JaxNN conversion of the timm vit_large_patch16_224.mae Vision Transformer checkpoint.

Model Details

• Architecture: vit_large_patch16_224
• Source: timm/vit_large_patch16_224.mae

Model card for vit_large_patch16_224.mae

A Vision Transformer (ViT) image feature model. Pretrained on ImageNet-1k with Self-Supervised Masked Autoencoder (MAE) method.

Model Details

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 303.3
  • GMACs: 61.6
  • Activations (M): 63.5
  • Image size: 224 x 224
• Papers:
  • Masked Autoencoders Are Scalable Vision Learners: https://arxiv.org/abs/2111.06377
  • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
• Pretrain Dataset: ImageNet-1k
• Original: https://github.com/facebookresearch/mae

Model Usage

Image Classification

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_large_patch16_224.mae", 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

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_large_patch16_224.mae",
    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

@Article{MaskedAutoencoders2021,
  author  = {Kaiming He and Xinlei Chen and Saining Xie and Yanghao Li and Piotr Doll{'a}r and Ross Girshick},
  journal = {arXiv:2111.06377},
  title   = {Masked Autoencoders Are Scalable Vision Learners},
  year    = {2021},
}

@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}
}

@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}}
}