---
title: regnet-y-320-seer
canonical_url: "https://www.modelscope.cn/models/facebook/regnet-y-320-seer"
md_url: "https://www.modelscope.cn/models/facebook/regnet-y-320-seer.md"
repository: facebook/regnet-y-320-seer
last_updated: 2025-05-20
license: apache-2.0
model_type:
  - regnet
architectures:
  - RegNetModel
library_name:
  - pytorch
  - transformer
  - tensorflow
frameworks:
  - pytorch
downloads: 333
stars: 0
tags:
  - vision
---

# regnet-y-320-seer

> regnet-y-320-seer - facebook 在 ModelScope 开源的模型。RegNetModel model was introduced in the paper Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision and first released in this repository.

facebook/regnet-y-320-seer 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。

- **Repository**: facebook/regnet-y-320-seer
- **License**: apache-2.0
- **Tags**: vision
- **Downloads**: 333
- **Stars**: 0
- **Last updated**: 2025-05-20

Source: https://www.modelscope.cn/models/facebook/regnet-y-320-seer

---

# RegNetModel

RegNetModel model was introduced in the paper [Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision](https://arxiv.org/abs/2202.08360) 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

The authors trained [RegNets](https://huggingface.co/?models=regnet) models in a self-supervised fashion on bilion of random images from the internet

![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("zuppif/regnet-y-040")
>>> model = RegNetModel.from_pretrained("zuppif/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).