README.md

---
license: odc-by
language:
- en
tags:
- remote-sensing
- earth-observation
- satellite
- aerial
- multispectral
- feature-extraction
- vision
- satlaspretrain
- transformers
library_name: transformers
pipeline_tag: feature-extraction
---

# SatlasPretrain Transformers Models

Hugging Face–compatible checkpoints from the official [SatlasPretrain](https://github.com/allenai/satlas) foundation models (ICCV 2023). Each subfolder is a standalone model repo layout (`config.json`, `model.safetensors`, preprocessor, and remote code) for feature extraction on satellite and aerial imagery.

## Model Description

These models are remote sensing encoders pretrained on the [SatlasPretrain dataset](https://github.com/allenai/satlas/blob/main/SatlasPretrain.md) covering Sentinel-2, Landsat 8/9, and high-resolution aerial imagery.

This collection bundles **19 checkpoints** spanning:

- **Architectures:** Swin-v2-Base, Swin-v2-Tiny, ResNet50, ResNet152
- **Input sources:** Sentinel-2, Landsat, aerial
- **Modes:** single-image (SI) and multi-image temporal max-pooling (MI)
- **Band configs:** RGB (3ch), multispectral (9ch), Landsat all-bands (11ch)

All folders ship self-contained remote code (`modeling_satlaspretrain.py`, processor, pipeline) and load with `trust_remote_code=True`.

**Developed by:** [Allen AI / Satlas](https://github.com/allenai/satlas)  
**Packaged for Hugging Face by:** BiliSakura  
**License (weights):** [ODC-BY](https://github.com/allenai/satlas/blob/main/DataLicense)  
**Original paper:** [SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding](https://openaccess.thecvf.com/content/ICCV2023/html/Bastani_SatlasPretrain_A_Large-Scale_Dataset_for_Remote_Sensing_Image_Understanding_ICCV_2023_paper.html)

## Available checkpoints (19 models)

| Folder | Source | Backbone | Mode | Bands |
|--------|--------|----------|------|-------|
| `satlaspretrain-sentinel2-swinb-si-rgb` | Sentinel-2 | Swin-B | SI | RGB |
| `satlaspretrain-sentinel2-swinb-mi-rgb` | Sentinel-2 | Swin-B | MI | RGB |
| `satlaspretrain-sentinel2-swinb-si-ms` | Sentinel-2 | Swin-B | SI | MS (9ch) |
| `satlaspretrain-sentinel2-swinb-mi-ms` | Sentinel-2 | Swin-B | MI | MS (9ch) |
| `satlaspretrain-sentinel2-swint-si-rgb` | Sentinel-2 | Swin-T | SI | RGB |
| `satlaspretrain-sentinel2-swint-mi-rgb` | Sentinel-2 | Swin-T | MI | RGB |
| `satlaspretrain-sentinel2-swint-si-ms` | Sentinel-2 | Swin-T | SI | MS (9ch) |
| `satlaspretrain-sentinel2-swint-mi-ms` | Sentinel-2 | Swin-T | MI | MS (9ch) |
| `satlaspretrain-sentinel2-resnet50-si-rgb` | Sentinel-2 | ResNet50 | SI | RGB |
| `satlaspretrain-sentinel2-resnet50-mi-rgb` | Sentinel-2 | ResNet50 | MI | RGB |
| `satlaspretrain-sentinel2-resnet50-mi-ms` | Sentinel-2 | ResNet50 | MI | MS (9ch) |
| `satlaspretrain-sentinel2-resnet152-si-rgb` | Sentinel-2 | ResNet152 | SI | RGB |
| `satlaspretrain-sentinel2-resnet152-si-ms` | Sentinel-2 | ResNet152 | SI | MS (9ch) |
| `satlaspretrain-sentinel2-resnet152-mi-rgb` | Sentinel-2 | ResNet152 | MI | RGB |
| `satlaspretrain-sentinel2-resnet152-mi-ms` | Sentinel-2 | ResNet152 | MI | MS (9ch) |
| `satlaspretrain-landsat-swinb-si` | Landsat 8/9 | Swin-B | SI | All (11ch) |
| `satlaspretrain-landsat-swinb-mi` | Landsat 8/9 | Swin-B | MI | All (11ch) |
| `satlaspretrain-aerial-swinb-si` | Aerial | Swin-B | SI | RGB |
| `satlaspretrain-aerial-swinb-mi` | Aerial | Swin-B | MI | RGB |

## Usage

Processors default to **`do_resize: false`**. Pass tensors or arrays at native resolution; sensor-specific normalization is still applied.

```python
from transformers import pipeline
import torch

model_dir = "satlaspretrain-sentinel2-swinb-si-rgb"
pipe = pipeline(
    task="satlaspretrain-feature-extraction",
    model=model_dir,
    trust_remote_code=True,
)

# Sentinel-2 RGB at native size, values in [0, 1]
x = torch.rand(1, 3, 512, 512)
features = pipe(x, pool=True, return_tensors=True)
print(features.shape)

# Dense feature map
tokens = pipe(x, pool=False, return_tensors=True)
```

Opt in to resize using the reference size in `preprocessor_config.json`:

```python
features = pipe(x, pool=True, return_tensors=True, image_processor_kwargs={"do_resize": True})
```

Standard `image-feature-extraction` also works:

```python
pipe = pipeline(
    task="image-feature-extraction",
    model=model_dir,
    trust_remote_code=True,
)
```

## Normalization

The bundled image processor applies sensor-specific normalization:

- **Sentinel-2 / aerial RGB:** divide by 255
- **Landsat:** `(x - 4000) / 16320`, clipped to [0, 1]

See [Normalization.md](https://github.com/allenai/satlas/blob/main/Normalization.md) for details.