Hugging Face's logo

qualcomm
/
MobileNet-v3-Large

Image Classification
PyTorch
backbone
bu_auto
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
bc01c42
·
verified ·
1 Parent(s): 45e19e6

v0.59.0

Browse files

See https://github.com/qualcomm/ai-hub-models/releases/v0.59.0 for changelog.

Files changed (2) hide show
  1. README.md +81 -84
  2. release_assets.json +15 -16
README.md CHANGED
@@ -17,7 +17,7 @@ pipeline_tag: image-classification
17
  MobileNet-v3-Large is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
18
 
19
  This is based on the implementation of MobileNet-v3-Large found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/mobilenetv3.py).
20
- This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/mobilenet_v3_large) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
21
 
22
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
23
 
@@ -30,25 +30,25 @@ Below are pre-exported model assets ready for deployment.
30
 
31
  | Runtime | Precision | Chipset | SDK Versions | Download |
32
  |---|---|---|---|---|
33
- | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.58.0/mobilenet_v3_large-onnx-float.zip)
34
- | ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.58.0/mobilenet_v3_large-onnx-w8a16.zip)
35
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.58.0/mobilenet_v3_large-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/mobilenet_v3_large/releases/v0.58.0/mobilenet_v3_large-qnn_dlc-w8a16.zip)
37
- | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.58.0/mobilenet_v3_large-tflite-float.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[MobileNet-v3-Large on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/mobilenet_v3_large)**.
40
 
41
 
42
  ### Option 2: Export with Custom Configurations
43
 
44
- Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/mobilenet_v3_large) Python library to compile and export the model with your own:
45
  - Custom weights (e.g., fine-tuned checkpoints)
46
  - Custom input shapes
47
  - Target device and runtime configurations
48
 
49
  This option is ideal if you need to customize the model beyond the default configuration provided here.
50
 
51
- See our repository for [MobileNet-v3-Large on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.58.0/src/qai_hub_models/models/mobilenet_v3_large) for usage instructions.
52
 
53
  ## Model Details
54
 
@@ -64,84 +64,81 @@ See our repository for [MobileNet-v3-Large on GitHub](https://github.com/qualcom
64
  ## Performance Summary
65
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
66
  |---|---|---|---|---|---|---
67
- | MobileNet-v3-Large | ONNX | float | Snapdragon® X2 Elite | 0.326 ms | 2 - 2 MB | NPU
68
- | MobileNet-v3-Large | ONNX | float | Snapdragon® X Elite | 0.73 ms | 13 - 13 MB | NPU
69
- | MobileNet-v3-Large | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.489 ms | 0 - 52 MB | NPU
70
- | MobileNet-v3-Large | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 1.231 ms | 1 - 61 MB | NPU
71
- | MobileNet-v3-Large | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.709 ms | 0 - 16 MB | NPU
72
- | MobileNet-v3-Large | ONNX | float | Qualcomm® QCS8450 | 1.231 ms | 1 - 61 MB | NPU
73
- | MobileNet-v3-Large | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 0.963 ms | 1 - 3 MB | NPU
 
 
 
74
  | MobileNet-v3-Large | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.36 ms | 0 - 31 MB | NPU
75
- | MobileNet-v3-Large | ONNX | float | Snapdragon® 8 Elite Mobile | 0.401 ms | 0 - 30 MB | NPU
76
- | MobileNet-v3-Large | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.401 ms | 0 - 30 MB | NPU
77
- | MobileNet-v3-Large | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.73 ms | 13 - 13 MB | NPU
78
- | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® X2 Elite | 0.308 ms | 1 - 1 MB | NPU
79
- | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® X Elite | 0.708 ms | 6 - 6 MB | NPU
80
- | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.472 ms | 0 - 61 MB | NPU
81
- | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 0.951 ms | 0 - 68 MB | NPU
82
- | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 2.829 ms | 0 - 3 MB | NPU
83
- | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.683 ms | 0 - 3 MB | NPU
84
- | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® QCS8450 | 0.951 ms | 0 - 68 MB | NPU
85
- | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 0.797 ms | 0 - 3 MB | NPU
86
- | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 0.727 ms | 0 - 42 MB | NPU
87
- | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.292 ms | 0 - 41 MB | NPU
88
- | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 3.199 ms | 0 - 157 MB | NPU
89
- | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 0.361 ms | 0 - 41 MB | NPU
90
- | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 0.727 ms | 0 - 42 MB | NPU
91
- | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.361 ms | 0 - 41 MB | NPU
92
- | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 0.708 ms | 6 - 6 MB | NPU
93
- | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® X2 Elite | 0.512 ms | 1 - 1 MB | NPU
94
- | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® X Elite | 1.187 ms | 1 - 1 MB | NPU
95
- | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.686 ms | 0 - 51 MB | NPU
96
- | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 1.899 ms | 0 - 58 MB | NPU
97
- | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® QCS8275 | 2.927 ms | 1 - 31 MB | NPU
98
- | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.022 ms | 1 - 2 MB | NPU
99
- | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® SA8775P | 1.357 ms | 1 - 33 MB | NPU
100
- | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® SA8650P | 1.357 ms | 1 - 33 MB | NPU
101
- | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® SA8255P | 1.357 ms | 1 - 33 MB | NPU
102
- | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® QCS8450 | 1.899 ms | 0 - 58 MB | NPU
103
- | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.235 ms | 1 - 3 MB | NPU
104
- | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.428 ms | 1 - 34 MB | NPU
105
- | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® SA7255P | 2.927 ms | 1 - 31 MB | NPU
106
- | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.517 ms | 1 - 36 MB | NPU
107
- | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® SA8295P | 1.828 ms | 0 - 31 MB | NPU
108
- | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.517 ms | 1 - 36 MB | NPU
109
- | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.187 ms | 1 - 1 MB | NPU
110
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.502 ms | 0 - 0 MB | NPU
111
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.073 ms | 0 - 0 MB | NPU
112
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.657 ms | 0 - 50 MB | NPU
113
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 1.221 ms | 0 - 58 MB | NPU
114
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 3.191 ms | 2 - 4 MB | NPU
115
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® QCS8275 | 2.081 ms | 0 - 36 MB | NPU
116
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.933 ms | 0 - 64 MB | NPU
117
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® SA8775P | 1.151 ms | 0 - 38 MB | NPU
118
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® SA8650P | 1.151 ms | 0 - 38 MB | NPU
119
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® SA8255P | 1.151 ms | 0 - 38 MB | NPU
120
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 1.221 ms | 0 - 58 MB | NPU
121
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 1.029 ms | 0 - 2 MB | NPU
122
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 0.992 ms | 0 - 35 MB | NPU
123
  | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.367 ms | 0 - 36 MB | NPU
124
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 4.021 ms | 0 - 150 MB | NPU
125
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® SA7255P | 2.081 ms | 0 - 36 MB | NPU
126
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 0.459 ms | 0 - 39 MB | NPU
127
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® SA8295P | 1.562 ms | 0 - 36 MB | NPU
128
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 0.992 ms | 0 - 35 MB | NPU
129
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.459 ms | 0 - 39 MB | NPU
130
- | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 1.073 ms | 0 - 0 MB | NPU
131
- | MobileNet-v3-Large | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.699 ms | 0 - 55 MB | NPU
132
- | MobileNet-v3-Large | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 1.92 ms | 0 - 62 MB | NPU
133
- | MobileNet-v3-Large | TFLITE | float | Qualcomm® QCS8275 | 3.12 ms | 0 - 35 MB | NPU
134
- | MobileNet-v3-Large | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.039 ms | 0 - 17 MB | NPU
135
- | MobileNet-v3-Large | TFLITE | float | Qualcomm® SA8775P | 1.407 ms | 0 - 38 MB | NPU
136
- | MobileNet-v3-Large | TFLITE | float | Qualcomm® SA8650P | 1.407 ms | 0 - 38 MB | NPU
137
- | MobileNet-v3-Large | TFLITE | float | Qualcomm® SA8255P | 1.407 ms | 0 - 38 MB | NPU
138
- | MobileNet-v3-Large | TFLITE | float | Qualcomm® QCS8450 | 1.92 ms | 0 - 62 MB | NPU
139
- | MobileNet-v3-Large | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.274 ms | 0 - 15 MB | NPU
140
- | MobileNet-v3-Large | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.435 ms | 0 - 36 MB | NPU
141
- | MobileNet-v3-Large | TFLITE | float | Qualcomm® SA7255P | 3.12 ms | 0 - 35 MB | NPU
142
- | MobileNet-v3-Large | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.529 ms | 0 - 36 MB | NPU
143
- | MobileNet-v3-Large | TFLITE | float | Qualcomm® SA8295P | 1.869 ms | 0 - 35 MB | NPU
144
- | MobileNet-v3-Large | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.529 ms | 0 - 36 MB | NPU
145
 
146
  ## License
147
  * The license for the original implementation of MobileNet-v3-Large can be found
 
17
  MobileNet-v3-Large is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.
18
 
19
  This is based on the implementation of MobileNet-v3-Large found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/mobilenetv3.py).
20
+ This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/mobilenet_v3_large) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
21
 
22
  Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
23
 
 
30
 
31
  | Runtime | Precision | Chipset | SDK Versions | Download |
32
  |---|---|---|---|---|
33
+ | ONNX | float | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.59.0/mobilenet_v3_large-onnx-float.zip)
34
+ | ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.59.0/mobilenet_v3_large-onnx-w8a16.zip)
35
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.59.0/mobilenet_v3_large-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/mobilenet_v3_large/releases/v0.59.0/mobilenet_v3_large-qnn_dlc-w8a16.zip)
37
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.59.0/mobilenet_v3_large-tflite-float.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[MobileNet-v3-Large on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/mobilenet_v3_large)**.
40
 
41
 
42
  ### Option 2: Export with Custom Configurations
43
 
44
+ Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/mobilenet_v3_large) Python library to compile and export the model with your own:
45
  - Custom weights (e.g., fine-tuned checkpoints)
46
  - Custom input shapes
47
  - Target device and runtime configurations
48
 
49
  This option is ideal if you need to customize the model beyond the default configuration provided here.
50
 
51
+ See our repository for [MobileNet-v3-Large on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/mobilenet_v3_large) for usage instructions.
52
 
53
  ## Model Details
54
 
 
64
  ## Performance Summary
65
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
66
  |---|---|---|---|---|---|---
67
+ | MobileNet-v3-Large | ONNX | float | Snapdragon® X2 Elite | 0.33 ms | 2 - 2 MB | NPU
68
+ | MobileNet-v3-Large | ONNX | float | Snapdragon® X Elite | 0.72 ms | 12 - 12 MB | NPU
69
+ | MobileNet-v3-Large | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.491 ms | 0 - 57 MB | NPU
70
+ | MobileNet-v3-Large | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 1.212 ms | 1 - 59 MB | NPU
71
+ | MobileNet-v3-Large | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.713 ms | 0 - 15 MB | NPU
72
+ | MobileNet-v3-Large | ONNX | float | Qualcomm® QCS8450 | 1.212 ms | 1 - 59 MB | NPU
73
+ | MobileNet-v3-Large | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 0.961 ms | 1 - 3 MB | NPU
74
+ | MobileNet-v3-Large | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.72 ms | 12 - 12 MB | NPU
75
+ | MobileNet-v3-Large | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.4 ms | 0 - 30 MB | NPU
76
+ | MobileNet-v3-Large | ONNX | float | Snapdragon® 8 Elite Mobile | 0.4 ms | 0 - 30 MB | NPU
77
  | MobileNet-v3-Large | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.36 ms | 0 - 31 MB | NPU
78
+ | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® X2 Elite | 0.31 ms | 1 - 1 MB | NPU
79
+ | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® X Elite | 0.714 ms | 7 - 7 MB | NPU
80
+ | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.479 ms | 0 - 67 MB | NPU
81
+ | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 0.972 ms | 0 - 69 MB | NPU
82
+ | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 2.857 ms | 0 - 3 MB | NPU
83
+ | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.698 ms | 0 - 9 MB | NPU
84
+ | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® QCS8450 | 0.972 ms | 0 - 69 MB | NPU
85
+ | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 0.836 ms | 0 - 3 MB | NPU
86
+ | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 0.714 ms | 7 - 7 MB | NPU
87
+ | MobileNet-v3-Large | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.356 ms | 0 - 42 MB | NPU
88
+ | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 0.356 ms | 0 - 42 MB | NPU
89
+ | MobileNet-v3-Large | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.29 ms | 0 - 48 MB | NPU
90
+ | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® X2 Elite | 0.517 ms | 1 - 1 MB | NPU
91
+ | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® X Elite | 1.174 ms | 1 - 1 MB | NPU
92
+ | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.685 ms | 0 - 51 MB | NPU
93
+ | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 1.889 ms | 0 - 58 MB | NPU
94
+ | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 2.918 ms | 0 - 30 MB | NPU
95
+ | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.027 ms | 1 - 2 MB | NPU
96
+ | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® SA8775P | 1.368 ms | 1 - 33 MB | NPU
97
+ | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® SA8650P | 1.368 ms | 1 - 33 MB | NPU
98
+ | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® SA8255P | 1.368 ms | 1 - 33 MB | NPU
99
+ | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® QCS8450 | 1.889 ms | 0 - 58 MB | NPU
100
+ | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.223 ms | 3 - 5 MB | NPU
101
+ | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 1.174 ms | 1 - 1 MB | NPU
102
+ | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.527 ms | 0 - 35 MB | NPU
103
+ | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® SA7255P | 2.918 ms | 0 - 30 MB | NPU
104
+ | MobileNet-v3-Large | QNN_DLC | float | Qualcomm® SA8295P | 1.847 ms | 0 - 31 MB | NPU
105
+ | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.527 ms | 0 - 35 MB | NPU
106
+ | MobileNet-v3-Large | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.428 ms | 1 - 32 MB | NPU
107
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.508 ms | 0 - 0 MB | NPU
108
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® X Elite | 1.092 ms | 0 - 0 MB | NPU
109
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.659 ms | 0 - 52 MB | NPU
110
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 1.223 ms | 0 - 59 MB | NPU
111
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 3.369 ms | 0 - 2 MB | NPU
112
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8275 | 2.071 ms | 0 - 36 MB | NPU
113
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.95 ms | 0 - 2 MB | NPU
114
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® SA8775P | 1.172 ms | 0 - 39 MB | NPU
115
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® SA8650P | 1.172 ms | 0 - 39 MB | NPU
116
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® SA8255P | 1.172 ms | 0 - 39 MB | NPU
117
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® QCS8450 | 1.223 ms | 0 - 59 MB | NPU
118
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 1.034 ms | 2 - 4 MB | NPU
119
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 1.092 ms | 0 - 0 MB | NPU
120
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 4.344 ms | 0 - 151 MB | NPU
121
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 1.017 ms | 0 - 37 MB | NPU
122
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.464 ms | 0 - 35 MB | NPU
123
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® SA7255P | 2.071 ms | 0 - 36 MB | NPU
124
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Qualcomm® SA8295P | 1.586 ms | 0 - 37 MB | NPU
125
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 0.464 ms | 0 - 35 MB | NPU
126
  | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.367 ms | 0 - 36 MB | NPU
127
+ | MobileNet-v3-Large | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 1.017 ms | 0 - 37 MB | NPU
128
+ | MobileNet-v3-Large | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.696 ms | 0 - 56 MB | NPU
129
+ | MobileNet-v3-Large | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 1.915 ms | 0 - 66 MB | NPU
130
+ | MobileNet-v3-Large | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 3.078 ms | 0 - 35 MB | NPU
131
+ | MobileNet-v3-Large | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1.039 ms | 0 - 2 MB | NPU
132
+ | MobileNet-v3-Large | TFLITE | float | Qualcomm® SA8775P | 1.415 ms | 0 - 38 MB | NPU
133
+ | MobileNet-v3-Large | TFLITE | float | Qualcomm® SA8650P | 1.415 ms | 0 - 38 MB | NPU
134
+ | MobileNet-v3-Large | TFLITE | float | Qualcomm® SA8255P | 1.415 ms | 0 - 38 MB | NPU
135
+ | MobileNet-v3-Large | TFLITE | float | Qualcomm® QCS8450 | 1.915 ms | 0 - 66 MB | NPU
136
+ | MobileNet-v3-Large | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.281 ms | 0 - 15 MB | NPU
137
+ | MobileNet-v3-Large | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.528 ms | 0 - 41 MB | NPU
138
+ | MobileNet-v3-Large | TFLITE | float | Qualcomm® SA7255P | 3.078 ms | 0 - 35 MB | NPU
139
+ | MobileNet-v3-Large | TFLITE | float | Qualcomm® SA8295P | 1.864 ms | 0 - 35 MB | NPU
140
+ | MobileNet-v3-Large | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.528 ms | 0 - 41 MB | NPU
141
+ | MobileNet-v3-Large | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.436 ms | 0 - 36 MB | NPU
 
 
 
 
 
 
142
 
143
  ## License
144
  * The license for the original implementation of MobileNet-v3-Large can be found
release_assets.json CHANGED
@@ -1,44 +1,43 @@
1
  {
2
- "version": "0.58.0",
3
  "precisions": {
4
  "float": {
5
  "universal_assets": {
6
- "tflite": {
7
  "tool_versions": {
8
  "qairt": "2.45.0.260326154327",
9
- "litert": "1.4.4"
10
  },
11
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.58.0/mobilenet_v3_large-tflite-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/mobilenet_v3_large/releases/v0.58.0/mobilenet_v3_large-qnn_dlc-float.zip"
18
  },
19
- "onnx": {
20
  "tool_versions": {
21
- "qairt": "2.45.0.260326154327",
22
- "onnx_runtime": "1.25.0"
23
  },
24
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.58.0/mobilenet_v3_large-onnx-float.zip"
25
  }
26
  }
27
  },
28
  "w8a16": {
29
  "universal_assets": {
30
- "qnn_dlc": {
31
  "tool_versions": {
32
- "qairt": "2.45.0.260326154327"
 
33
  },
34
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.58.0/mobilenet_v3_large-qnn_dlc-w8a16.zip"
35
  },
36
- "onnx": {
37
  "tool_versions": {
38
- "qairt": "2.45.0.260326154327",
39
- "onnx_runtime": "1.25.0"
40
  },
41
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.58.0/mobilenet_v3_large-onnx-w8a16.zip"
42
  }
43
  }
44
  }
 
1
  {
2
+ "version": "0.59.0",
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/mobilenet_v3_large/releases/v0.59.0/mobilenet_v3_large-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/mobilenet_v3_large/releases/v0.59.0/mobilenet_v3_large-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/mobilenet_v3_large/releases/v0.59.0/mobilenet_v3_large-tflite-float.zip"
24
  }
25
  }
26
  },
27
  "w8a16": {
28
  "universal_assets": {
29
+ "onnx": {
30
  "tool_versions": {
31
+ "qairt": "2.45.0.260326154327",
32
+ "onnx_runtime": "1.27.1"
33
  },
34
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_large/releases/v0.59.0/mobilenet_v3_large-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/mobilenet_v3_large/releases/v0.59.0/mobilenet_v3_large-qnn_dlc-w8a16.zip"
41
  }
42
  }
43
  }