Hugging Face's logo

qualcomm
/
MobileNet-v3-Small

Image Classification
PyTorch
backbone
bu_auto
real_time
android
Model card Files
xet
 Community
qaihm-bot commited on
Commit
0fd14d1
·
verified ·
1 Parent(s): 07ead72

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 +60 -64
  2. release_assets.json +10 -10
README.md CHANGED
@@ -17,7 +17,7 @@ pipeline_tag: image-classification
17
  MobileNetV3Small 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-Small 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/v0.62.2/src/qai_hub_models/models/mobilenet_v3_small) 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 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.62.2/mobilenet_v3_small-onnx-float.zip)
34
- | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.62.2/mobilenet_v3_small-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/mobilenet_v3_small/releases/v0.62.2/mobilenet_v3_small-qnn_dlc-w8a16.zip)
36
- | QNN_DLC | w8a16_mixed_int16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.62.2/mobilenet_v3_small-qnn_dlc-w8a16_mixed_int16.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_small/releases/v0.62.2/mobilenet_v3_small-tflite-float.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[MobileNet-v3-Small on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/mobilenet_v3_small)**.
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/v0.62.2/src/qai_hub_models/models/mobilenet_v3_small) 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-Small on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.62.2/src/qai_hub_models/models/mobilenet_v3_small) for usage instructions.
52
 
53
  ## Model Details
54
 
@@ -63,35 +63,35 @@ See our repository for [MobileNet-v3-Small on GitHub](https://github.com/qualcom
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
- | MobileNet-v3-Small | ONNX | float | Snapdragon® X2 Elite | 0.25 ms | 2 - 2 MB | NPU
67
- | MobileNet-v3-Small | ONNX | float | Snapdragon® X Elite | 0.559 ms | 5 - 5 MB | NPU
68
- | MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.352 ms | 0 - 46 MB | NPU
69
- | MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 0.867 ms | 1 - 51 MB | NPU
70
- | MobileNet-v3-Small | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 0.664 ms | 0 - 4 MB | NPU
71
- | MobileNet-v3-Small | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.554 ms | 0 - 8 MB | NPU
72
- | MobileNet-v3-Small | ONNX | float | Qualcomm® QCS8450 | 0.867 ms | 1 - 51 MB | NPU
73
- | MobileNet-v3-Small | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 0.711 ms | 1 - 3 MB | NPU
74
- | MobileNet-v3-Small | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.559 ms | 5 - 5 MB | NPU
75
- | MobileNet-v3-Small | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.286 ms | 0 - 33 MB | NPU
76
- | MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Elite Mobile | 0.286 ms | 0 - 33 MB | NPU
77
- | MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.251 ms | 0 - 29 MB | NPU
78
- | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® X2 Elite | 0.435 ms | 1 - 1 MB | NPU
79
- | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® X Elite | 0.957 ms | 1 - 1 MB | NPU
80
- | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.551 ms | 0 - 43 MB | NPU
81
- | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 1.578 ms | 0 - 49 MB | NPU
82
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 0.887 ms | 1 - 4 MB | NPU
83
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.826 ms | 1 - 2 MB | NPU
84
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA8775P | 1.107 ms | 1 - 32 MB | NPU
 
85
  | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA8650P | 1.107 ms | 1 - 32 MB | NPU
86
  | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA8255P | 1.107 ms | 1 - 32 MB | NPU
87
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® QCS8450 | 1.578 ms | 0 - 49 MB | NPU
88
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 0.974 ms | 3 - 5 MB | NPU
89
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.957 ms | 1 - 1 MB | NPU
90
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.412 ms | 1 - 34 MB | NPU
91
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA7255P | 2.078 ms | 1 - 29 MB | NPU
92
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA8295P | 1.467 ms | 0 - 29 MB | NPU
93
- | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.412 ms | 1 - 34 MB | NPU
94
- | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.321 ms | 0 - 30 MB | NPU
95
  | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.426 ms | 0 - 0 MB | NPU
96
  | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® X Elite | 0.941 ms | 1 - 1 MB | NPU
97
  | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.545 ms | 0 - 39 MB | NPU
@@ -110,40 +110,36 @@ See our repository for [MobileNet-v3-Small on GitHub](https://github.com/qualcom
110
  | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.376 ms | 0 - 31 MB | NPU
111
  | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® SA7255P | 1.725 ms | 0 - 28 MB | NPU
112
  | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® SA8295P | 1.327 ms | 0 - 27 MB | NPU
113
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 0.376 ms | 0 - 31 MB | NPU
114
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.311 ms | 0 - 28 MB | NPU
115
  | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 0.808 ms | 0 - 26 MB | NPU
116
- | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Snapdragon® X2 Elite | 0.414 ms | 0 - 0 MB | NPU
117
- | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Snapdragon® X Elite | 0.946 ms | 0 - 0 MB | NPU
118
- | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 0.541 ms | 0 - 39 MB | NPU
119
- | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-8275 | 0.816 ms | 0 - 3 MB | NPU
120
- | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.813 ms | 0 - 2 MB | NPU
121
- | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA8775P | 1.02 ms | 0 - 30 MB | NPU
 
122
  | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA8650P | 1.02 ms | 0 - 30 MB | NPU
123
  | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA8255P | 1.02 ms | 0 - 30 MB | NPU
124
- | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-9075 | 0.903 ms | 0 - 2 MB | NPU
125
- | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-X7181 | 0.946 ms | 0 - 0 MB | NPU
126
- | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-6690 | 2.896 ms | 0 - 142 MB | NPU
127
- | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-7790 | 0.823 ms | 0 - 27 MB | NPU
128
- | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-8750 | 0.372 ms | 0 - 31 MB | NPU
129
- | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA7255P | 1.701 ms | 0 - 27 MB | NPU
130
- | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Elite Mobile | 0.372 ms | 0 - 31 MB | NPU
131
- | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.323 ms | 0 - 28 MB | NPU
132
- | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 0.823 ms | 0 - 27 MB | NPU
133
- | MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.555 ms | 0 - 44 MB | NPU
134
- | MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 1.584 ms | 0 - 51 MB | NPU
135
- | MobileNet-v3-Small | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 0.928 ms | 0 - 9 MB | NPU
136
- | MobileNet-v3-Small | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.836 ms | 0 - 3 MB | NPU
137
- | MobileNet-v3-Small | TFLITE | float | Qualcomm® SA8775P | 1.141 ms | 0 - 32 MB | NPU
138
  | MobileNet-v3-Small | TFLITE | float | Qualcomm® SA8650P | 1.141 ms | 0 - 32 MB | NPU
139
  | MobileNet-v3-Small | TFLITE | float | Qualcomm® SA8255P | 1.141 ms | 0 - 32 MB | NPU
140
- | MobileNet-v3-Small | TFLITE | float | Qualcomm® QCS8450 | 1.584 ms | 0 - 51 MB | NPU
141
- | MobileNet-v3-Small | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.005 ms | 0 - 8 MB | NPU
142
- | MobileNet-v3-Small | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.423 ms | 0 - 34 MB | NPU
143
- | MobileNet-v3-Small | TFLITE | float | Qualcomm® SA7255P | 2.171 ms | 0 - 29 MB | NPU
144
- | MobileNet-v3-Small | TFLITE | float | Qualcomm® SA8295P | 1.492 ms | 0 - 29 MB | NPU
145
- | MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.423 ms | 0 - 34 MB | NPU
146
- | MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.323 ms | 0 - 32 MB | NPU
147
 
148
  ## License
149
  * The license for the original implementation of MobileNet-v3-Small can be found
 
17
  MobileNetV3Small 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-Small 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/v0.63.0/src/qai_hub_models/models/mobilenet_v3_small) 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 2.50, ONNX Runtime 1.27.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.63.0/mobilenet_v3_small-onnx-float.zip)
34
+ | QNN_DLC | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.63.0/mobilenet_v3_small-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/mobilenet_v3_small/releases/v0.63.0/mobilenet_v3_small-qnn_dlc-w8a16.zip)
36
+ | QNN_DLC | w8a16_mixed_int16 | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.63.0/mobilenet_v3_small-qnn_dlc-w8a16_mixed_int16.zip)
37
+ | TFLITE | float | Universal | QAIRT 2.50 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.63.0/mobilenet_v3_small-tflite-float.zip)
38
 
39
  For more device-specific assets and performance metrics, visit **[MobileNet-v3-Small on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/mobilenet_v3_small)**.
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/v0.63.0/src/qai_hub_models/models/mobilenet_v3_small) 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-Small on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.63.0/src/qai_hub_models/models/mobilenet_v3_small) for usage instructions.
52
 
53
  ## Model Details
54
 
 
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
+ | MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.256 ms | 0 - 33 MB | NPU
67
+ | MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.287 ms | 0 - 37 MB | NPU
68
+ | MobileNet-v3-Small | ONNX | float | Snapdragon® X2 Elite | 0.268 ms | 2 - 2 MB | NPU
69
+ | MobileNet-v3-Small | ONNX | float | Snapdragon® X Elite | 0.549 ms | 5 - 5 MB | NPU
70
+ | MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.361 ms | 3 - 52 MB | NPU
71
+ | MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 0.801 ms | 1 - 55 MB | NPU
72
+ | MobileNet-v3-Small | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 0.675 ms | 0 - 4 MB | NPU
73
+ | MobileNet-v3-Small | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.547 ms | 0 - 8 MB | NPU
74
+ | MobileNet-v3-Small | ONNX | float | Qualcomm® QCS8450 | 0.801 ms | 1 - 55 MB | NPU
75
+ | MobileNet-v3-Small | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 0.714 ms | 1 - 4 MB | NPU
76
+ | MobileNet-v3-Small | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.549 ms | 5 - 5 MB | NPU
77
+ | MobileNet-v3-Small | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.287 ms | 0 - 37 MB | NPU
78
+ | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.318 ms | 0 - 34 MB | NPU
79
+ | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.416 ms | 1 - 36 MB | NPU
80
+ | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® X2 Elite | 0.439 ms | 1 - 1 MB | NPU
81
+ | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® X Elite | 0.971 ms | 1 - 1 MB | NPU
82
+ | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.558 ms | 0 - 46 MB | NPU
83
+ | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 1.469 ms | 0 - 54 MB | NPU
84
+ | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 0.899 ms | 1 - 4 MB | NPU
85
+ | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.838 ms | 1 - 42 MB | NPU
86
  | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA8650P | 1.107 ms | 1 - 32 MB | NPU
87
  | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA8255P | 1.107 ms | 1 - 32 MB | NPU
88
+ | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® QCS8450 | 1.469 ms | 0 - 54 MB | NPU
89
+ | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 1.027 ms | 1 - 3 MB | NPU
90
+ | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.971 ms | 1 - 1 MB | NPU
91
+ | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.416 ms | 1 - 36 MB | NPU
92
+ | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA8295P | 1.338 ms | 0 - 32 MB | NPU
93
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.311 ms | 0 - 28 MB | NPU
94
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.376 ms | 0 - 31 MB | NPU
 
95
  | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.426 ms | 0 - 0 MB | NPU
96
  | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® X Elite | 0.941 ms | 1 - 1 MB | NPU
97
  | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.545 ms | 0 - 39 MB | NPU
 
110
  | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.376 ms | 0 - 31 MB | NPU
111
  | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® SA7255P | 1.725 ms | 0 - 28 MB | NPU
112
  | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® SA8295P | 1.327 ms | 0 - 27 MB | NPU
 
 
113
  | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 0.808 ms | 0 - 26 MB | NPU
114
+ | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.317 ms | 0 - 32 MB | NPU
115
+ | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.382 ms | 0 - 35 MB | NPU
116
+ | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Snapdragon® X2 Elite | 0.442 ms | 0 - 0 MB | NPU
117
+ | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Snapdragon® X Elite | 0.943 ms | 0 - 0 MB | NPU
118
+ | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 0.567 ms | 0 - 44 MB | NPU
119
+ | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-8275 | 0.803 ms | 0 - 3 MB | NPU
120
+ | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.818 ms | 0 - 2 MB | NPU
121
  | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA8650P | 1.02 ms | 0 - 30 MB | NPU
122
  | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA8255P | 1.02 ms | 0 - 30 MB | NPU
123
+ | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-9075 | 0.897 ms | 0 - 3 MB | NPU
124
+ | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ IQ-X7181 | 0.943 ms | 0 - 0 MB | NPU
125
+ | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-6690 | 2.837 ms | 0 - 31 MB | NPU
126
+ | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-7790 | 0.823 ms | 0 - 31 MB | NPU
127
+ | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® Dragonwing™ Q-8750 | 0.382 ms | 0 - 35 MB | NPU
128
+ | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Qualcomm® SA7255P | 1.691 ms | 0 - 33 MB | NPU
129
+ | MobileNet-v3-Small | QNN_DLC | w8a16_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 0.823 ms | 0 - 31 MB | NPU
130
+ | MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Elite Gen 5 For Galaxy Mobile | 0.321 ms | 0 - 35 MB | NPU
131
+ | MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.43 ms | 0 - 32 MB | NPU
132
+ | MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.559 ms | 0 - 48 MB | NPU
133
+ | MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 1.484 ms | 0 - 54 MB | NPU
134
+ | MobileNet-v3-Small | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 0.926 ms | 0 - 10 MB | NPU
135
+ | MobileNet-v3-Small | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.857 ms | 0 - 7 MB | NPU
 
136
  | MobileNet-v3-Small | TFLITE | float | Qualcomm® SA8650P | 1.141 ms | 0 - 32 MB | NPU
137
  | MobileNet-v3-Small | TFLITE | float | Qualcomm® SA8255P | 1.141 ms | 0 - 32 MB | NPU
138
+ | MobileNet-v3-Small | TFLITE | float | Qualcomm® QCS8450 | 1.484 ms | 0 - 54 MB | NPU
139
+ | MobileNet-v3-Small | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 1.026 ms | 0 - 9 MB | NPU
140
+ | MobileNet-v3-Small | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.43 ms | 0 - 32 MB | NPU
141
+ | MobileNet-v3-Small | TFLITE | float | Qualcomm® SA7255P | 2.174 ms | 0 - 34 MB | NPU
142
+ | MobileNet-v3-Small | TFLITE | float | Qualcomm® SA8295P | 1.361 ms | 0 - 33 MB | NPU
 
 
143
 
144
  ## License
145
  * The license for the original implementation of MobileNet-v3-Small 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/mobilenet_v3_small/releases/v0.62.2/mobilenet_v3_small-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_small/releases/v0.62.2/mobilenet_v3_small-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_small/releases/v0.62.2/mobilenet_v3_small-tflite-float.zip"
24
  }
25
  }
26
  },
@@ -30,7 +30,7 @@
30
  "tool_versions": {
31
  "qairt": "2.45.0.260326154327"
32
  },
33
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.62.2/mobilenet_v3_small-qnn_dlc-w8a16.zip"
34
  }
35
  }
36
  },
@@ -38,9 +38,9 @@
38
  "universal_assets": {
39
  "qnn_dlc": {
40
  "tool_versions": {
41
- "qairt": "2.45.0.260326154327"
42
  },
43
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.62.2/mobilenet_v3_small-qnn_dlc-w8a16_mixed_int16.zip"
44
  }
45
  }
46
  }
 
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/mobilenet_v3_small/releases/v0.63.0/mobilenet_v3_small-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/mobilenet_v3_small/releases/v0.63.0/mobilenet_v3_small-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/mobilenet_v3_small/releases/v0.63.0/mobilenet_v3_small-tflite-float.zip"
24
  }
25
  }
26
  },
 
30
  "tool_versions": {
31
  "qairt": "2.45.0.260326154327"
32
  },
33
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.63.0/mobilenet_v3_small-qnn_dlc-w8a16.zip"
34
  }
35
  }
36
  },
 
38
  "universal_assets": {
39
  "qnn_dlc": {
40
  "tool_versions": {
41
+ "qairt": "2.50.0.260828221209"
42
  },
43
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.63.0/mobilenet_v3_small-qnn_dlc-w8a16_mixed_int16.zip"
44
  }
45
  }
46
  }