Image Classification
PyTorch
android

GoogLeNet: Optimized for Qualcomm Devices

GoogLeNet 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 GoogLeNet 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 GoogLeNet 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 GoogLeNet 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): 25.3 MB
  • Model size (w8a8): 6.54 MB
  • Number of parameters: 6.62M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
GoogLeNet ONNX float Snapdragon® X2 Elite 0.407 ms 2 - 2 MB NPU
GoogLeNet ONNX float Snapdragon® X Elite 0.864 ms 13 - 13 MB NPU
GoogLeNet ONNX float Snapdragon® 8 Gen 3 Mobile 0.565 ms 0 - 48 MB NPU
GoogLeNet ONNX float Snapdragon® 8 Gen 1 Mobile 1.564 ms 1 - 51 MB NPU
GoogLeNet ONNX float Qualcomm® Dragonwing™ IQ-8275 1.534 ms 1 - 4 MB NPU
GoogLeNet ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.845 ms 0 - 16 MB NPU
GoogLeNet ONNX float Qualcomm® QCS8450 1.564 ms 1 - 51 MB NPU
GoogLeNet ONNX float Qualcomm® Dragonwing™ IQ-9075 1.686 ms 1 - 3 MB NPU
GoogLeNet ONNX float Qualcomm® Dragonwing™ IQ-X7181 0.864 ms 13 - 13 MB NPU
GoogLeNet ONNX float Qualcomm® Dragonwing™ Q-8750 0.466 ms 0 - 32 MB NPU
GoogLeNet ONNX float Snapdragon® 8 Elite Mobile 0.466 ms 0 - 32 MB NPU
GoogLeNet ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.396 ms 0 - 31 MB NPU
GoogLeNet ONNX w8a8 Snapdragon® X2 Elite 0.162 ms 1 - 1 MB NPU
GoogLeNet ONNX w8a8 Snapdragon® X Elite 0.293 ms 7 - 7 MB NPU
GoogLeNet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.228 ms 0 - 51 MB NPU
GoogLeNet ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.479 ms 0 - 55 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 1.298 ms 0 - 3 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 0.41 ms 0 - 4 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.309 ms 0 - 9 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® QCS8450 0.479 ms 0 - 55 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 0.427 ms 0 - 3 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.293 ms 7 - 7 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 2.308 ms 0 - 37 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 0.363 ms 0 - 36 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.196 ms 0 - 39 MB NPU
GoogLeNet ONNX w8a8 Snapdragon® 8 Elite Mobile 0.196 ms 0 - 39 MB NPU
GoogLeNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.185 ms 0 - 34 MB NPU
GoogLeNet ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 0.363 ms 0 - 36 MB NPU
GoogLeNet QNN_DLC float Snapdragon® X2 Elite 0.495 ms 1 - 1 MB NPU
GoogLeNet QNN_DLC float Snapdragon® X Elite 0.953 ms 1 - 1 MB NPU
GoogLeNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.558 ms 0 - 44 MB NPU
GoogLeNet QNN_DLC float Snapdragon® 8 Gen 1 Mobile 1.746 ms 0 - 49 MB NPU
GoogLeNet QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 1.472 ms 1 - 4 MB NPU
GoogLeNet QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 4.976 ms 1 - 27 MB NPU
GoogLeNet QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.811 ms 0 - 5 MB NPU
GoogLeNet QNN_DLC float Qualcomm® SA8775P 1.533 ms 1 - 29 MB NPU
GoogLeNet QNN_DLC float Qualcomm® SA8650P 1.533 ms 1 - 29 MB NPU
GoogLeNet QNN_DLC float Qualcomm® SA8255P 1.533 ms 1 - 29 MB NPU
GoogLeNet QNN_DLC float Qualcomm® QCS8450 1.746 ms 0 - 49 MB NPU
GoogLeNet QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.416 ms 3 - 5 MB NPU
GoogLeNet QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 0.953 ms 1 - 1 MB NPU
GoogLeNet QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.453 ms 0 - 26 MB NPU
GoogLeNet QNN_DLC float Qualcomm® SA7255P 4.976 ms 1 - 27 MB NPU
GoogLeNet QNN_DLC float Qualcomm® SA8295P 1.759 ms 1 - 25 MB NPU
GoogLeNet QNN_DLC float Snapdragon® 8 Elite Mobile 0.453 ms 0 - 26 MB NPU
GoogLeNet QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.382 ms 1 - 28 MB NPU
GoogLeNet QNN_DLC w8a8 Snapdragon® X2 Elite 0.217 ms 0 - 0 MB NPU
GoogLeNet QNN_DLC w8a8 Snapdragon® X Elite 0.334 ms 0 - 0 MB NPU
GoogLeNet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.187 ms 0 - 44 MB NPU
GoogLeNet QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.413 ms 0 - 50 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 1.193 ms 0 - 2 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.341 ms 0 - 3 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.813 ms 0 - 29 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.252 ms 0 - 64 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® SA8775P 0.414 ms 0 - 31 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® SA8650P 0.414 ms 0 - 31 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® SA8255P 0.414 ms 0 - 31 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® QCS8450 0.413 ms 0 - 50 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 0.311 ms 0 - 2 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.334 ms 0 - 0 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 2.317 ms 0 - 33 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 0.328 ms 0 - 30 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.158 ms 0 - 30 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® SA7255P 0.813 ms 0 - 29 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® SA8295P 0.619 ms 0 - 27 MB NPU
GoogLeNet QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.158 ms 0 - 30 MB NPU
GoogLeNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.143 ms 0 - 29 MB NPU
GoogLeNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.328 ms 0 - 30 MB NPU
GoogLeNet TFLITE float Snapdragon® 8 Gen 3 Mobile 0.562 ms 0 - 53 MB NPU
GoogLeNet TFLITE float Snapdragon® 8 Gen 1 Mobile 1.761 ms 0 - 60 MB NPU
GoogLeNet TFLITE float Qualcomm® Dragonwing™ IQ-8275 1.477 ms 0 - 17 MB NPU
GoogLeNet TFLITE float Qualcomm® Dragonwing™ IQ-8275 5.031 ms 0 - 33 MB NPU
GoogLeNet TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.815 ms 0 - 2 MB NPU
GoogLeNet TFLITE float Qualcomm® SA8775P 1.551 ms 0 - 35 MB NPU
GoogLeNet TFLITE float Qualcomm® SA8650P 1.551 ms 0 - 35 MB NPU
GoogLeNet TFLITE float Qualcomm® SA8255P 1.551 ms 0 - 35 MB NPU
GoogLeNet TFLITE float Qualcomm® QCS8450 1.761 ms 0 - 60 MB NPU
GoogLeNet TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.429 ms 0 - 16 MB NPU
GoogLeNet TFLITE float Qualcomm® Dragonwing™ Q-8750 0.46 ms 0 - 34 MB NPU
GoogLeNet TFLITE float Qualcomm® SA7255P 5.031 ms 0 - 33 MB NPU
GoogLeNet TFLITE float Qualcomm® SA8295P 1.809 ms 0 - 31 MB NPU
GoogLeNet TFLITE float Snapdragon® 8 Elite Mobile 0.46 ms 0 - 34 MB NPU
GoogLeNet TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.379 ms 0 - 35 MB NPU
GoogLeNet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.189 ms 0 - 43 MB NPU
GoogLeNet TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.42 ms 0 - 49 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 1.092 ms 0 - 8 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.355 ms 0 - 9 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.819 ms 0 - 28 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.24 ms 0 - 1 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® SA8775P 0.423 ms 0 - 30 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® SA8650P 0.423 ms 0 - 30 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® SA8255P 0.423 ms 0 - 30 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® QCS8450 0.42 ms 0 - 49 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 0.324 ms 0 - 9 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 2.253 ms 0 - 29 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 0.33 ms 0 - 29 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.161 ms 0 - 28 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® SA7255P 0.819 ms 0 - 28 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® SA8295P 0.616 ms 0 - 26 MB NPU
GoogLeNet TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.161 ms 0 - 28 MB NPU
GoogLeNet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.146 ms 0 - 28 MB NPU
GoogLeNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.33 ms 0 - 29 MB NPU

License

  • The license for the original implementation of GoogLeNet 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

Model tree for qualcomm/GoogLeNet

Finetunes
1 model

Paper for qualcomm/GoogLeNet