---
title: vit_base_r50_s16_384.orig_in21k_ft_in1k
canonical_url: "https://www.modelscope.cn/models/timm/vit_base_r50_s16_384.orig_in21k_ft_in1k"
md_url: "https://www.modelscope.cn/models/timm/vit_base_r50_s16_384.orig_in21k_ft_in1k.md"
repository: timm/vit_base_r50_s16_384.orig_in21k_ft_in1k
last_updated: 2025-01-22
license: apache-2.0
pipeline_tag: image-classification
tasks:
  - image-classification
parameters: 99.0M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 1842
stars: 3
tags:
  - image-classification
  - timm
  - transformers
---

# vit_base_r50_s16_384.orig_in21k_ft_in1k

> vit_base_r50_s16_384.orig_in21k_ft_in1k - timm 在 ModelScope 开源的模型。Model card for vitbaser50s16384.origin21kftin1k

timm/vit_base_r50_s16_384.orig_in21k_ft_in1k 是 ModelScope 魔搭社区上的 99.0M 参数image-classification模型，采用 apache-2.0 许可。

- **Repository**: timm/vit_base_r50_s16_384.orig_in21k_ft_in1k
- **License**: apache-2.0
- **Tasks**: image-classification
- **Parameters**: 99.0M
- **Tags**: image-classification, timm, transformers
- **Downloads**: 1842
- **Stars**: 3
- **Last updated**: 2025-01-22

Source: https://www.modelscope.cn/models/timm/vit_base_r50_s16_384.orig_in21k_ft_in1k

---

# Model card for vit_base_r50_s16_384.orig_in21k_ft_in1k

A ResNet - Vision Transformer (ViT) hybrid image classification model. Trained on ImageNet-21k and fine-tuned on ImageNet-1k in JAX by paper authors, ported to PyTorch by Ross Wightman.


## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
  - Params (M): 99.0
  - GMACs: 61.3
  - Activations (M): 81.8
  - Image size: 384 x 384
- **Papers:**
  - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- **Dataset:** ImageNet-1k
- **Pretrain Dataset:** ImageNet-21k
- **Original:** https://github.com/google-research/vision_transformer

## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model('vit_base_r50_s16_384.orig_in21k_ft_in1k', pretrained=True)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1

top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```

### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model(
    'vit_base_r50_s16_384.orig_in21k_ft_in1k',
    pretrained=True,
    num_classes=0,  # remove classifier nn.Linear
)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor

# or equivalently (without needing to set num_classes=0)

output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 577, 768) shaped tensor

output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```

## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).

## Citation
```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}}
}
```
