---
tags:
- image-classification
- timm
library_name: timm
license: other
datasets:
- imagenet-1k
---
# Model card for fastvit_sa24.apple_dist_in1k

A FastViT image classification model. Trained on ImageNet-1k with distillation by paper authors.

Please observe [original license](https://github.com/apple/ml-fastvit/blob/8af5928238cab99c45f64fc3e4e7b1516b8224ba/LICENSE).

## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
  - Params (M): 21.6
  - GMACs: 3.8
  - Activations (M): 23.9
  - Image size: 256 x 256
- **Papers:**
  - FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization: https://arxiv.org/abs/2303.14189
- **Original:** https://github.com/apple/ml-fastvit
- **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('fastvit_sa24.apple_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)
```

### 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(
    'fastvit_sa24.apple_dist_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.:
    #  torch.Size([1, 64, 64, 64])
    #  torch.Size([1, 128, 32, 32])
    #  torch.Size([1, 256, 16, 16])
    #  torch.Size([1, 512, 8, 8])

    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(
    'fastvit_sa24.apple_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, 512, 8, 8) shaped tensor

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

## Citation
```bibtex
@inproceedings{vasufastvit2023,
  author = {Pavan Kumar Anasosalu Vasu and James Gabriel and Jeff Zhu and Oncel Tuzel and Anurag Ranjan},
  title = {FastViT:  A Fast Hybrid Vision Transformer using Structural Reparameterization},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  year = {2023}
}
```