Hugging Face's logo

qualcomm
/
EfficientNet-B0

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
ba5d995
·
verified ·
1 Parent(s): 7e6cc3c

v0.61.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.61.0 for changelog.

Files changed (2) hide show
  1. README.md +87 -53
  2. release_assets.json +23 -6
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: pytorch
3
- license: other
4
  tags:
5
  - backbone
6
  - bu_auto
@@ -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/v0.60.0/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
 
@@ -29,25 +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/v0.60.0/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/v0.60.0/efficientnet_b0-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_b0/releases/v0.60.0/efficientnet_b0-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_b0/releases/v0.60.0/efficientnet_b0-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_b0/releases/v0.60.0/efficientnet_b0-tflite-float.zip)
 
 
37
 
38
  For more device-specific assets and performance metrics, visit **[EfficientNet-B0 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/efficientnet_b0)**.
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_b0) 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-B0 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.60.0/src/qai_hub_models/models/efficientnet_b0) for usage instructions.
51
 
52
  ## Model Details
53
 
@@ -63,18 +65,18 @@ See our repository for [EfficientNet-B0 on GitHub](https://github.com/qualcomm/a
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
- | EfficientNet-B0 | ONNX | float | Snapdragon® X2 Elite | 0.652 ms | 2 - 2 MB | NPU
67
- | EfficientNet-B0 | ONNX | float | Snapdragon® X Elite | 1.302 ms | 14 - 14 MB | NPU
68
- | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.9 ms | 0 - 69 MB | NPU
69
- | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2.881 ms | 1 - 78 MB | NPU
70
- | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 1.607 ms | 1 - 4 MB | NPU
71
- | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.246 ms | 0 - 19 MB | NPU
72
- | EfficientNet-B0 | ONNX | float | Qualcomm® QCS8450 | 2.881 ms | 1 - 78 MB | NPU
73
- | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 1.626 ms | 1 - 3 MB | NPU
74
- | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.302 ms | 14 - 14 MB | NPU
75
- | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.7 ms | 0 - 37 MB | NPU
76
- | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Elite Mobile | 0.7 ms | 0 - 37 MB | NPU
77
- | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.552 ms | 0 - 40 MB | NPU
78
  | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® X2 Elite | 0.571 ms | 1 - 1 MB | NPU
79
  | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® X Elite | 1.486 ms | 6 - 6 MB | NPU
80
  | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.949 ms | 0 - 82 MB | NPU
@@ -91,23 +93,37 @@ See our repository for [EfficientNet-B0 on GitHub](https://github.com/qualcomm/a
91
  | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 0.668 ms | 0 - 57 MB | NPU
92
  | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.555 ms | 0 - 60 MB | NPU
93
  | EfficientNet-B0 | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.444 ms | 2 - 60 MB | NPU
94
- | EfficientNet-B0 | QNN_DLC | float | Snapdragon® X2 Elite | 0.855 ms | 1 - 1 MB | NPU
95
- | EfficientNet-B0 | QNN_DLC | float | Snapdragon® X Elite | 1.765 ms | 1 - 1 MB | NPU
96
- | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.065 ms | 0 - 61 MB | NPU
97
- | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 3.59 ms | 0 - 73 MB | NPU
98
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 4.906 ms | 1 - 36 MB | NPU
99
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.563 ms | 0 - 10 MB | NPU
100
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8775P | 2.015 ms | 1 - 39 MB | NPU
101
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8650P | 2.015 ms | 1 - 39 MB | NPU
102
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8255P | 2.015 ms | 1 - 39 MB | NPU
103
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® QCS8450 | 3.59 ms | 0 - 73 MB | NPU
104
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.866 ms | 1 - 3 MB | NPU
105
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.765 ms | 1 - 1 MB | NPU
106
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.806 ms | 0 - 36 MB | NPU
107
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA7255P | 4.906 ms | 1 - 36 MB | NPU
108
- | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8295P | 3.615 ms | 1 - 44 MB | NPU
109
- | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.806 ms | 0 - 36 MB | NPU
110
- | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.61 ms | 1 - 38 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
111
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.803 ms | 0 - 0 MB | NPU
112
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.862 ms | 0 - 0 MB | NPU
113
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1.132 ms | 0 - 66 MB | NPU
@@ -130,21 +146,39 @@ See our repository for [EfficientNet-B0 on GitHub](https://github.com/qualcomm/a
130
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 0.773 ms | 0 - 46 MB | NPU
131
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.645 ms | 0 - 47 MB | NPU
132
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.708 ms | 0 - 48 MB | NPU
133
- | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.064 ms | 0 - 66 MB | NPU
134
- | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 3.597 ms | 0 - 80 MB | NPU
135
- | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 1.796 ms | 0 - 17 MB | NPU
136
- | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 4.938 ms | 0 - 41 MB | NPU
137
- | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.539 ms | 0 - 2 MB | NPU
138
- | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8775P | 2.027 ms | 0 - 46 MB | NPU
139
- | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8650P | 2.027 ms | 0 - 46 MB | NPU
140
- | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8255P | 2.027 ms | 0 - 46 MB | NPU
141
- | EfficientNet-B0 | TFLITE | float | Qualcomm® QCS8450 | 3.597 ms | 0 - 80 MB | NPU
142
- | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 2.391 ms | 0 - 16 MB | NPU
143
- | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.816 ms | 0 - 41 MB | NPU
144
- | EfficientNet-B0 | TFLITE | float | Qualcomm® SA7255P | 4.938 ms | 0 - 41 MB | NPU
145
- | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8295P | 3.642 ms | 0 - 47 MB | NPU
146
- | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.816 ms | 0 - 41 MB | NPU
147
- | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.612 ms | 0 - 41 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
148
 
149
  ## License
150
  * The license for the original implementation of EfficientNet-B0 can be found
 
1
  ---
2
  library_name: pytorch
3
+ license: bsd-3-clause
4
  tags:
5
  - backbone
6
  - bu_auto
 
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/v0.61.0/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 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/efficientnet_b0/releases/v0.61.0/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/v0.61.0/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/v0.61.0/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/v0.61.0/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/v0.61.0/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/v0.61.0/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/v0.61.0/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/v0.61.0/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/v0.61.0/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® X2 Elite | 0.656 ms | 2 - 2 MB | NPU
69
+ | EfficientNet-B0 | ONNX | float | Snapdragon® X Elite | 1.313 ms | 14 - 14 MB | NPU
70
+ | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.894 ms | 0 - 71 MB | NPU
71
+ | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 2.874 ms | 1 - 77 MB | NPU
72
+ | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 1.615 ms | 1 - 4 MB | NPU
73
+ | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.253 ms | 0 - 15 MB | NPU
74
+ | EfficientNet-B0 | ONNX | float | Qualcomm® QCS8450 | 2.874 ms | 1 - 77 MB | NPU
75
+ | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 1.858 ms | 1 - 3 MB | NPU
76
+ | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.313 ms | 14 - 14 MB | NPU
77
+ | EfficientNet-B0 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.698 ms | 0 - 42 MB | NPU
78
+ | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Elite Mobile | 0.698 ms | 0 - 42 MB | NPU
79
+ | EfficientNet-B0 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.551 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
 
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 | 0.652 ms | 1 - 1 MB | NPU
97
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® X Elite | 1.493 ms | 6 - 6 MB | NPU
98
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 0.942 ms | 0 - 82 MB | NPU
99
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-8275 | 1.358 ms | 0 - 4 MB | NPU
100
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.43 ms | 0 - 9 MB | NPU
101
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-9075 | 1.573 ms | 0 - 3 MB | NPU
102
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-X7181 | 1.493 ms | 6 - 6 MB | NPU
103
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-6690 | 5.891 ms | 0 - 60 MB | NPU
104
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-7790 | 1.474 ms | 0 - 59 MB | NPU
105
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-8750 | 0.677 ms | 0 - 57 MB | NPU
106
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® 8 Elite Mobile | 0.677 ms | 0 - 57 MB | NPU
107
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.551 ms | 0 - 63 MB | NPU
108
+ | EfficientNet-B0 | ONNX | w8a16_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 1.474 ms | 0 - 59 MB | NPU
109
+ | EfficientNet-B0 | QNN_DLC | float | Snapdragon® X2 Elite | 0.841 ms | 1 - 1 MB | NPU
110
+ | EfficientNet-B0 | QNN_DLC | float | Snapdragon® X Elite | 1.758 ms | 1 - 1 MB | NPU
111
+ | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.078 ms | 0 - 64 MB | NPU
112
+ | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 3.609 ms | 0 - 73 MB | NPU
113
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 1.778 ms | 1 - 4 MB | NPU
114
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 4.892 ms | 1 - 36 MB | NPU
115
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.557 ms | 1 - 2 MB | NPU
116
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8775P | 2.021 ms | 0 - 39 MB | NPU
117
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8650P | 2.021 ms | 0 - 39 MB | NPU
118
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8255P | 2.021 ms | 0 - 39 MB | NPU
119
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® QCS8450 | 3.609 ms | 0 - 73 MB | NPU
120
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.867 ms | 1 - 3 MB | NPU
121
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.758 ms | 1 - 1 MB | NPU
122
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.807 ms | 1 - 41 MB | NPU
123
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA7255P | 4.892 ms | 1 - 36 MB | NPU
124
+ | EfficientNet-B0 | QNN_DLC | float | Qualcomm® SA8295P | 3.606 ms | 0 - 43 MB | NPU
125
+ | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.807 ms | 1 - 41 MB | NPU
126
+ | EfficientNet-B0 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.612 ms | 1 - 42 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
 
146
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 0.773 ms | 0 - 46 MB | NPU
147
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.645 ms | 0 - 47 MB | NPU
148
  | EfficientNet-B0 | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.708 ms | 0 - 48 MB | NPU
149
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® X2 Elite | 0.83 ms | 0 - 0 MB | NPU
150
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® X Elite | 1.875 ms | 0 - 0 MB | NPU
151
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 1.135 ms | 0 - 66 MB | NPU
152
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-8275 | 1.583 ms | 0 - 3 MB | NPU
153
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-8275 | 3.295 ms | 0 - 48 MB | NPU
154
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.679 ms | 0 - 2 MB | NPU
155
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA8775P | 1.971 ms | 0 - 51 MB | NPU
156
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA8650P | 1.971 ms | 0 - 51 MB | NPU
157
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA8255P | 1.971 ms | 0 - 51 MB | NPU
158
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-9075 | 1.798 ms | 0 - 2 MB | NPU
159
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-X7181 | 1.875 ms | 0 - 0 MB | NPU
160
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-6690 | 6.724 ms | 0 - 165 MB | NPU
161
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-7790 | 1.729 ms | 0 - 48 MB | NPU
162
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-8750 | 0.78 ms | 0 - 47 MB | NPU
163
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA7255P | 3.295 ms | 0 - 48 MB | NPU
164
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Elite Mobile | 0.78 ms | 0 - 47 MB | NPU
165
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.632 ms | 0 - 52 MB | NPU
166
+ | EfficientNet-B0 | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 1.729 ms | 0 - 48 MB | NPU
167
+ | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.065 ms | 0 - 66 MB | NPU
168
+ | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 3.613 ms | 0 - 80 MB | NPU
169
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 1.801 ms | 0 - 17 MB | NPU
170
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 4.92 ms | 0 - 41 MB | NPU
171
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.541 ms | 0 - 6 MB | NPU
172
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8775P | 2.03 ms | 0 - 45 MB | NPU
173
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8650P | 2.03 ms | 0 - 45 MB | NPU
174
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8255P | 2.03 ms | 0 - 45 MB | NPU
175
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® QCS8450 | 3.613 ms | 0 - 80 MB | NPU
176
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.883 ms | 0 - 16 MB | NPU
177
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.815 ms | 0 - 46 MB | NPU
178
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® SA7255P | 4.92 ms | 0 - 41 MB | NPU
179
+ | EfficientNet-B0 | TFLITE | float | Qualcomm® SA8295P | 3.634 ms | 0 - 48 MB | NPU
180
+ | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.815 ms | 0 - 46 MB | NPU
181
+ | EfficientNet-B0 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.613 ms | 0 - 45 MB | NPU
182
 
183
  ## License
184
  * The license for the original implementation of EfficientNet-B0 can be found
release_assets.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "version": "0.60.0",
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_b0/releases/v0.60.0/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/v0.60.0/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/v0.60.0/efficientnet_b0-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -31,13 +31,30 @@
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/v0.60.0/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/v0.60.0/efficientnet_b0-qnn_dlc-w8a16.zip"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41
  }
42
  }
43
  }
 
1
  {
2
+ "version": "0.61.0",
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_b0/releases/v0.61.0/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/v0.61.0/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/v0.61.0/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/v0.61.0/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/v0.61.0/efficientnet_b0-qnn_dlc-w8a16.zip"
41
+ }
42
+ }
43
+ },
44
+ "w8a16_mixed_int16": {
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/v0.61.0/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/v0.61.0/efficientnet_b0-qnn_dlc-w8a16_mixed_int16.zip"
58
  }
59
  }
60
  }