---
license: apache-2.0
tags:
- vision





---

# RegNetModel

RegNetModel model was introduced in the paper [Self-supervised Pretraining of Visual Features in the Wild](https://arxiv.org/abs/2103.01988) and first released in [this repository](https://github.com/facebookresearch/vissl/tree/main/projects/SEER). 

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

## Model description

This gigantic model is a scale up [RegNetY](https://arxiv.org/abs/2003.13678) model trained on one bilion random images.

![model image](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/regnet_architecture.png)

## Intended uses & limitations

You can use the raw model for image classification. See the [model hub](https://huggingface.co/models?search=regnet) to look for
fine-tuned versions on a task that interests you.

### How to use

Here is how to use this model:

```python
>>> from transformers import AutoFeatureExtractor, RegNetModel
>>> import torch
>>> from datasets import load_dataset

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

>>> feature_extractor = AutoFeatureExtractor.from_pretrained("facebook/regnet-y-040")
>>> model = RegNetModel.from_pretrained("facebook/regnet-y-040")

>>> inputs = feature_extractor(image, return_tensors="pt")

>>> with torch.no_grad():
...     outputs = model(**inputs)

>>> last_hidden_states = outputs.last_hidden_state
>>> list(last_hidden_states.shape)
[1, 1088, 7, 7]
```



For more code examples, we refer to the [documentation](https://huggingface.co/docs/transformers/master/en/model_doc/regnet).