Skip to content
imaged

Image classification

EfficientNet-B0

The CPU-friendly default classifier, around 21 MB on disk.

BSD-3-Clause
Explore model

About this model

EfficientNet-B0 is the entry point of the EfficientNet scaling family. Around 5.3M parameters, fp32 ONNX is 21 MB. It returns top-K class probabilities over the 1000 ImageNet-1k classes.

The build is a fresh torchvision IMAGENET1K_V1 export with normalize baked into the graph. On M1 Max, CPU runs at 37 ms warm and CoreML at 18 ms warm.

What you can build

  • Tag uploaded photos with a coarse subject before further routing.
  • Run on-device classification with a 20 MB asset budget.
  • Compare against MobileNetV3-Small when you need a bit more accuracy.
  • Drop into a content pipeline that needs predictable CPU latency.

Variants & downloads

Choose the build for your app

Model files are being prepared.

Explore the model’s examples, source links, and integration notes while download variants are added.

Performance

Results depend on the device, runtime, and test conditions. Each measurement keeps its own context.

M1 Max, macOS 15, ONNX Runtime 1.17

See original catalog hardware notes · CPU

37.1 ms

Warm inference

Catalog reference · variant unspecifiedCold start (ms): 41.39

Reference result from the existing catalog; conversion variant and measurement date were not recorded.

M1 Max, macOS 15, ONNX Runtime 1.17

See original catalog hardware notes · CoreML

18.1 ms

Warm inference

Catalog reference · variant unspecifiedCold start (ms): 86.84

Reference result from the existing catalog; conversion variant and measurement date were not recorded.

RTX 2060, Ubuntu 24.04, ONNX Runtime 1.24.3

See original catalog hardware notes · CUDA

4.4 ms

Warm inference

Catalog reference · variant unspecified

Reference result from the existing catalog; conversion variant and measurement date were not recorded.

Integration examples

Vision SDK integration

cpp

#include "imaged/sdk.hpp"
#include "imaged/families/classifier/classifier_family.hpp"

imaged::SDK::AI ai;
auto& config = ai.getOptions();
config.set("classifier.model", "weights/efficientnet_b0.onnx");
config.set("classifier.labels", "weights/labels.txt");
config.set("classifier.topK", 5);

imaged::SDK::ClassifierFamily family;
family.load(config);

imaged::SDK::Image image;
image.load("photo.jpg");

auto result = family.run(&image);
auto& classes = std::get<imaged::SDK::ClassificationResult>(result).classes;