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
e9a3b2e
·
verified ·
1 Parent(s): 90e9e47

v0.48.0

Browse files

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

Files changed (1) hide show
  1. README.md +50 -50
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/quic/ai-hub-models/blob/main/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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.47.0/mobilenet_v3_small-onnx-float.zip)
34
- | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.47.0/mobilenet_v3_small-onnx-w8a16.zip)
35
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.47.0/mobilenet_v3_small-qnn_dlc-float.zip)
36
- | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.47.0/mobilenet_v3_small-qnn_dlc-w8a16.zip)
37
- | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.47.0/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/quic/ai-hub-models/blob/main/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/quic/ai-hub-models/blob/main/qai_hub_models/models/mobilenet_v3_small) for usage instructions.
52
 
53
  ## Model Details
54
 
@@ -63,50 +63,50 @@ See our repository for [MobileNet-v3-Small on GitHub](https://github.com/quic/ai
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
- | MobileNet-v3-Small | ONNX | float | Snapdragon® X Elite | 0.669 ms | 5 - 5 MB | NPU
67
- | MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.355 ms | 0 - 45 MB | NPU
68
- | MobileNet-v3-Small | ONNX | float | Qualcomm® QCS8550 (Proxy) | 0.541 ms | 0 - 8 MB | NPU
69
- | MobileNet-v3-Small | ONNX | float | Qualcomm® QCS9075 | 0.767 ms | 1 - 3 MB | NPU
70
- | MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.285 ms | 0 - 29 MB | NPU
 
71
  | MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.244 ms | 0 - 33 MB | NPU
72
- | MobileNet-v3-Small | ONNX | float | Snapdragon® X2 Elite | 0.251 ms | 5 - 5 MB | NPU
73
- | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® X Elite | 1.012 ms | 1 - 1 MB | NPU
74
- | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.557 ms | 0 - 46 MB | NPU
75
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 2.114 ms | 1 - 30 MB | NPU
76
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 0.845 ms | 1 - 2 MB | NPU
77
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA8775P | 1.148 ms | 0 - 32 MB | NPU
78
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® QCS9075 | 0.991 ms | 1 - 3 MB | NPU
79
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1.587 ms | 0 - 47 MB | NPU
80
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA7255P | 2.114 ms | 1 - 30 MB | NPU
81
- | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA8295P | 1.497 ms | 0 - 29 MB | NPU
82
  | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.427 ms | 0 - 30 MB | NPU
83
- | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.324 ms | 1 - 34 MB | NPU
84
- | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® X2 Elite | 0.452 ms | 1 - 1 MB | NPU
85
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® X Elite | 0.989 ms | 0 - 0 MB | NPU
86
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.556 ms | 0 - 37 MB | NPU
87
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 2.276 ms | 0 - 2 MB | NPU
88
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 1.7 ms | 0 - 25 MB | NPU
89
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 0.804 ms | 0 - 2 MB | NPU
90
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® SA8775P | 4.299 ms | 0 - 26 MB | NPU
91
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 0.976 ms | 0 - 2 MB | NPU
92
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 2.812 ms | 0 - 140 MB | NPU
93
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 0.986 ms | 0 - 40 MB | NPU
94
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® SA7255P | 1.7 ms | 0 - 25 MB | NPU
95
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® SA8295P | 1.369 ms | 0 - 23 MB | NPU
96
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.374 ms | 0 - 29 MB | NPU
97
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 0.791 ms | 0 - 25 MB | NPU
98
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.307 ms | 0 - 28 MB | NPU
99
- | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.453 ms | 0 - 0 MB | NPU
100
- | MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.562 ms | 0 - 46 MB | NPU
101
- | MobileNet-v3-Small | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 2.201 ms | 0 - 31 MB | NPU
102
- | MobileNet-v3-Small | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 0.86 ms | 0 - 2 MB | NPU
103
- | MobileNet-v3-Small | TFLITE | float | Qualcomm® SA8775P | 1.184 ms | 0 - 33 MB | NPU
104
- | MobileNet-v3-Small | TFLITE | float | Qualcomm® QCS9075 | 1.018 ms | 0 - 8 MB | NPU
105
- | MobileNet-v3-Small | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 1.618 ms | 0 - 48 MB | NPU
106
- | MobileNet-v3-Small | TFLITE | float | Qualcomm® SA7255P | 2.201 ms | 0 - 31 MB | NPU
107
- | MobileNet-v3-Small | TFLITE | float | Qualcomm® SA8295P | 1.504 ms | 0 - 30 MB | NPU
108
- | MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.436 ms | 0 - 35 MB | NPU
109
- | MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.344 ms | 0 - 35 MB | NPU
110
 
111
  ## License
112
  * 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/main/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 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.48.0/mobilenet_v3_small-onnx-float.zip)
34
+ | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.48.0/mobilenet_v3_small-onnx-w8a16.zip)
35
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.48.0/mobilenet_v3_small-qnn_dlc-float.zip)
36
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.48.0/mobilenet_v3_small-qnn_dlc-w8a16.zip)
37
+ | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mobilenet_v3_small/releases/v0.48.0/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/main/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/main/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® X2 Elite | 0.247 ms | 5 - 5 MB | NPU
67
+ | MobileNet-v3-Small | ONNX | float | Snapdragon® X Elite | 0.667 ms | 5 - 5 MB | NPU
68
+ | MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.354 ms | 0 - 45 MB | NPU
69
+ | MobileNet-v3-Small | ONNX | float | Qualcomm® QCS8550 (Proxy) | 0.548 ms | 0 - 2 MB | NPU
70
+ | MobileNet-v3-Small | ONNX | float | Qualcomm® QCS9075 | 0.759 ms | 1 - 3 MB | NPU
71
+ | MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.283 ms | 0 - 33 MB | NPU
72
  | MobileNet-v3-Small | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.244 ms | 0 - 33 MB | NPU
73
+ | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® X2 Elite | 0.449 ms | 1 - 1 MB | NPU
74
+ | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® X Elite | 0.996 ms | 1 - 1 MB | NPU
75
+ | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 0.553 ms | 0 - 45 MB | NPU
76
+ | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 2.097 ms | 1 - 30 MB | NPU
77
+ | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 0.853 ms | 1 - 2 MB | NPU
78
+ | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA8775P | 1.141 ms | 1 - 32 MB | NPU
79
+ | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® QCS9075 | 0.992 ms | 1 - 3 MB | NPU
80
+ | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 1.583 ms | 0 - 47 MB | NPU
81
+ | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA7255P | 2.097 ms | 1 - 30 MB | NPU
82
+ | MobileNet-v3-Small | QNN_DLC | float | Qualcomm® SA8295P | 1.48 ms | 0 - 29 MB | NPU
83
  | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.427 ms | 0 - 30 MB | NPU
84
+ | MobileNet-v3-Small | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.33 ms | 1 - 34 MB | NPU
85
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.427 ms | 0 - 0 MB | NPU
86
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® X Elite | 0.97 ms | 0 - 0 MB | NPU
87
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.563 ms | 0 - 37 MB | NPU
88
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCS6490 | 2.289 ms | 2 - 4 MB | NPU
89
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 1.72 ms | 0 - 26 MB | NPU
90
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 0.805 ms | 0 - 2 MB | NPU
91
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® SA8775P | 1.008 ms | 0 - 27 MB | NPU
92
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 0.963 ms | 0 - 2 MB | NPU
93
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 2.792 ms | 0 - 140 MB | NPU
94
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® QCS8450 (Proxy) | 0.981 ms | 0 - 39 MB | NPU
95
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® SA7255P | 1.72 ms | 0 - 26 MB | NPU
96
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Qualcomm® SA8295P | 1.378 ms | 0 - 23 MB | NPU
97
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 0.377 ms | 0 - 24 MB | NPU
98
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 0.789 ms | 0 - 25 MB | NPU
99
+ | MobileNet-v3-Small | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.31 ms | 0 - 28 MB | NPU
100
+ | MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.559 ms | 0 - 45 MB | NPU
101
+ | MobileNet-v3-Small | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 2.18 ms | 0 - 31 MB | NPU
102
+ | MobileNet-v3-Small | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 0.857 ms | 0 - 2 MB | NPU
103
+ | MobileNet-v3-Small | TFLITE | float | Qualcomm® SA8775P | 1.179 ms | 0 - 33 MB | NPU
104
+ | MobileNet-v3-Small | TFLITE | float | Qualcomm® QCS9075 | 1.021 ms | 0 - 8 MB | NPU
105
+ | MobileNet-v3-Small | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 1.609 ms | 0 - 49 MB | NPU
106
+ | MobileNet-v3-Small | TFLITE | float | Qualcomm® SA7255P | 2.18 ms | 0 - 31 MB | NPU
107
+ | MobileNet-v3-Small | TFLITE | float | Qualcomm® SA8295P | 1.516 ms | 0 - 30 MB | NPU
108
+ | MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.436 ms | 0 - 36 MB | NPU
109
+ | MobileNet-v3-Small | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.344 ms | 0 - 36 MB | NPU
 
110
 
111
  ## License
112
  * The license for the original implementation of MobileNet-v3-Small can be found