---
tags:
- image-classification
- jax
- jaxnn
- vision-transformer
pipeline_tag: image-classification
library_name: jaxnn
license: apache-2.0
---

JaxNN conversion of the timm `vit_base_patch16_224.sam_in1k` Vision Transformer checkpoint.

## Model Details
- **Architecture:** vit_base_patch16_224
- **Source:** timm/vit_base_patch16_224.sam_in1k

# Model card for vit_base_patch16_224.sam_in1k

A Vision Transformer (ViT) image classification model. Trained on ImageNet-1k using Sharpness Aware Minimization.


## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
  - Params (M): 86.6
  - GMACs: 16.9
  - Activations (M): 16.5
  - Image size: 224 x 224
- **Papers:**
  - When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations: https://arxiv.org/abs/2106.01548
  - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/google-research/vision_transformer

## Model Usage

### Image Classification

```python
from urllib.request import urlopen

import jax
from PIL import Image

import jaxnn

img = Image.open(urlopen(
    "https://huggingface.co/datasets/huggingface/cats-image/resolve/main/cats_image.jpeg"
))

model = jaxnn.create_model("vit_base_patch16_224.sam_in1k", pretrained=True)
model.eval()

data_config = jaxnn.data.resolve_model_data_config(model)
transforms = jaxnn.data.create_transform(**data_config, is_training=False)

x = jax.numpy.expand_dims(transforms(img), 0)
output = model(x, deterministic=True)

top5_probabilities, top5_class_indices = jax.lax.top_k(
    jax.nn.softmax(output, axis=-1) * 100,
    k=5,
)
```

### Image Embeddings

```python
from urllib.request import urlopen

import jax
from PIL import Image

import jaxnn

img = Image.open(urlopen(
    "https://huggingface.co/datasets/huggingface/cats-image/resolve/main/cats_image.jpeg"
))

model = jaxnn.create_model(
    "vit_base_patch16_224.sam_in1k",
    pretrained=True,
    num_classes=0,
)
model.eval()

data_config = jaxnn.data.resolve_model_data_config(model)
transforms = jaxnn.data.create_transform(**data_config, is_training=False)

x = jax.numpy.expand_dims(transforms(img), 0)
output = model(x, deterministic=True)
```

## Citation
```bibtex
@article{chen2021vision,
  title={When vision transformers outperform resnets without pre-training or strong data augmentations},
  author={Chen, Xiangning and Hsieh, Cho-Jui and Gong, Boqing},
  journal={arXiv preprint arXiv:2106.01548},
  year={2021}
}
```
```bibtex
@article{dosovitskiy2020vit,
  title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
  author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and  Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
  journal={ICLR},
  year={2021}
}
```
```bibtex
@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```