Convnext Base 384 22k 1k

🚀 ConvNeXT (base-sized model)

A ConvNeXT model pre - trained on ImageNet - 22k and fine - tuned on ImageNet - 1k at resolution 384x384. It offers a new approach to image classification by combining convolutional design with modern architecture concepts.

🚀 Quick Start

The ConvNeXT model is a powerful tool for image classification. It was introduced in the paper A ConvNet for the 2020s by Liu et al. and first released in this repository.

Disclaimer: The team releasing ConvNeXT did not write a model card for this model so this model card has been written by the Hugging Face team.

✨ Features

• Innovative Design: ConvNeXT is a pure convolutional model (ConvNet) inspired by Vision Transformers, aiming to outperform them.
• Modernized Architecture: The authors started from a ResNet and "modernized" its design by taking the Swin Transformer as inspiration.

📚 Documentation

Intended uses & limitations

You can use the raw model for image classification. See the model hub to look for fine - tuned versions on a task that interests you.

💻 Usage Examples

Basic Usage

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

from transformers import ConvNextImageProcessor, ConvNextForImageClassification
import torch
from datasets import load_dataset

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

processor = ConvNextImageProcessor.from_pretrained("facebook/convnext-base-384-22k-1k")
model = ConvNextForImageClassification.from_pretrained("facebook/convnext-base-384-22k-1k")

inputs = processor(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, we refer to the documentation.

🔧 Technical Details

ConvNeXT is a pure convolutional model (ConvNet), inspired by the design of Vision Transformers. The authors started from a ResNet and "modernized" its design by taking the Swin Transformer as inspiration, claiming to outperform Vision Transformers.

📄 License

This model is licensed under the Apache - 2.0 license.

BibTeX entry and citation info

@article{DBLP:journals/corr/abs-2201-03545,
  author    = {Zhuang Liu and
               Hanzi Mao and
               Chao{-}Yuan Wu and
               Christoph Feichtenhofer and
               Trevor Darrell and
               Saining Xie},
  title     = {A ConvNet for the 2020s},
  journal   = {CoRR},
  volume    = {abs/2201.03545},
  year      = {2022},
  url       = {https://arxiv.org/abs/2201.03545},
  eprinttype = {arXiv},
  eprint    = {2201.03545},
  timestamp = {Thu, 20 Jan 2022 14:21:35 +0100},
  biburl    = {https://dblp.org/rec/journals/corr/abs-2201-03545.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}