Hugging Face's logo

qualcomm
/
Inception-v3

Image Classification
PyTorch
backbone
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
0cce9b6
·
verified ·
1 Parent(s): c75b0d2

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 +13 -13
README.md CHANGED
@@ -15,7 +15,7 @@ pipeline_tag: image-classification
15
  InceptionNetV3 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.
16
 
17
  This is based on the implementation of Inception-v3 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/inception.py).
18
- 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/inception_v3) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  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.
21
 
@@ -28,26 +28,26 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | 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/inception_v3/releases/v0.47.0/inception_v3-onnx-float.zip)
32
- | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/inception_v3/releases/v0.47.0/inception_v3-onnx-w8a8.zip)
33
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/inception_v3/releases/v0.47.0/inception_v3-qnn_dlc-float.zip)
34
- | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/inception_v3/releases/v0.47.0/inception_v3-qnn_dlc-w8a8.zip)
35
- | 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/inception_v3/releases/v0.47.0/inception_v3-tflite-float.zip)
36
- | TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/inception_v3/releases/v0.47.0/inception_v3-tflite-w8a8.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[Inception-v3 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/inception_v3)**.
39
 
40
 
41
  ### Option 2: Export with Custom Configurations
42
 
43
- Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/inception_v3) 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 [Inception-v3 on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/inception_v3) for usage instructions.
51
 
52
  ## Model Details
53
 
@@ -63,13 +63,14 @@ See our repository for [Inception-v3 on GitHub](https://github.com/quic/ai-hub-m
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
 
66
  | Inception-v3 | ONNX | float | Snapdragon® X Elite | 1.518 ms | 46 - 46 MB | NPU
67
  | Inception-v3 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.051 ms | 0 - 60 MB | NPU
68
  | Inception-v3 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.483 ms | 0 - 49 MB | NPU
69
  | Inception-v3 | ONNX | float | Qualcomm® QCS9075 | 2.177 ms | 0 - 4 MB | NPU
70
  | Inception-v3 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.925 ms | 0 - 34 MB | NPU
71
  | Inception-v3 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.805 ms | 0 - 39 MB | NPU
72
- | Inception-v3 | ONNX | float | Snapdragon® X2 Elite | 0.691 ms | 46 - 46 MB | NPU
73
  | Inception-v3 | ONNX | w8a8 | Snapdragon® X Elite | 0.729 ms | 23 - 23 MB | NPU
74
  | Inception-v3 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.506 ms | 0 - 95 MB | NPU
75
  | Inception-v3 | ONNX | w8a8 | Qualcomm® QCS6490 | 25.099 ms | 10 - 39 MB | CPU
@@ -79,7 +80,7 @@ See our repository for [Inception-v3 on GitHub](https://github.com/quic/ai-hub-m
79
  | Inception-v3 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.431 ms | 0 - 58 MB | NPU
80
  | Inception-v3 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 14.066 ms | 10 - 21 MB | CPU
81
  | Inception-v3 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.412 ms | 0 - 57 MB | NPU
82
- | Inception-v3 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.291 ms | 23 - 23 MB | NPU
83
  | Inception-v3 | QNN_DLC | float | Snapdragon® X Elite | 1.417 ms | 1 - 1 MB | NPU
84
  | Inception-v3 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.02 ms | 0 - 57 MB | NPU
85
  | Inception-v3 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 7.828 ms | 1 - 33 MB | NPU
@@ -91,7 +92,7 @@ See our repository for [Inception-v3 on GitHub](https://github.com/quic/ai-hub-m
91
  | Inception-v3 | QNN_DLC | float | Qualcomm® SA8295P | 2.688 ms | 1 - 31 MB | NPU
92
  | Inception-v3 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.879 ms | 1 - 35 MB | NPU
93
  | Inception-v3 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.758 ms | 1 - 37 MB | NPU
94
- | Inception-v3 | QNN_DLC | float | Snapdragon® X2 Elite | 0.78 ms | 1 - 1 MB | NPU
95
  | Inception-v3 | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.661 ms | 0 - 0 MB | NPU
96
  | Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.458 ms | 0 - 73 MB | NPU
97
  | Inception-v3 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 2.289 ms | 2 - 4 MB | NPU
@@ -106,7 +107,6 @@ See our repository for [Inception-v3 on GitHub](https://github.com/quic/ai-hub-m
106
  | Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.425 ms | 0 - 51 MB | NPU
107
  | Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.978 ms | 0 - 49 MB | NPU
108
  | Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.37 ms | 0 - 51 MB | NPU
109
- | Inception-v3 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.343 ms | 0 - 0 MB | NPU
110
  | Inception-v3 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.018 ms | 0 - 127 MB | NPU
111
  | Inception-v3 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 7.849 ms | 0 - 73 MB | NPU
112
  | Inception-v3 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.367 ms | 0 - 132 MB | NPU
 
15
  InceptionNetV3 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.
16
 
17
  This is based on the implementation of Inception-v3 found [here](https://github.com/pytorch/vision/blob/main/torchvision/models/inception.py).
18
+ 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/inception_v3) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
19
 
20
  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.
21
 
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | 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/inception_v3/releases/v0.48.0/inception_v3-onnx-float.zip)
32
+ | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/inception_v3/releases/v0.48.0/inception_v3-onnx-w8a8.zip)
33
+ | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/inception_v3/releases/v0.48.0/inception_v3-qnn_dlc-float.zip)
34
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/inception_v3/releases/v0.48.0/inception_v3-qnn_dlc-w8a8.zip)
35
+ | 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/inception_v3/releases/v0.48.0/inception_v3-tflite-float.zip)
36
+ | TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/inception_v3/releases/v0.48.0/inception_v3-tflite-w8a8.zip)
37
 
38
  For more device-specific assets and performance metrics, visit **[Inception-v3 on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/inception_v3)**.
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/main/qai_hub_models/models/inception_v3) 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 [Inception-v3 on GitHub](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/inception_v3) for usage instructions.
51
 
52
  ## Model Details
53
 
 
63
  ## Performance Summary
64
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
65
  |---|---|---|---|---|---|---
66
+ | Inception-v3 | ONNX | float | Snapdragon® X2 Elite | 0.691 ms | 46 - 46 MB | NPU
67
  | Inception-v3 | ONNX | float | Snapdragon® X Elite | 1.518 ms | 46 - 46 MB | NPU
68
  | Inception-v3 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 1.051 ms | 0 - 60 MB | NPU
69
  | Inception-v3 | ONNX | float | Qualcomm® QCS8550 (Proxy) | 1.483 ms | 0 - 49 MB | NPU
70
  | Inception-v3 | ONNX | float | Qualcomm® QCS9075 | 2.177 ms | 0 - 4 MB | NPU
71
  | Inception-v3 | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.925 ms | 0 - 34 MB | NPU
72
  | Inception-v3 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.805 ms | 0 - 39 MB | NPU
73
+ | Inception-v3 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.291 ms | 23 - 23 MB | NPU
74
  | Inception-v3 | ONNX | w8a8 | Snapdragon® X Elite | 0.729 ms | 23 - 23 MB | NPU
75
  | Inception-v3 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.506 ms | 0 - 95 MB | NPU
76
  | Inception-v3 | ONNX | w8a8 | Qualcomm® QCS6490 | 25.099 ms | 10 - 39 MB | CPU
 
80
  | Inception-v3 | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.431 ms | 0 - 58 MB | NPU
81
  | Inception-v3 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 14.066 ms | 10 - 21 MB | CPU
82
  | Inception-v3 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.412 ms | 0 - 57 MB | NPU
83
+ | Inception-v3 | QNN_DLC | float | Snapdragon® X2 Elite | 0.78 ms | 1 - 1 MB | NPU
84
  | Inception-v3 | QNN_DLC | float | Snapdragon® X Elite | 1.417 ms | 1 - 1 MB | NPU
85
  | Inception-v3 | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.02 ms | 0 - 57 MB | NPU
86
  | Inception-v3 | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 7.828 ms | 1 - 33 MB | NPU
 
92
  | Inception-v3 | QNN_DLC | float | Qualcomm® SA8295P | 2.688 ms | 1 - 31 MB | NPU
93
  | Inception-v3 | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 0.879 ms | 1 - 35 MB | NPU
94
  | Inception-v3 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.758 ms | 1 - 37 MB | NPU
95
+ | Inception-v3 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.343 ms | 0 - 0 MB | NPU
96
  | Inception-v3 | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.661 ms | 0 - 0 MB | NPU
97
  | Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.458 ms | 0 - 73 MB | NPU
98
  | Inception-v3 | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 2.289 ms | 2 - 4 MB | NPU
 
107
  | Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 0.425 ms | 0 - 51 MB | NPU
108
  | Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.978 ms | 0 - 49 MB | NPU
109
  | Inception-v3 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.37 ms | 0 - 51 MB | NPU
 
110
  | Inception-v3 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 1.018 ms | 0 - 127 MB | NPU
111
  | Inception-v3 | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 7.849 ms | 0 - 73 MB | NPU
112
  | Inception-v3 | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 1.367 ms | 0 - 132 MB | NPU