---
title: cait_xs24_384.fb_dist_in1k
canonical_url: "https://www.modelscope.cn/models/timm/cait_xs24_384.fb_dist_in1k"
md_url: "https://www.modelscope.cn/models/timm/cait_xs24_384.fb_dist_in1k.md"
repository: timm/cait_xs24_384.fb_dist_in1k
last_updated: 2025-01-22
license: apache-2.0
pipeline_tag: image-classification
tasks:
  - image-classification
parameters: 26.7M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 1820
stars: 0
tags:
  - image-classification
  - timm
  - transformers
---

# cait_xs24_384.fb_dist_in1k

> cait_xs24_384.fb_dist_in1k - timm 在 ModelScope 开源的模型。Model card for caitxs24384.fbdistin1k

timm/cait_xs24_384.fb_dist_in1k 是 ModelScope 魔搭社区上的 26.7M 参数image-classification模型，采用 apache-2.0 许可。

- **Repository**: timm/cait_xs24_384.fb_dist_in1k
- **License**: apache-2.0
- **Tasks**: image-classification
- **Parameters**: 26.7M
- **Tags**: image-classification, timm, transformers
- **Downloads**: 1820
- **Stars**: 0
- **Last updated**: 2025-01-22

Source: https://www.modelscope.cn/models/timm/cait_xs24_384.fb_dist_in1k

---

# Model card for cait_xs24_384.fb_dist_in1k

A CaiT (Class-Attention in Image Transformers) image classification model. Pretrained on ImageNet-1k with distillation by paper authors.

## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
  - Params (M): 26.7
  - GMACs: 19.3
  - Activations (M): 184.0
  - Image size: 384 x 384
- **Papers:**
  - Going deeper with Image Transformers: https://arxiv.org/abs/2103.17239
- **Dataset:** ImageNet-1k
- **Original:** https://github.com/facebookresearch/deit

## 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('cait_xs24_384.fb_dist_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(
    'cait_xs24_384.fb_dist_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, 288) shaped tensor

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

## Citation
```bibtex
@InProceedings{Touvron_2021_ICCV,
    author    = {Touvron, Hugo and Cord, Matthieu and Sablayrolles, Alexandre and Synnaeve, Gabriel and J'egou, Herv'e},
    title     = {Going Deeper With Image Transformers},
    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
    month     = {October},
    year      = {2021},
    pages     = {32-42}
}
```
