# HieraDet (SAM 2)

**Category:** ViT · **Code:**
[`timm/models/hieradet_sam2.py`](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/hieradet_sam2.py)
· **Architectures:** 5 · **Pretrained weights:** 8 (0 with ImageNet-1k results)

HieraDet, the Hiera based image encoder of Segment Anything 2 (SAM 2), with windowed attention and windowed position
embeddings.

## Papers

* [SAM 2: Segment Anything in Images and Videos](https://arxiv.org/abs/2408.00714)
* [Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles](https://arxiv.org/abs/2306.00989)

## 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('sam2_hiera_base_plus.fb_r896', pretrained=True)
>>> data_config = timm.data.resolve_model_data_config(model)
```

## Model API support

| Feature | `HieraDet` |
|---|---|
| [`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 (`HieraDet` with `sam2_hiera_tiny` at 256), 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 |
|---|---:|---:|---:|---:|
| `hieradet_small` | 34.73 | 8.51 | 256 | 0 |
| `sam2_hiera_base_plus` | 68.68 | 227.48 | 896 | 2 |
| `sam2_hiera_large` | 212.15 | 907.48 | 1024 | 2 |
| `sam2_hiera_small` | 33.95 | 123.99 | 896 | 2 |
| `sam2_hiera_tiny` | 26.85 | 99.86 | 896 | 2 |

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.

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `sam2_hiera_base_plus.fb_r896` | 896 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/sam2_hiera_base_plus.fb_r896) |
| `sam2_hiera_base_plus.fb_r896_2pt1` | 896 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/sam2_hiera_base_plus.fb_r896_2pt1) |
| `sam2_hiera_large.fb_r1024` | 1024 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/sam2_hiera_large.fb_r1024) |
| `sam2_hiera_large.fb_r1024_2pt1` | 1024 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/sam2_hiera_large.fb_r1024_2pt1) |
| `sam2_hiera_small.fb_r896` | 896 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/sam2_hiera_small.fb_r896) |
| `sam2_hiera_small.fb_r896_2pt1` | 896 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/sam2_hiera_small.fb_r896_2pt1) |
| `sam2_hiera_tiny.fb_r896` | 896 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/sam2_hiera_tiny.fb_r896) |
| `sam2_hiera_tiny.fb_r896_2pt1` | 896 | - | - | none | apache-2.0 | [timm](https://huggingface.co/timm/sam2_hiera_tiny.fb_r896_2pt1) |