---
title: swinv2_tiny_window16_256.ms_in1k
canonical_url: "https://www.modelscope.cn/models/timm/swinv2_tiny_window16_256.ms_in1k"
md_url: "https://www.modelscope.cn/models/timm/swinv2_tiny_window16_256.ms_in1k.md"
repository: timm/swinv2_tiny_window16_256.ms_in1k
last_updated: 2025-01-22
license: mit
pipeline_tag: image-classification
tasks:
  - image-classification
parameters: 29.7M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 1819
stars: 0
tags:
  - image-classification
  - timm
  - transformers
---

# swinv2_tiny_window16_256.ms_in1k

> swinv2_tiny_window16_256.ms_in1k - timm 在 ModelScope 开源的模型。Model card for swinv2tinywindow16256.msin1k

timm/swinv2_tiny_window16_256.ms_in1k 是 ModelScope 魔搭社区上的 29.7M 参数image-classification模型，采用 mit 许可。

- **Repository**: timm/swinv2_tiny_window16_256.ms_in1k
- **License**: mit
- **Tasks**: image-classification
- **Parameters**: 29.7M
- **Tags**: image-classification, timm, transformers
- **Downloads**: 1819
- **Stars**: 0
- **Last updated**: 2025-01-22

Source: https://www.modelscope.cn/models/timm/swinv2_tiny_window16_256.ms_in1k

---

# Model card for swinv2_tiny_window16_256.ms_in1k

A Swin Transformer V2 image classification model. Pretrained on ImageNet-1k by paper authors.


## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
  - Params (M): 28.3
  - GMACs: 6.7
  - Activations (M): 39.0
  - Image size: 256 x 256
- **Papers:**
  - Swin Transformer V2: Scaling Up Capacity and Resolution: https://arxiv.org/abs/2111.09883
- **Original:** https://github.com/microsoft/Swin-Transformer
- **Dataset:** ImageNet-1k

## 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('swinv2_tiny_window16_256.ms_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)
```

### Feature Map Extraction
```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(
    'swinv2_tiny_window16_256.ms_in1k',
    pretrained=True,
    features_only=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

for o in output:
    # print shape of each feature map in output
    # e.g. for swin_base_patch4_window7_224 (NHWC output)
    #  torch.Size([1, 56, 56, 128])
    #  torch.Size([1, 28, 28, 256])
    #  torch.Size([1, 14, 14, 512])
    #  torch.Size([1, 7, 7, 1024])
    # e.g. for swinv2_cr_small_ns_224 (NCHW output)
    #  torch.Size([1, 96, 56, 56]) 
    #  torch.Size([1, 192, 28, 28])
    #  torch.Size([1, 384, 14, 14])
    #  torch.Size([1, 768, 7, 7])
    print(o.shape)
```

### 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(
    'swinv2_tiny_window16_256.ms_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 (ie.e a (batch_size, H, W,  num_features) tensor for swin / swinv2
# or (batch_size, num_features, H, W) for swinv2_cr

output = model.forward_head(output, pre_logits=True)
# output is (batch_size, num_features) 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
@inproceedings{liu2021swinv2,
  title={Swin Transformer V2: Scaling Up Capacity and Resolution}, 
  author={Ze Liu and Han Hu and Yutong Lin and Zhuliang Yao and Zhenda Xie and Yixuan Wei and Jia Ning and Yue Cao and Zheng Zhang and Li Dong and Furu Wei and Baining Guo},
  booktitle={International Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2022}
}
```
```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}}
}
```
