Inception-v4: Optimized for Qualcomm Devices

InceptionNetV4 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-v4 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 1.30.0 Download
ONNX w8a8 Universal QAIRT 2.50, ONNX Runtime 1.30.0 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-v4 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-v4 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

  • Input resolution: 299x299
  • Model checkpoint: Imagenet
  • Model size (float): 163 MB
  • Model size (w8a8): 41.6 MB
  • Number of parameters: 42.6M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Inception-v4 ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.925 ms 0 - 57 MB NPU
Inception-v4 ONNX float Snapdragon® 8 Elite For Galaxy Mobile 2.352 ms 0 - 55 MB NPU
Inception-v4 ONNX float Snapdragon® X2 Elite 2.105 ms 1 - 1 MB NPU
Inception-v4 ONNX float Snapdragon® X Elite 3.983 ms 82 - 82 MB NPU
Inception-v4 ONNX float Snapdragon® 8 Gen 3 Mobile 2.963 ms 0 - 103 MB NPU
Inception-v4 ONNX float Snapdragon® 8 Gen 1 Mobile 6.778 ms 1 - 109 MB NPU
Inception-v4 ONNX float Qualcomm® Dragonwing™ IQ-8275 8.118 ms 1 - 6 MB NPU
Inception-v4 ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.994 ms 0 - 97 MB NPU
Inception-v4 ONNX float Qualcomm® QCS8450 6.778 ms 1 - 109 MB NPU
Inception-v4 ONNX float Qualcomm® Dragonwing™ IQ-9075 7.017 ms 1 - 5 MB NPU
Inception-v4 ONNX float Qualcomm® Dragonwing™ IQ-X7181 3.983 ms 82 - 82 MB NPU
Inception-v4 ONNX float Qualcomm® Dragonwing™ Q-8750 2.352 ms 0 - 55 MB NPU
Inception-v4 ONNX w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.7 ms 0 - 98 MB NPU
Inception-v4 ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.846 ms 0 - 95 MB NPU
Inception-v4 ONNX w8a8 Snapdragon® X2 Elite 0.672 ms 1 - 1 MB NPU
Inception-v4 ONNX w8a8 Snapdragon® X Elite 1.296 ms 42 - 42 MB NPU
Inception-v4 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.946 ms 0 - 139 MB NPU
Inception-v4 ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 1.718 ms 0 - 142 MB NPU
Inception-v4 ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 6.073 ms 0 - 4 MB NPU
Inception-v4 ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 1.518 ms 0 - 5 MB NPU
Inception-v4 ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.348 ms 0 - 50 MB NPU
Inception-v4 ONNX w8a8 Qualcomm® QCS8450 1.718 ms 0 - 142 MB NPU
Inception-v4 ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 1.461 ms 0 - 4 MB NPU
Inception-v4 ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.296 ms 42 - 42 MB NPU
Inception-v4 ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 21.949 ms 0 - 211 MB NPU
Inception-v4 ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 2.321 ms 0 - 101 MB NPU
Inception-v4 ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.846 ms 0 - 95 MB NPU
Inception-v4 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 2.321 ms 0 - 101 MB NPU
Inception-v4 QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.837 ms 1 - 50 MB NPU
Inception-v4 QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 2.276 ms 1 - 48 MB NPU
Inception-v4 QNN_DLC float Snapdragon® X2 Elite 2.251 ms 1 - 1 MB NPU
Inception-v4 QNN_DLC float Snapdragon® X Elite 3.961 ms 1 - 1 MB NPU
Inception-v4 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.822 ms 0 - 99 MB NPU
Inception-v4 QNN_DLC float Snapdragon® 8 Gen 1 Mobile 6.589 ms 1 - 102 MB NPU
Inception-v4 QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 7.851 ms 1 - 5 MB NPU
Inception-v4 QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.797 ms 1 - 178 MB NPU
Inception-v4 QNN_DLC float Qualcomm® SA8775P 7.046 ms 1 - 49 MB NPU
Inception-v4 QNN_DLC float Qualcomm® SA8650P 7.046 ms 1 - 49 MB NPU
Inception-v4 QNN_DLC float Qualcomm® SA8255P 7.046 ms 1 - 49 MB NPU
Inception-v4 QNN_DLC float Qualcomm® QCS8450 6.589 ms 1 - 102 MB NPU
Inception-v4 QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 6.794 ms 1 - 4 MB NPU
Inception-v4 QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 3.961 ms 1 - 1 MB NPU
Inception-v4 QNN_DLC float Qualcomm® Dragonwing™ Q-8750 2.276 ms 1 - 48 MB NPU
Inception-v4 QNN_DLC float Qualcomm® SA7255P 27.206 ms 1 - 47 MB NPU
Inception-v4 QNN_DLC float Qualcomm® SA8295P 7.587 ms 0 - 49 MB NPU
Inception-v4 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.687 ms 0 - 84 MB NPU
Inception-v4 QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.843 ms 0 - 84 MB NPU
Inception-v4 QNN_DLC w8a8 Snapdragon® X2 Elite 0.862 ms 0 - 0 MB NPU
Inception-v4 QNN_DLC w8a8 Snapdragon® X Elite 1.432 ms 0 - 0 MB NPU
Inception-v4 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.945 ms 0 - 117 MB NPU
Inception-v4 QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 1.706 ms 0 - 122 MB NPU
Inception-v4 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 6.023 ms 2 - 5 MB NPU
Inception-v4 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 1.482 ms 0 - 3 MB NPU
Inception-v4 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.312 ms 0 - 2 MB NPU
Inception-v4 QNN_DLC w8a8 Qualcomm® SA8775P 1.565 ms 0 - 86 MB NPU
Inception-v4 QNN_DLC w8a8 Qualcomm® SA8650P 1.565 ms 0 - 86 MB NPU
Inception-v4 QNN_DLC w8a8 Qualcomm® SA8255P 1.565 ms 0 - 86 MB NPU
Inception-v4 QNN_DLC w8a8 Qualcomm® QCS8450 1.706 ms 0 - 122 MB NPU
Inception-v4 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 1.408 ms 0 - 3 MB NPU
Inception-v4 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.432 ms 0 - 0 MB NPU
Inception-v4 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 24.594 ms 0 - 200 MB NPU
Inception-v4 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 2.289 ms 0 - 89 MB NPU
Inception-v4 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.843 ms 0 - 84 MB NPU
Inception-v4 QNN_DLC w8a8 Qualcomm® SA7255P 4.407 ms 0 - 83 MB NPU
Inception-v4 QNN_DLC w8a8 Qualcomm® SA8295P 2.472 ms 0 - 81 MB NPU
Inception-v4 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 2.289 ms 0 - 89 MB NPU
Inception-v4 TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 1.836 ms 0 - 111 MB NPU
Inception-v4 TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 2.281 ms 0 - 112 MB NPU
Inception-v4 TFLITE float Snapdragon® 8 Gen 3 Mobile 2.837 ms 0 - 210 MB NPU
Inception-v4 TFLITE float Snapdragon® 8 Gen 1 Mobile 6.586 ms 0 - 211 MB NPU
Inception-v4 TFLITE float Qualcomm® Dragonwing™ IQ-8275 7.846 ms 0 - 86 MB NPU
Inception-v4 TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 3.809 ms 0 - 2 MB NPU
Inception-v4 TFLITE float Qualcomm® SA8775P 7.087 ms 0 - 111 MB NPU
Inception-v4 TFLITE float Qualcomm® SA8650P 7.087 ms 0 - 111 MB NPU
Inception-v4 TFLITE float Qualcomm® SA8255P 7.087 ms 0 - 111 MB NPU
Inception-v4 TFLITE float Qualcomm® QCS8450 6.586 ms 0 - 211 MB NPU
Inception-v4 TFLITE float Qualcomm® Dragonwing™ IQ-9075 6.812 ms 0 - 85 MB NPU
Inception-v4 TFLITE float Qualcomm® Dragonwing™ Q-8750 2.281 ms 0 - 112 MB NPU
Inception-v4 TFLITE float Qualcomm® SA7255P 27.23 ms 0 - 110 MB NPU
Inception-v4 TFLITE float Qualcomm® SA8295P 7.593 ms 0 - 106 MB NPU
Inception-v4 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.696 ms 0 - 81 MB NPU
Inception-v4 TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.842 ms 0 - 79 MB NPU
Inception-v4 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.948 ms 0 - 115 MB NPU
Inception-v4 TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 1.68 ms 0 - 123 MB NPU
Inception-v4 TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 5.807 ms 0 - 44 MB NPU
Inception-v4 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 1.489 ms 0 - 45 MB NPU
Inception-v4 TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.289 ms 0 - 3 MB NPU
Inception-v4 TFLITE w8a8 Qualcomm® SA8775P 1.577 ms 0 - 82 MB NPU
Inception-v4 TFLITE w8a8 Qualcomm® SA8650P 1.577 ms 0 - 82 MB NPU
Inception-v4 TFLITE w8a8 Qualcomm® SA8255P 1.577 ms 0 - 82 MB NPU
Inception-v4 TFLITE w8a8 Qualcomm® QCS8450 1.68 ms 0 - 123 MB NPU
Inception-v4 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 1.43 ms 0 - 44 MB NPU
Inception-v4 TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 25.183 ms 0 - 198 MB NPU
Inception-v4 TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 2.293 ms 0 - 86 MB NPU
Inception-v4 TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.842 ms 0 - 79 MB NPU
Inception-v4 TFLITE w8a8 Qualcomm® SA7255P 4.425 ms 0 - 80 MB NPU
Inception-v4 TFLITE w8a8 Qualcomm® SA8295P 2.447 ms 0 - 77 MB NPU
Inception-v4 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 2.293 ms 0 - 86 MB NPU

License

  • The license for the original implementation of Inception-v4 can be found here.

References

Community

Downloads last month

-

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

Paper for qualcomm/Inception-v4