Hugging Face's logo

qualcomm
/
GoogLeNet

Image Classification
PyTorch
android
Model card Files
xet
 Community

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 2.50, 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 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® 8 Elite Gen 5 For Galaxy Mobile 0.39 ms 0 - 32 MB NPU
GoogLeNet ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.465 ms 0 - 31 MB NPU
GoogLeNet ONNX float Snapdragon® X2 Elite 0.406 ms 2 - 2 MB NPU
GoogLeNet ONNX float Snapdragon® X Elite 0.879 ms 13 - 13 MB NPU
GoogLeNet ONNX float Snapdragon® 8 Gen 3 Mobile 0.568 ms 0 - 50 MB NPU
GoogLeNet ONNX float Snapdragon® 8 Gen 1 Mobile 1.45 ms 1 - 57 MB NPU
GoogLeNet ONNX float Qualcomm® Dragonwing™ IQ-8275 1.542 ms 1 - 5 MB NPU
GoogLeNet ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.849 ms 0 - 15 MB NPU
GoogLeNet ONNX float Qualcomm® QCS8450 1.45 ms 1 - 57 MB NPU
GoogLeNet ONNX float Qualcomm® Dragonwing™ IQ-9075 1.493 ms 1 - 4 MB NPU
GoogLeNet ONNX float Qualcomm® Dragonwing™ IQ-X7181 0.879 ms 13 - 13 MB NPU
GoogLeNet ONNX float Qualcomm® Dragonwing™ Q-8750 0.465 ms 0 - 31 MB NPU
GoogLeNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.185 ms 0 - 39 MB NPU
GoogLeNet ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.197 ms 0 - 39 MB NPU
GoogLeNet ONNX w8a8 Snapdragon® X2 Elite 0.161 ms 1 - 1 MB NPU
GoogLeNet ONNX w8a8 Snapdragon® X Elite 0.291 ms 7 - 7 MB NPU
GoogLeNet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.223 ms 0 - 56 MB NPU
GoogLeNet ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.388 ms 0 - 59 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 1.163 ms 0 - 3 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 0.49 ms 0 - 4 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.314 ms 0 - 51 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® QCS8450 0.388 ms 0 - 59 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 0.418 ms 0 - 3 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.291 ms 7 - 7 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 2.323 ms 0 - 40 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 0.346 ms 0 - 41 MB NPU
GoogLeNet ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.197 ms 0 - 39 MB NPU
GoogLeNet ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 0.346 ms 0 - 41 MB NPU
GoogLeNet QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.368 ms 0 - 31 MB NPU
GoogLeNet QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.458 ms 1 - 31 MB NPU
GoogLeNet QNN_DLC float Snapdragon® X2 Elite 0.505 ms 1 - 1 MB NPU
GoogLeNet QNN_DLC float Snapdragon® X Elite 0.974 ms 1 - 1 MB NPU
GoogLeNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.564 ms 0 - 47 MB NPU
GoogLeNet QNN_DLC float Snapdragon® 8 Gen 1 Mobile 1.464 ms 0 - 53 MB NPU
GoogLeNet QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 1.484 ms 1 - 4 MB NPU
GoogLeNet QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.825 ms 1 - 2 MB NPU
GoogLeNet QNN_DLC float Qualcomm® SA8775P 1.538 ms 1 - 34 MB NPU
GoogLeNet QNN_DLC float Qualcomm® SA8650P 1.538 ms 1 - 34 MB NPU
GoogLeNet QNN_DLC float Qualcomm® SA8255P 1.538 ms 1 - 34 MB NPU
GoogLeNet QNN_DLC float Qualcomm® QCS8450 1.464 ms 0 - 53 MB NPU
GoogLeNet QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.428 ms 1 - 3 MB NPU
GoogLeNet QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 0.974 ms 1 - 1 MB NPU
GoogLeNet QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.458 ms 1 - 31 MB NPU
GoogLeNet QNN_DLC float Qualcomm® SA7255P 5.025 ms 1 - 32 MB NPU
GoogLeNet QNN_DLC float Qualcomm® SA8295P 1.668 ms 0 - 29 MB NPU
GoogLeNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.148 ms 0 - 33 MB NPU
GoogLeNet QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.156 ms 0 - 34 MB NPU
GoogLeNet QNN_DLC w8a8 Snapdragon® X2 Elite 0.218 ms 0 - 0 MB NPU
GoogLeNet QNN_DLC w8a8 Snapdragon® X Elite 0.345 ms 0 - 0 MB NPU
GoogLeNet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.186 ms 0 - 49 MB NPU
GoogLeNet QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.326 ms 0 - 55 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 1.032 ms 0 - 2 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.305 ms 0 - 3 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.254 ms 0 - 2 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® SA8775P 0.424 ms 0 - 35 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® SA8650P 0.424 ms 0 - 35 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® SA8255P 0.424 ms 0 - 35 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® QCS8450 0.326 ms 0 - 55 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 0.325 ms 0 - 2 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.345 ms 0 - 0 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 2.284 ms 0 - 35 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 0.334 ms 0 - 34 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.156 ms 0 - 34 MB NPU
GoogLeNet QNN_DLC w8a8 Qualcomm® SA8295P 0.504 ms 0 - 32 MB NPU
GoogLeNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.334 ms 0 - 34 MB NPU
GoogLeNet TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.374 ms 0 - 39 MB NPU
GoogLeNet TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.461 ms 0 - 42 MB NPU
GoogLeNet TFLITE float Snapdragon® 8 Gen 3 Mobile 0.57 ms 0 - 58 MB NPU
GoogLeNet TFLITE float Snapdragon® 8 Gen 1 Mobile 1.478 ms 0 - 67 MB NPU
GoogLeNet TFLITE float Qualcomm® Dragonwing™ IQ-8275 1.495 ms 0 - 17 MB NPU
GoogLeNet TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.826 ms 0 - 31 MB NPU
GoogLeNet TFLITE float Qualcomm® QCS8450 1.478 ms 0 - 67 MB NPU
GoogLeNet TFLITE float Qualcomm® Dragonwing™ IQ-9075 1.433 ms 0 - 16 MB NPU
GoogLeNet TFLITE float Qualcomm® Dragonwing™ Q-8750 0.461 ms 0 - 42 MB NPU
GoogLeNet TFLITE float Qualcomm® SA7255P 5.084 ms 0 - 37 MB NPU
GoogLeNet TFLITE float Qualcomm® SA8295P 1.691 ms 0 - 35 MB NPU
GoogLeNet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.142 ms 0 - 32 MB NPU
GoogLeNet TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.156 ms 0 - 32 MB NPU
GoogLeNet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.187 ms 0 - 48 MB NPU
GoogLeNet TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.325 ms 0 - 54 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 0.952 ms 0 - 9 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.312 ms 0 - 10 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.242 ms 0 - 58 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® SA8775P 0.437 ms 0 - 34 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® SA8650P 0.437 ms 0 - 34 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® SA8255P 0.437 ms 0 - 34 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® QCS8450 0.325 ms 0 - 54 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 0.341 ms 0 - 9 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 2.241 ms 0 - 34 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 0.333 ms 0 - 33 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.156 ms 0 - 32 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® SA7255P 0.819 ms 0 - 32 MB NPU
GoogLeNet TFLITE w8a8 Qualcomm® SA8295P 0.524 ms 0 - 30 MB NPU
GoogLeNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.333 ms 0 - 33 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
Image Classification
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