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-7790 | 1.495 ms | 0 - 63 MB | NPU
107
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-8750 | 0.671 ms | 0 - 63 MB | NPU
108
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 1.495 ms | 0 - 63 MB | NPU
109
+ | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.607 ms | 0 - 40 MB | NPU
110
+ | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.816 ms | 1 - 45 MB | NPU
111
+ | EfficientNet-B0 | QNN_DLC | float | Snapdragon® X2 Elite | 0.834 ms | 1 - 1 MB | NPU
112
+ | EfficientNet-B0 | QNN_DLC | float | Snapdragon® X Elite | 1.732 ms | 1 - 1 MB | NPU
113
+ | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.084 ms | 0 - 63 MB | NPU
114
+ | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 3.406 ms | 0 - 77 MB | NPU
115
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 1.79 ms | 1 - 4 MB | NPU
116
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.539 ms | 1 - 3 MB | NPU
117
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8775P | 1.996 ms | 1 - 44 MB | NPU
118
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8650P | 1.996 ms | 1 - 44 MB | NPU
119
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8255P | 1.996 ms | 1 - 44 MB | NPU
120
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® QCS8450 | 3.406 ms | 0 - 77 MB | NPU
121
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.875 ms | 1 - 3 MB | NPU
122
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.732 ms | 1 - 1 MB | NPU
123
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.816 ms | 1 - 45 MB | NPU
124
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8295P | 3.472 ms | 0 - 46 MB | NPU
125
+ | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.645 ms | 0 - 47 MB | NPU
126
+ | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.773 ms | 0 - 46 MB | NPU
127
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.803 ms | 0 - 0 MB | NPU
128
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.862 ms | 0 - 0 MB | NPU
129
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.132 ms | 0 - 66 MB | NPU
 
142
  | EfficientNet-B0 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.773 ms | 0 - 46 MB | NPU
143
  | EfficientNet-B0 | QNN_DLC | w8a16 | Qualcomm® SA7255P | 3.281 ms | 0 - 47 MB | NPU
144
  | EfficientNet-B0 | QNN_DLC | w8a16 | Qualcomm® SA8295P | 2.375 ms | 0 - 46 MB | NPU
 
 
145
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.708 ms | 0 - 48 MB | NPU
146
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.653 ms | 0 - 52 MB | NPU
147
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.782 ms | 0 - 52 MB | NPU
148
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® X2 Elite | 0.8 ms | 0 - 0 MB | NPU
149
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® X Elite | 1.923 ms | 0 - 0 MB | NPU
150
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 1.143 ms | 0 - 71 MB | NPU
151
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-8275 | 1.619 ms | 0 - 3 MB | NPU
152
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.704 ms | 0 - 52 MB | NPU
153
  | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA8650P | 1.951 ms | 0 - 51 MB | NPU
154
  | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA8255P | 1.951 ms | 0 - 51 MB | NPU
155
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-9075 | 1.831 ms | 0 - 3 MB | NPU
156
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-X7181 | 1.923 ms | 0 - 0 MB | NPU
157
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-6690 | 7.41 ms | 0 - 167 MB | NPU
158
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-7790 | 1.751 ms | 0 - 53 MB | NPU
159
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-8750 | 0.782 ms | 0 - 52 MB | NPU
160
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 1.751 ms | 0 - 53 MB | NPU
161
+ | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.616 ms | 0 - 45 MB | NPU
162
+ | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.817 ms | 0 - 43 MB | NPU
163
+ | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.084 ms | 0 - 70 MB | NPU
164
+ | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 3.375 ms | 0 - 84 MB | NPU
165
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 1.815 ms | 0 - 17 MB | NPU
166
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.538 ms | 0 - 6 MB | NPU
167
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8775P | 2.003 ms | 0 - 48 MB | NPU
168
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8650P | 2.003 ms | 0 - 48 MB | NPU
169
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8255P | 2.003 ms | 0 - 48 MB | NPU
170
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® QCS8450 | 3.375 ms | 0 - 84 MB | NPU
171
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.868 ms | 0 - 16 MB | NPU
172
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.817 ms | 0 - 43 MB | NPU
173
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® SA7255P | 4.907 ms | 0 - 45 MB | NPU
174
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8295P | 3.48 ms | 0 - 51 MB | NPU
 
 
 
175
 
176
  ## License
177
  * The license for the original implementation of EfficientNet-B0 can be found
release_assets.json CHANGED
@@ -1,26 +1,26 @@
1
  {
2
- "version": "0.62.2",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
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_b0/releases/v0.62.2/efficientnet_b0-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_b0/releases/v0.62.2/efficientnet_b0-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_b0/releases/v0.62.2/efficientnet_b0-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_b0/releases/v0.62.2/efficientnet_b0-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_b0/releases/v0.62.2/efficientnet_b0-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  },
@@ -45,16 +45,16 @@
45
  "universal_assets": {
46
  "onnx": {
47
  "tool_versions": {
48
- "qairt": "2.45.0.260326154327",
49
  "onnx_runtime": "1.27.1"
50
  },
51
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b0/releases/v0.62.2/efficientnet_b0-onnx-w8a16_mixed_int16.zip"
52
  },
53
  "qnn_dlc": {
54
  "tool_versions": {
55
- "qairt": "2.45.0.260326154327"
56
  },
57
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b0/releases/v0.62.2/efficientnet_b0-qnn_dlc-w8a16_mixed_int16.zip"
58
  }
59
  }
60
  }
 
1
  {
2
+ "version": "0.63.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
  "onnx": {
7
  "tool_versions": {
8
+ "qairt": "2.50.0.260828221209",
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_b0/releases/v0.63.0/efficientnet_b0-onnx-float.zip"
12
  },
13
  "qnn_dlc": {
14
  "tool_versions": {
15
+ "qairt": "2.50.0.260828221209"
16
  },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b0/releases/v0.63.0/efficientnet_b0-qnn_dlc-float.zip"
18
  },
19
  "tflite": {
20
  "tool_versions": {
21
+ "qairt": "2.50.0.260828221209"
22
  },
23
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b0/releases/v0.63.0/efficientnet_b0-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_b0/releases/v0.63.0/efficientnet_b0-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_b0/releases/v0.63.0/efficientnet_b0-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  },
 
45
  "universal_assets": {
46
  "onnx": {
47
  "tool_versions": {
48
+ "qairt": "2.50.0.260828221209",
49
  "onnx_runtime": "1.27.1"
50
  },
51
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b0/releases/v0.63.0/efficientnet_b0-onnx-w8a16_mixed_int16.zip"
52
  },
53
  "qnn_dlc": {
54
  "tool_versions": {
55
+ "qairt": "2.50.0.260828221209"
56
  },
57
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b0/releases/v0.63.0/efficientnet_b0-qnn_dlc-w8a16_mixed_int16.zip"
58
  }
59
  }
60
  }