---
license: mit
tags:
- image-classification
- remote-sensing
- resnet
- pytorch
- transformers
---

# RSP-ResNet-50

ResNet-50 based model for remote sensing scene classification (51 classes).

## Usage

```python
from transformers import AutoModelForImageClassification
import torch

# Load model
model = AutoModelForImageClassification.from_pretrained(
    "BiliSakura/RSP-ResNet-50",
    trust_remote_code=True
)

# Inference
model.eval()
input_image = torch.randn(1, 3, 224, 224)  # (batch, channels, height, width)

with torch.no_grad():
    outputs = model(pixel_values=input_image)
    logits = outputs.logits  # Shape: (1, 51)
    predicted_class = logits.argmax(dim=-1).item()
```

## Model Details

- **Architecture:** ResNet-50
- **Input size:** 224×224×3
- **Number of classes:** 51
- **Parameters:** ~23.6M

## Citation

If you use this model, please cite the original RSP paper:

```bibtex
@ARTICLE{rsp,
  author={Wang, Di and Zhang, Jing and Du, Bo and Xia, Gui-Song and Tao, Dacheng},
  journal={IEEE Transactions on Geoscience and Remote Sensing}, 
  title={An Empirical Study of Remote Sensing Pretraining}, 
  year={2023},
  volume={61},
  number={},
  pages={1-20},
  doi={10.1109/TGRS.2022.3176603}
}
```

**Original Repository:** [ViTAE-Transformer/RSP](https://github.com/ViTAE-Transformer/RSP)