Hugging Face's logo

qualcomm
/
EfficientNet-B4

Image Classification
PyTorch
backbone
bu_auto
android
Model card Files
xet
 Community

EfficientNet-B4: Optimized for Qualcomm Devices

EfficientNetB4 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 EfficientNet-B4 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 w8a16 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a16 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit EfficientNet-B4 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 EfficientNet-B4 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

  • Input resolution: 380x380
  • Model checkpoint: Imagenet
  • Model size (float): 73.6 MB
  • Model size (w8a16): 24.0 MB
  • Number of parameters: 19.3M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
EfficientNet-B4 ONNX float Snapdragon® X2 Elite 3.926 ms 2 - 2 MB NPU
EfficientNet-B4 ONNX float Snapdragon® X Elite 7.685 ms 45 - 45 MB NPU
EfficientNet-B4 ONNX float Snapdragon® 8 Gen 3 Mobile 5.316 ms 0 - 150 MB NPU
EfficientNet-B4 ONNX float Snapdragon® 8 Gen 1 Mobile 20.51 ms 0 - 190 MB NPU
EfficientNet-B4 ONNX float Qualcomm® Dragonwing™ IQ-8275 9.585 ms 2 - 7 MB NPU
EfficientNet-B4 ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.329 ms 0 - 215 MB NPU
EfficientNet-B4 ONNX float Qualcomm® QCS8450 20.51 ms 0 - 190 MB NPU
EfficientNet-B4 ONNX float Qualcomm® Dragonwing™ IQ-9075 11.231 ms 1 - 6 MB NPU
EfficientNet-B4 ONNX float Qualcomm® Dragonwing™ IQ-X7181 7.685 ms 45 - 45 MB NPU
EfficientNet-B4 ONNX float Qualcomm® Dragonwing™ Q-8750 4.04 ms 0 - 90 MB NPU
EfficientNet-B4 ONNX float Snapdragon® 8 Elite Mobile 4.04 ms 0 - 90 MB NPU
EfficientNet-B4 ONNX float Snapdragon® 8 Elite Gen 5 Mobile 3.114 ms 0 - 206 MB NPU
EfficientNet-B4 ONNX w8a16 Snapdragon® X2 Elite 2.917 ms 2 - 2 MB NPU
EfficientNet-B4 ONNX w8a16 Snapdragon® X Elite 7.998 ms 24 - 24 MB NPU
EfficientNet-B4 ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 5.071 ms 1 - 226 MB NPU
EfficientNet-B4 ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 8.902 ms 0 - 226 MB NPU
EfficientNet-B4 ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 32.879 ms 0 - 4 MB NPU
EfficientNet-B4 ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 6.951 ms 1 - 4 MB NPU
EfficientNet-B4 ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 7.624 ms 0 - 30 MB NPU
EfficientNet-B4 ONNX w8a16 Qualcomm® QCS8450 8.902 ms 0 - 226 MB NPU
EfficientNet-B4 ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 8.015 ms 1 - 4 MB NPU
EfficientNet-B4 ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 7.998 ms 24 - 24 MB NPU
EfficientNet-B4 ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 53.875 ms 1 - 296 MB NPU
EfficientNet-B4 ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 8.929 ms 1 - 288 MB NPU
EfficientNet-B4 ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 3.413 ms 0 - 165 MB NPU
EfficientNet-B4 ONNX w8a16 Snapdragon® 8 Elite Mobile 3.413 ms 0 - 165 MB NPU
EfficientNet-B4 ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 2.744 ms 0 - 176 MB NPU
EfficientNet-B4 ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 8.929 ms 1 - 288 MB NPU
EfficientNet-B4 QNN_DLC float Snapdragon® X2 Elite 4.518 ms 2 - 2 MB NPU
EfficientNet-B4 QNN_DLC float Snapdragon® X Elite 8.905 ms 2 - 2 MB NPU
EfficientNet-B4 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 5.813 ms 0 - 142 MB NPU
EfficientNet-B4 QNN_DLC float Snapdragon® 8 Gen 1 Mobile 22.944 ms 2 - 188 MB NPU
EfficientNet-B4 QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 10.038 ms 2 - 6 MB NPU
EfficientNet-B4 QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 29.128 ms 2 - 81 MB NPU
EfficientNet-B4 QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 8.13 ms 2 - 3 MB NPU
EfficientNet-B4 QNN_DLC float Qualcomm® SA8775P 10.309 ms 2 - 85 MB NPU
EfficientNet-B4 QNN_DLC float Qualcomm® SA8650P 10.309 ms 2 - 85 MB NPU
EfficientNet-B4 QNN_DLC float Qualcomm® SA8255P 10.309 ms 2 - 85 MB NPU
EfficientNet-B4 QNN_DLC float Qualcomm® QCS8450 22.944 ms 2 - 188 MB NPU
EfficientNet-B4 QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 10.033 ms 4 - 7 MB NPU
EfficientNet-B4 QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 8.905 ms 2 - 2 MB NPU
EfficientNet-B4 QNN_DLC float Qualcomm® Dragonwing™ Q-8750 4.304 ms 2 - 87 MB NPU
EfficientNet-B4 QNN_DLC float Qualcomm® SA7255P 29.128 ms 2 - 81 MB NPU
EfficientNet-B4 QNN_DLC float Qualcomm® SA8295P 18.789 ms 2 - 124 MB NPU
EfficientNet-B4 QNN_DLC float Snapdragon® 8 Elite Mobile 4.304 ms 2 - 87 MB NPU
EfficientNet-B4 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 3.254 ms 2 - 207 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Snapdragon® X2 Elite 3.541 ms 1 - 1 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Snapdragon® X Elite 9.091 ms 1 - 1 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 5.643 ms 0 - 196 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 11.391 ms 1 - 202 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 33.692 ms 1 - 3 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 7.617 ms 1 - 4 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 15.42 ms 1 - 141 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 8.358 ms 1 - 136 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Qualcomm® SA8775P 8.902 ms 1 - 144 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Qualcomm® SA8650P 8.902 ms 1 - 144 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Qualcomm® SA8255P 8.902 ms 1 - 144 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Qualcomm® QCS8450 11.391 ms 1 - 202 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 8.652 ms 2 - 5 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 9.091 ms 1 - 1 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 60.7 ms 1 - 275 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 9.803 ms 1 - 268 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 3.716 ms 0 - 145 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Qualcomm® SA7255P 15.42 ms 1 - 141 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Qualcomm® SA8295P 10.91 ms 1 - 144 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 3.716 ms 0 - 145 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 3.008 ms 1 - 155 MB NPU
EfficientNet-B4 QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 9.803 ms 1 - 268 MB NPU
EfficientNet-B4 TFLITE float Snapdragon® 8 Gen 3 Mobile 5.745 ms 0 - 159 MB NPU
EfficientNet-B4 TFLITE float Snapdragon® 8 Gen 1 Mobile 21.784 ms 0 - 205 MB NPU
EfficientNet-B4 TFLITE float Qualcomm® Dragonwing™ IQ-8275 9.984 ms 0 - 50 MB NPU
EfficientNet-B4 TFLITE float Qualcomm® Dragonwing™ IQ-8275 28.92 ms 0 - 98 MB NPU
EfficientNet-B4 TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 8.024 ms 0 - 3 MB NPU
EfficientNet-B4 TFLITE float Qualcomm® SA8775P 10.285 ms 0 - 100 MB NPU
EfficientNet-B4 TFLITE float Qualcomm® SA8650P 10.285 ms 0 - 100 MB NPU
EfficientNet-B4 TFLITE float Qualcomm® SA8255P 10.285 ms 0 - 100 MB NPU
EfficientNet-B4 TFLITE float Qualcomm® QCS8450 21.784 ms 0 - 205 MB NPU
EfficientNet-B4 TFLITE float Qualcomm® Dragonwing™ IQ-9075 10.0 ms 0 - 49 MB NPU
EfficientNet-B4 TFLITE float Qualcomm® Dragonwing™ Q-8750 4.334 ms 0 - 104 MB NPU
EfficientNet-B4 TFLITE float Qualcomm® SA7255P 28.92 ms 0 - 98 MB NPU
EfficientNet-B4 TFLITE float Qualcomm® SA8295P 18.869 ms 0 - 139 MB NPU
EfficientNet-B4 TFLITE float Snapdragon® 8 Elite Mobile 4.334 ms 0 - 104 MB NPU
EfficientNet-B4 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 3.316 ms 0 - 99 MB NPU

License

  • The license for the original implementation of EfficientNet-B4 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/EfficientNet-B4