EfficientNet4Lite

Image classification model based on EfficientNet-Lite architecture. Trained on ImageNet 1k dataset. (labels are available via org.jetbrains.kotlinx.dl.impl.dataset.Imagenet.labels method).

EfficientNet-Lite 4 is the largest variant and most accurate of the set of EfficientNet-Lite model. It is an integer-only quantized model that produces the highest accuracy of all the EfficientNet models. It achieves 80.4% ImageNet top-1 accuracy, while still running in real-time (e.g. 30ms/image) on a Pixel 4 CPU.

The model have

• an input with the shape (1x224x224x3)

• an output with the shape (1x1000)