---
title: README
emoji: 🌍
colorFrom: blue
colorTo: green
sdk: static
pinned: false
license: mit
short_description: Repository of Pretrained Model Weights on BigEarthNet v2.0
---
[TU Berlin](https://www.tu.berlin/) | [RSiM](https://rsim.berlin/) | [DIMA](https://www.dima.tu-berlin.de/menue/database_systems_and_information_management_group/) | [BigEarth](http://www.bigearth.eu/) | [BIFOLD](https://bifold.berlin/)
:---:|:---:|:---:|:---:|:---:
| 
| 
| 
| 
# BigEarthNet v2.0 Pretrained Model Weights
We provide weights for several different pretrained models.
The model weights for the best-performing model, based on the macro average precision score on the recommended test split, have been uploaded.
All models have been trained using: i) BigEarthNet-S1 data only (S1), ii) BigEarthNet-S2 data only (S2), or iii) both BigEarthNet-S1 and -S2 (S1+S2) together.
The following bands were used to train the models:
- For models using BigEarthNet-S1 only: Sentinel-1 bands `["VH", "VV"]`
- For models using BigEarthNet-S2 only: Sentinel-2 10m bands and 20m bands `["B02", "B03", "B04", "B08", "B05", "B06", "B07", "B11", "B12", "B8A"]`
- For models using BigEarthNet-S1 and -S2: Sentinel-2 10m bands and 20m bands and Sentinel-1 bands = `["B02", "B03", "B04", "B08", "B05", "B06", "B07", "B11", "B12", "B8A", "VH", "VV"]`
The multi-hot encoded output of the model indicates the predicted multi-label output.
The multi-hot encoded output relates to the following class labels sorted in alphabetical order:
`['Agro-forestry areas', 'Arable land', 'Beaches, dunes, sands', 'Broad-leaved forest', 'Coastal wetlands',
'Complex cultivation patterns', 'Coniferous forest', 'Industrial or commercial units', 'Inland waters',
'Inland wetlands', 'Land principally occupied by agriculture, with significant areas of natural vegetation',
'Marine waters', 'Mixed forest', 'Moors, heathland and sclerophyllous vegetation',
'Natural grassland and sparsely vegetated areas', 'Pastures', 'Permanent crops', 'Transitional woodland, shrub',
'Urban fabric']`
](https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/combined_2000_600_2020_0_wide.jpg)
## Links
| Model | Equivalent [`timm`](https://huggingface.co/docs/timm/en/index) model name | S1 only | S2 only | S1+S2 |
|:-----------------|:---------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------:|:-----------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------------------------------:|
| ConvMixer-768/32 | `convmixer_768_32` | [ConvMixer-768/32 S1](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convmixer_768_32-s1-v0.1.1) | [ConvMixer-768/32 S2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convmixer_768_32-s2-v0.1.1) | [ConvMixer-768/32 S1+S2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convmixer_768_32-all-v0.1.1) |
| ConvNext v2 Base | `convnextv2_base` | [ConvNext v2 Base S1](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convnextv2_base-s1-v0.1.1) | [ConvNext v2 Base S2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convnextv2_base-s2-v0.1.1) | [ConvNext v2 Base S1+S2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/convnextv2_base-all-v0.1.1) |
| MLP-Mixer Base | `mixer_b16_224` | [MLP-Mixer Base S1](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mixer_b16_224-s1-v0.1.1) | [MLP-Mixer Base S2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mixer_b16_224-s2-v0.1.1) | [MLP-Mixer Base S1+S2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mixer_b16_224-all-v0.1.1) |
| MobileViT-S | `mobilevit_s` | [MobileViT-S S1](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mobilevit_s-s1-v0.1.1) | [MobileViT-S S2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mobilevit_s-s2-v0.1.1) | [MobileViT-S S1+S2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/mobilevit_s-all-v0.1.1) |
| ResNet-50 | `resnet50` | [ResNet-50 S1](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet50-s1-v0.1.1) | [ResNet-50 S2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet50-s2-v0.1.1) | [ResNet-50 S1+S2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet50-all-v0.1.1) |
| ResNet-101 | `resnet101` | [ResNet-101 S1](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet101-s1-v0.1.1) | [ResNet-101 S2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet101-s2-v0.1.1) | [ResNet-101 S1+S2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/resnet101-all-v0.1.1) |
| ViT Base | `vit_base_patch8_224` | [ViT Base S1](https://huggingface.co/BIFOLD-BigEarthNetv2-0/vit_base_patch8_224-s1-v0.1.1) | [ViT Base S2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/vit_base_patch8_224-s2-v0.1.1) | [ViT Base S1+S2](https://huggingface.co/BIFOLD-BigEarthNetv2-0/vit_base_patch8_224-all-v0.1.1) |
](https://raw.githubusercontent.com/wiki/lhackel-tub/ConfigILM/static/imgs/combined_2000_600_2020_0_wide.jpg)
## Usage
To use the model, download the codes that define the model architecture from the
[official BigEarthNet v2.0 (reBEN) repository](https://git.tu-berlin.de/rsim/reben-training-scripts) and load the model with the corresponding weights
using the code below. Note that [`configilm`](https://pypi.org/project/configilm/) is a requirement to use the
code below.
```python
from reben_publication.BigEarthNetv2_0_ImageClassifier import BigEarthNetv2_0_ImageClassifier
model = BigEarthNetv2_0_ImageClassifier.from_pretrained(
"path_to/huggingface_model_folder"
)
```
e.g.
```python
from reben_publication.BigEarthNetv2_0_ImageClassifier import BigEarthNetv2_0_ImageClassifier
model = BigEarthNetv2_0_ImageClassifier.from_pretrained(
"BIFOLD-BigEarthNetv2-0/resnet50-s2-v0.1.1"
)
```
If you use any of these models in your research, please cite the following papers:
```bibtex
@article{clasen2024refinedbigearthnet,
title={reBEN: Refined BigEarthNet Dataset for Remote Sensing Image Analysis},
author={Clasen, Kai Norman and Hackel, Leonard and Burgert, Tom and Sumbul, Gencer and Demir, Beg{\"u}m and Markl, Volker},
year={2024},
eprint={2407.03653},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2407.03653},
}
```
```bibtex
@article{hackel2024configilm,
title={ConfigILM: A general purpose configurable library for combining image and language models for visual question answering},
author={Hackel, Leonard and Clasen, Kai Norman and Demir, Beg{\"u}m},
journal={SoftwareX},
volume={26},
pages={101731},
year={2024},
publisher={Elsevier}
}
```