---
license: apache-2.0
tags:
- vision
- image-classification
datasets:
- imagenet-1k
widget:
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/tiger.jpg
  example_title: Tiger
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/teapot.jpg
  example_title: Teapot
- src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/palace.jpg
  example_title: Palace
---

# Pyramid Vision Transformer (large-sized model) 

Pyramid Vision Transformer  (PVT) model pre-trained on ImageNet-1K (1 million images, 1000 classes) at resolution 224x224, and fine-tuned on ImageNet 2012 (1 million images, 1,000 classes) at resolution 224x224. It was introduced in the paper [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://arxiv.org/abs/2102.12122) by Wenhai Wang, Enze Xie, Xiang Li, Deng-Ping Fan, Kaitao Song, Ding Liang, Tong Lu, Ping Luo, Ling Shao and first released in [this repository](https://github.com/whai362/PVT). 

Disclaimer: The team releasing PVT did not write a model card for this model so this model card has been written by [Rinat S. [@Xrenya]](https://huggingface.co/Xrenya).

## Model description

The Pyramid Vision Transformer (PVT) is a transformer encoder model (BERT-like) pretrained on ImageNet-1k (also referred to as ILSVRC2012), a dataset comprising 1 million images and 1,000 classes, also at resolution 224x224.

Images are presented to the model as a sequence of variable-size patches, which are linearly embedded. Unlike ViT models, PVT is  using a progressive shrinking pyramid to reduce computations of large feature maps at each stage. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One also adds absolute position embeddings before feeding the sequence to the layers of the Transformer encoder.

By pre-training the model, it learns an inner representation of images that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled images for instance, you can train a standard classifier by placing a linear layer on top of the pre-trained encoder. One typically places a linear layer on top of the [CLS] token, as the last hidden state of this token can be seen as a representation of an entire image.

## Intended uses & limitations

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

### How to use

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

```python
from transformers import PvtImageProcessor, PvtForImageClassification
from PIL import Image
import requests

url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)

processor = PvtImageProcessor.from_pretrained('Zetatech/pvt-large-224')
model = PvtForImageClassification.from_pretrained('Zetatech/pvt-large-224')

inputs = processor(images=image, return_tensors="pt")
outputs = model(**inputs)
logits = outputs.logits
# model predicts one of the 1000 ImageNet classes
predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])
```

For more code examples, we refer to the [documentation](https://huggingface.co/transformers/model_doc/pvt.html#).

## Training data

The ViT model was pretrained on [ImageNet-1k](http://www.image-net.org/challenges/LSVRC/2012/), a dataset consisting of 1 million images and 1k classes. 

## Training procedure

### Preprocessing

The exact details of preprocessing of images during training/validation can be found [here](https://github.com/whai362/PVT/blob/v2/classification/datasets.py). 

Images are resized/rescaled to the same resolution (224x224) and normalized across the RGB channels with mean (0.485, 0.456, 0.406) and standard deviation (0.229, 0.224, 0.225).



### BibTeX entry and citation info

```bibtex
@inproceedings{wang2021pyramid,
  title={Pyramid vision transformer: A versatile backbone for dense prediction without convolutions},
  author={Wang, Wenhai and Xie, Enze and Li, Xiang and Fan, Deng-Ping and Song, Kaitao and Liang, Ding and Lu, Tong and Luo, Ping and Shao, Ling},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={568--578},
  year={2021}
}
```