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 2.45, ONNX Runtime 1.27.1 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a8 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download
TFLITE w8a8 Universal QAIRT 2.45 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® X2 Elite 1.135 ms 1 - 1 MB NPU
Inception-v3 ONNX float Snapdragon® X Elite 2.141 ms 46 - 46 MB NPU
Inception-v3 ONNX float Snapdragon® 8 Gen 3 Mobile 1.592 ms 0 - 64 MB NPU
Inception-v3 ONNX float Snapdragon® 8 Gen 1 Mobile 3.96 ms 0 - 65 MB NPU
Inception-v3 ONNX float Qualcomm® Dragonwing™ IQ-8275 4.253 ms 1 - 5 MB NPU
Inception-v3 ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.185 ms 0 - 167 MB NPU
Inception-v3 ONNX float Qualcomm® QCS8450 3.96 ms 0 - 65 MB NPU
Inception-v3 ONNX float Qualcomm® Dragonwing™ IQ-9075 3.661 ms 1 - 5 MB NPU
Inception-v3 ONNX float Qualcomm® Dragonwing™ IQ-X7181 2.141 ms 46 - 46 MB NPU
Inception-v3 ONNX float Qualcomm® Dragonwing™ Q-8750 1.34 ms 0 - 42 MB NPU
Inception-v3 ONNX float Snapdragon® 8 Elite Mobile 1.34 ms 0 - 42 MB NPU
Inception-v3 ONNX float Snapdragon® 8 Elite Gen 5 Mobile 1.086 ms 0 - 41 MB NPU
Inception-v3 ONNX w8a8 Snapdragon® X2 Elite 0.374 ms 1 - 1 MB NPU
Inception-v3 ONNX w8a8 Snapdragon® X Elite 0.797 ms 24 - 24 MB NPU
Inception-v3 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.628 ms 0 - 102 MB NPU
Inception-v3 ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 1.235 ms 0 - 101 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 4.005 ms 0 - 3 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 0.995 ms 0 - 4 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.847 ms 0 - 26 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® QCS8450 1.235 ms 0 - 101 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 0.964 ms 0 - 3 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.797 ms 24 - 24 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 10.75 ms 0 - 181 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 1.358 ms 0 - 63 MB NPU
Inception-v3 ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.541 ms 0 - 64 MB NPU
Inception-v3 ONNX w8a8 Snapdragon® 8 Elite Mobile 0.541 ms 0 - 64 MB NPU
Inception-v3 ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.432 ms 0 - 62 MB NPU
Inception-v3 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.358 ms 0 - 63 MB NPU
Inception-v3 QNN_DLC float Snapdragon® X2 Elite 1.195 ms 1 - 1 MB NPU
Inception-v3 QNN_DLC float Snapdragon® X Elite 2.085 ms 1 - 1 MB NPU
Inception-v3 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.512 ms 0 - 60 MB NPU
Inception-v3 QNN_DLC float Snapdragon® 8 Gen 1 Mobile 3.73 ms 0 - 61 MB NPU
Inception-v3 QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 3.993 ms 1 - 4 MB NPU
Inception-v3 QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 13.451 ms 1 - 35 MB NPU
Inception-v3 QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.977 ms 1 - 3 MB NPU
Inception-v3 QNN_DLC float Qualcomm® SA8775P 3.611 ms 0 - 39 MB NPU
Inception-v3 QNN_DLC float Qualcomm® SA8650P 3.611 ms 0 - 39 MB NPU
Inception-v3 QNN_DLC float Qualcomm® SA8255P 3.611 ms 0 - 39 MB NPU
Inception-v3 QNN_DLC float Qualcomm® QCS8450 3.73 ms 0 - 61 MB NPU
Inception-v3 QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 3.42 ms 3 - 6 MB NPU
Inception-v3 QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 2.085 ms 1 - 1 MB NPU
Inception-v3 QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.285 ms 0 - 36 MB NPU
Inception-v3 QNN_DLC float Qualcomm® SA7255P 13.451 ms 1 - 35 MB NPU
Inception-v3 QNN_DLC float Qualcomm® SA8295P 4.192 ms 1 - 34 MB NPU
Inception-v3 QNN_DLC float Snapdragon® 8 Elite Mobile 1.285 ms 0 - 36 MB NPU
Inception-v3 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.015 ms 1 - 40 MB NPU
Inception-v3 QNN_DLC w8a8 Snapdragon® X2 Elite 0.465 ms 0 - 0 MB NPU
Inception-v3 QNN_DLC w8a8 Snapdragon® X Elite 0.882 ms 0 - 0 MB NPU
Inception-v3 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.604 ms 59 - 139 MB NPU
Inception-v3 QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 1.19 ms 0 - 83 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 3.997 ms 2 - 4 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.938 ms 0 - 3 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 2.394 ms 0 - 53 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.814 ms 0 - 9 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® SA8775P 0.997 ms 0 - 55 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® SA8650P 0.997 ms 0 - 55 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® SA8255P 0.997 ms 0 - 55 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® QCS8450 1.19 ms 0 - 83 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 0.87 ms 0 - 2 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.882 ms 0 - 0 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 10.481 ms 0 - 169 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 1.304 ms 0 - 55 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.515 ms 0 - 53 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® SA7255P 2.394 ms 0 - 53 MB NPU
Inception-v3 QNN_DLC w8a8 Qualcomm® SA8295P 1.615 ms 0 - 51 MB NPU
Inception-v3 QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.515 ms 0 - 53 MB NPU
Inception-v3 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.412 ms 0 - 52 MB NPU
Inception-v3 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.304 ms 0 - 55 MB NPU
Inception-v3 TFLITE float Snapdragon® 8 Gen 3 Mobile 1.485 ms 0 - 118 MB NPU
Inception-v3 TFLITE float Snapdragon® 8 Gen 1 Mobile 3.728 ms 0 - 121 MB NPU
Inception-v3 TFLITE float Qualcomm® Dragonwing™ IQ-8275 3.976 ms 0 - 50 MB NPU
Inception-v3 TFLITE float Qualcomm® Dragonwing™ IQ-8275 13.496 ms 0 - 66 MB NPU
Inception-v3 TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.031 ms 0 - 3 MB NPU
Inception-v3 TFLITE float Qualcomm® SA8775P 3.601 ms 0 - 69 MB NPU
Inception-v3 TFLITE float Qualcomm® SA8650P 3.601 ms 0 - 69 MB NPU
Inception-v3 TFLITE float Qualcomm® SA8255P 3.601 ms 0 - 69 MB NPU
Inception-v3 TFLITE float Qualcomm® QCS8450 3.728 ms 0 - 121 MB NPU
Inception-v3 TFLITE float Qualcomm® Dragonwing™ IQ-9075 3.433 ms 0 - 49 MB NPU
Inception-v3 TFLITE float Qualcomm® Dragonwing™ Q-8750 1.281 ms 0 - 69 MB NPU
Inception-v3 TFLITE float Qualcomm® SA7255P 13.496 ms 0 - 66 MB NPU
Inception-v3 TFLITE float Qualcomm® SA8295P 4.183 ms 0 - 70 MB NPU
Inception-v3 TFLITE float Snapdragon® 8 Elite Mobile 1.281 ms 0 - 69 MB NPU
Inception-v3 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 1.011 ms 0 - 69 MB NPU
Inception-v3 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.64 ms 0 - 80 MB NPU
Inception-v3 TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 1.275 ms 0 - 85 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 4.161 ms 0 - 25 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.99 ms 0 - 26 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 2.493 ms 0 - 51 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.907 ms 0 - 5 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® SA8775P 1.166 ms 0 - 55 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® SA8650P 1.166 ms 0 - 55 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® SA8255P 1.166 ms 0 - 55 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® QCS8450 1.275 ms 0 - 85 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 1.043 ms 0 - 25 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 10.698 ms 0 - 170 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 1.403 ms 0 - 53 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.547 ms 0 - 51 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® SA7255P 2.493 ms 0 - 51 MB NPU
Inception-v3 TFLITE w8a8 Qualcomm® SA8295P 1.813 ms 0 - 49 MB NPU
Inception-v3 TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.547 ms 0 - 51 MB NPU
Inception-v3 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.455 ms 0 - 55 MB NPU
Inception-v3 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 1.403 ms 0 - 53 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