Efficientnet B2

🚀 EfficientNet (b2 model)

EfficientNet model trained on ImageNet-1k at 260x260 resolution, offering a new way for model scaling in convolutional neural networks.

🚀 Quick Start

The EfficientNet model is trained on the ImageNet - 1k dataset at a resolution of 260x260. It was first introduced in the paper EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks by Mingxing Tan and Quoc V. Le, and initially released in this repository.

Disclaimer: The team releasing EfficientNet did not write a model card for this model, so this model card is written by the Hugging Face team.

✨ Features

EfficientNet is a mobile - friendly pure convolutional model (ConvNet). It proposes a novel scaling method that uniformly scales all dimensions of depth, width, and resolution using a simple yet highly effective compound coefficient.

📚 Documentation

Intended uses & limitations

You can use the raw model for image classification. Check the model hub to find fine - tuned versions for tasks that interest you.

How to use

Here is an example of using this model to classify an image from the COCO 2017 dataset into one of the 1,000 ImageNet classes:

import torch
from datasets import load_dataset
from transformers import EfficientNetImageProcessor, EfficientNetForImageClassification

dataset = load_dataset("huggingface/cats-image")
image = dataset["test"]["image"][0]

preprocessor = EfficientNetImageProcessor.from_pretrained("google/efficientnet-b2")
model = EfficientNetForImageClassification.from_pretrained("google/efficientnet-b2")

inputs = preprocessor(image, return_tensors="pt")

with torch.no_grad():
    logits = model(**inputs).logits

# model predicts one of the 1000 ImageNet classes
predicted_label = logits.argmax(-1).item()
print(model.config.id2label[predicted_label]),

For more code examples, refer to the documentation.

BibTeX entry and citation info

@article{Tan2019EfficientNetRM,
  title={EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks},
  author={Mingxing Tan and Quoc V. Le},
  journal={ArXiv},
  year={2019},
  volume={abs/1905.11946}
}

📄 License

This project is licensed under the Apache - 2.0 license.