# DaViT

**Category:** ViT · **Code:**
[`timm/models/davit.py`](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/davit.py) ·
**Architectures:** 8 · **Pretrained weights:** 5 (3 with ImageNet-1k results)

Dual Attention Vision Transformers (DaViT) combine spatial window attention and channel group attention, both linear in
the number of tokens, in a hierarchical design.

## Papers

* [DaViT: Dual Attention Vision Transformers](https://arxiv.org/abs/2204.03645)
* [Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://arxiv.org/abs/2311.06242)

## Usage

See the [Quickstart](../quickstart) for loading pretrained weights, image preprocessing and fine-tuning, and [Feature
Extraction](../feature_extraction) for using the models as backbones.

```py
>>> import timm
>>> model = timm.create_model('davit_tiny.msft_in1k', pretrained=True)
>>> data_config = timm.data.resolve_model_data_config(model)
```

## Model API support

| Feature | `DaVit` |
|---|---|
| [`features_only=True` feature maps](../model_api#intermediate-features) | ✓ (strides 4, 8, 16, 32) |
| [`forward_intermediates()`](../model_api#intermediate-features) | ✓ |
| [`prune_intermediate_layers()`](../model_api#intermediate-features) | ✓ |
| [Any input size, no changes needed](../model_api#input-size) | ✓ |
| [`set_input_size()`](../model_api#input-size) | – |
| [`dynamic_img_size=True`](../model_api#input-size) | – |
| [`set_grad_checkpointing()`](../model_api#training-hooks) | ✓ |
| [Layer-wise LR decay (`group_matcher()`)](../model_api#training-hooks) | ✓ |
| [`reset_classifier()`](../model_api#classifier) | ✓ |

✓ supported, ✓ (square) works for square sizes only, ✗ not supported, – not needed (the model already accepts any input
size). Checked by running each feature on a randomly initialized model (`DaVit` with `davit_tiny` at 224), other
architectures of the same class are expected to behave the same. See the [Model API](../model_api) page for details.

## Architectures

| Architecture | Params (M) | GMACs | Input size | Pretrained weights |
|---|---:|---:|---:|---:|
| `davit_base` | 87.95 | 15.51 | 224 | 1 |
| `davit_base_fl` | 90.37 | 190.32 | 768 | 1 |
| `davit_giant` | 1406.47 | 192.92 | 224 | 0 |
| `davit_huge` | 348.92 | 61.23 | 224 | 0 |
| `davit_huge_fl` | 360.64 | 744.84 | 768 | 1 |
| `davit_large` | 196.81 | 34.60 | 224 | 0 |
| `davit_small` | 49.75 | 8.80 | 224 | 1 |
| `davit_tiny` | 28.36 | 4.54 | 224 | 1 |

GMACs and parameter counts are for the default input size and classifier of each architecture, from the [benchmark
results](https://github.com/huggingface/pytorch-image-models/tree/main/results).

## Pretrained weights

Top-1 is ImageNet-1k validation accuracy from
[`results-imagenet.csv`](https://github.com/huggingface/pytorch-image-models/blob/main/results/results-imagenet.csv) at
the listed eval size, - if the weight has no ImageNet-1k result (e.g. pretraining or image-text weights). Classes is the
size of the pretrained classifier, none for weights without one.

Weights are grouped by source: the paper or origin given in the pretrained config, else a Hub organization other than
`timm`, else the first part of the pretrained tag (`architecture.tag`). Sources with a single weight are listed under
other.

### `msft` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `davit_base.msft_in1k` | 224 | 84.652 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/davit_base.msft_in1k) |
| `davit_small.msft_in1k` | 224 | 84.252 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/davit_small.msft_in1k) |
| `davit_tiny.msft_in1k` | 224 | 82.694 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/davit_tiny.msft_in1k) |

### microsoft

Hosted by [`microsoft`](https://huggingface.co/microsoft) on the Hugging Face Hub.

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `davit_base_fl.msft_florence2` | 768 | - | - | none | apache-2.0 | [microsoft/Florence-2-base](https://huggingface.co/microsoft/Florence-2-base) |
| `davit_huge_fl.msft_florence2` | 768 | - | - | none | apache-2.0 | [microsoft/Florence-2-large](https://huggingface.co/microsoft/Florence-2-large) |