---
title: volo_d3_224.sail_in1k
canonical_url: "https://www.modelscope.cn/models/timm/volo_d3_224.sail_in1k"
md_url: "https://www.modelscope.cn/models/timm/volo_d3_224.sail_in1k.md"
repository: timm/volo_d3_224.sail_in1k
last_updated: 2025-01-22
license: apache-2.0
pipeline_tag: image-classification
tasks:
  - image-classification
parameters: 86.3M
tensor_type:
  - I64
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 1816
stars: 0
tags:
  - image-classification
  - timm
  - transformers
---

# volo_d3_224.sail_in1k

> volo_d3_224.sail_in1k - timm 在 ModelScope 开源的模型。Model card for volod3224.sailin1k

timm/volo_d3_224.sail_in1k 是 ModelScope 魔搭社区上的 86.3M 参数image-classification模型，采用 apache-2.0 许可。

- **Repository**: timm/volo_d3_224.sail_in1k
- **License**: apache-2.0
- **Tasks**: image-classification
- **Parameters**: 86.3M
- **Tags**: image-classification, timm, transformers
- **Downloads**: 1816
- **Stars**: 0
- **Last updated**: 2025-01-22

Source: https://www.modelscope.cn/models/timm/volo_d3_224.sail_in1k

---

# Model card for volo_d3_224.sail_in1k

A VOLO (Vision Outlooker) image classification model. Trained on ImageNet-1k with token labelling by paper authors.

## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
  - Params (M): 86.3
  - GMACs: 20.8
  - Activations (M): 60.1
  - Image size: 224 x 224
- **Papers:**
  - VOLO: Vision Outlooker for Visual Recognition: https://arxiv.org/abs/2106.13112
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/sail-sg/volo

## 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('volo_d3_224.sail_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(
    'volo_d3_224.sail_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, 197, 512) shaped tensor

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

## Citation
```bibtex
@article{yuan2022volo,
  title={Volo: Vision outlooker for visual recognition},
  author={Yuan, Li and Hou, Qibin and Jiang, Zihang and Feng, Jiashi and Yan, Shuicheng},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2022},
  publisher={IEEE}
}
```
