Hugging Face's logo

qualcomm
/
Inception-v3

Image Classification
PyTorch
backbone
android
Model card Files
xet
 Community

Inception-v3: Optimized for Qualcomm Devices

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.

This is based on the implementation of Inception-v3 found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Getting Started

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime Precision Chipset SDK Versions Download
ONNX float Universal QAIRT 2.50, ONNX Runtime 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.50, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.50 Download
QNN_DLC w8a8 Universal QAIRT 2.50 Download
TFLITE float Universal QAIRT 2.50 Download
TFLITE w8a8 Universal QAIRT 2.50 Download

For more device-specific assets and performance metrics, visit Inception-v3 on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

  • Custom weights (e.g., fine-tuned checkpoints)
  • Custom input shapes
  • Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for Inception-v3 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

  • Input resolution: 224x224
  • Model checkpoint: Imagenet
  • Model size (float): 90.9 MB
  • Model size (w8a8): 23.3 MB
  • Number of parameters: 23.9M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Inception-v3 ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.083 ms 0 - 43 MB NPU
Inception-v3 ONNX float Snapdragon® 8 Elite For Galaxy Mobile 1.296 ms 0 - 47 MB NPU
Inception-v3 ONNX float Snapdragon® X2 Elite 1.121 ms 1 - 1 MB NPU
Inception-v3 ONNX float Snapdragon® X Elite 2.165 ms 46 - 46 MB NPU
Inception-v3 ONNX float Snapdragon® 8 Gen 3 Mobile 1.552 ms 0 - 67 MB NPU
Inception-v3 ONNX float Snapdragon® 8 Gen 1 Mobile 3.665 ms 1 - 68 MB NPU
Inception-v3 ONNX float Qualcomm® Dragonwing™ IQ-8275 4.189 ms 1 - 6 MB NPU
Inception-v3 ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.192 ms 0 - 64 MB NPU
Inception-v3 ONNX float Qualcomm® QCS8450 3.665 ms 1 - 68 MB NPU
Inception-v3 ONNX float Qualcomm® Dragonwing™ IQ-9075 3.674 ms 1 - 5 MB NPU
Inception-v3 ONNX float Qualcomm® Dragonwing™ IQ-X7181 2.165 ms 46 - 46 MB NPU
Inception-v3 ONNX float Qualcomm® Dragonwing™ Q-8750 1.296 ms 0 - 47 MB NPU
Inception-v3 ONNX w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.409 ms 0 - 70 MB NPU
Inception-v3 ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.524 ms 0 - 64 MB NPU
Inception-v3 ONNX w8a8 Snapdragon® X2 Elite 0.356 ms 1 - 1 MB NPU
Inception-v3 ONNX w8a8 Snapdragon® X Elite 0.783 ms 24 - 24 MB NPU
Inception-v3 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.606 ms 0 - 107 MB NPU
Inception-v3 ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.986 ms 0 - 107 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 3.045 ms 0 - 3 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 0.964 ms 0 - 4 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.828 ms 0 - 26 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® QCS8450 0.986 ms 0 - 107 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 0.907 ms 0 - 3 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.783 ms 24 - 24 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 10.656 ms 0 - 179 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 1.335 ms 0 - 68 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.524 ms 0 - 64 MB NPU
Inception-v3 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.335 ms 0 - 68 MB NPU
Inception-v3 QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.003 ms 1 - 38 MB NPU
Inception-v3 QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.231 ms 1 - 42 MB NPU
Inception-v3 QNN_DLC float Snapdragon® X2 Elite 1.202 ms 1 - 1 MB NPU
Inception-v3 QNN_DLC float Snapdragon® X Elite 2.053 ms 1 - 1 MB NPU
Inception-v3 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.451 ms 0 - 57 MB NPU
Inception-v3 QNN_DLC float Snapdragon® 8 Gen 1 Mobile 3.416 ms 0 - 63 MB NPU
Inception-v3 QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 4.016 ms 1 - 5 MB NPU
Inception-v3 QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.959 ms 1 - 107 MB NPU
Inception-v3 QNN_DLC float Qualcomm® QCS8450 3.416 ms 0 - 63 MB NPU
Inception-v3 QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 3.418 ms 1 - 4 MB NPU
Inception-v3 QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 2.053 ms 1 - 1 MB NPU
Inception-v3 QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.231 ms 1 - 42 MB NPU
Inception-v3 QNN_DLC float Qualcomm® SA7255P 13.512 ms 1 - 38 MB NPU
Inception-v3 QNN_DLC float Qualcomm® SA8295P 4.058 ms 1 - 36 MB NPU
Inception-v3 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.418 ms 0 - 62 MB NPU
Inception-v3 QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.517 ms 0 - 56 MB NPU
Inception-v3 QNN_DLC w8a8 Snapdragon® X2 Elite 0.469 ms 0 - 0 MB NPU
Inception-v3 QNN_DLC w8a8 Snapdragon® X Elite 0.862 ms 0 - 0 MB NPU
Inception-v3 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.599 ms 0 - 84 MB NPU
Inception-v3 QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.954 ms 0 - 89 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 3.082 ms 2 - 5 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.928 ms 0 - 3 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.794 ms 0 - 2 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® SA8775P 0.975 ms 0 - 62 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® SA8650P 0.975 ms 0 - 62 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® SA8255P 0.975 ms 0 - 62 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® QCS8450 0.954 ms 0 - 89 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 0.864 ms 0 - 3 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.862 ms 0 - 0 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 10.545 ms 0 - 166 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 1.3 ms 0 - 59 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.517 ms 0 - 56 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® SA7255P 2.389 ms 0 - 57 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® SA8295P 1.475 ms 0 - 56 MB NPU
Inception-v3 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.3 ms 0 - 59 MB NPU
Inception-v3 TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.004 ms 0 - 69 MB NPU
Inception-v3 TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.233 ms 0 - 70 MB NPU
Inception-v3 TFLITE float Snapdragon® 8 Gen 3 Mobile 1.503 ms 0 - 122 MB NPU
Inception-v3 TFLITE float Snapdragon® 8 Gen 1 Mobile 3.408 ms 0 - 124 MB NPU
Inception-v3 TFLITE float Qualcomm® Dragonwing™ IQ-8275 4.022 ms 0 - 50 MB NPU
Inception-v3 TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.026 ms 0 - 3 MB NPU
Inception-v3 TFLITE float Qualcomm® SA8775P 3.583 ms 0 - 71 MB NPU
Inception-v3 TFLITE float Qualcomm® SA8650P 3.583 ms 0 - 71 MB NPU
Inception-v3 TFLITE float Qualcomm® SA8255P 3.583 ms 0 - 71 MB NPU
Inception-v3 TFLITE float Qualcomm® QCS8450 3.408 ms 0 - 124 MB NPU
Inception-v3 TFLITE float Qualcomm® Dragonwing™ IQ-9075 3.425 ms 0 - 49 MB NPU
Inception-v3 TFLITE float Qualcomm® Dragonwing™ Q-8750 1.233 ms 0 - 70 MB NPU
Inception-v3 TFLITE float Qualcomm® SA7255P 13.49 ms 0 - 69 MB NPU
Inception-v3 TFLITE float Qualcomm® SA8295P 4.051 ms 0 - 67 MB NPU
Inception-v3 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.446 ms 0 - 60 MB NPU
Inception-v3 TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.537 ms 0 - 54 MB NPU
Inception-v3 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.619 ms 0 - 84 MB NPU
Inception-v3 TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 1.078 ms 0 - 92 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 3.742 ms 0 - 26 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.978 ms 0 - 26 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.919 ms 0 - 18 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® QCS8450 1.078 ms 0 - 92 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 1.031 ms 0 - 26 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 10.557 ms 0 - 171 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 1.417 ms 0 - 58 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.537 ms 0 - 54 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® SA7255P 2.524 ms 0 - 55 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® SA8295P 1.623 ms 0 - 54 MB NPU
Inception-v3 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.417 ms 0 - 58 MB NPU

License

  • The license for the original implementation of Inception-v3 can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Image Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/Inception-v3