---
license: mit
tags:
- clip
- feature-extraction
- remote-sensing
---

# GeoRSCLIP-ViT-B-32

This model is a mirror/redistribution of the original [GeoRSCLIP](https://huggingface.co/Zilun/GeoRSCLIP) model.

## Original Repository and Links
- **Original Hugging Face Model**: [Zilun/GeoRSCLIP](https://huggingface.co/Zilun/GeoRSCLIP)
- **Official GitHub Repository**: [om-ai-lab/RS5M](https://github.com/om-ai-lab/RS5M)

## Description
GeoRSCLIP is a vision-language foundation model for remote sensing, trained on a large-scale dataset of remote sensing image-text pairs (RS5M). It is based on the CLIP architecture and is designed to handle the unique characteristics of remote sensing imagery.

## How to use

### With `transformers`

```python
from transformers import CLIPProcessor, CLIPModel
from PIL import Image
import torch

# Load model and processor
model = CLIPModel.from_pretrained("BiliSakura/GeoRSCLIP-ViT-B-32")
processor = CLIPProcessor.from_pretrained("BiliSakura/GeoRSCLIP-ViT-B-32")

# Load and process image
image = Image.open("path/to/your/image.jpg")
inputs = processor(
    text=["a photo of a building", "a photo of vegetation", "a photo of water"],
    images=image,
    return_tensors="pt",
    padding=True
)

# Get image-text similarity scores
with torch.inference_mode():
    outputs = model(**inputs)
    logits_per_image = outputs.logits_per_image
    probs = logits_per_image.softmax(dim=1)

print(f"Similarity scores: {probs}")
```

**Zero-shot image classification:**

```python
from transformers import CLIPProcessor, CLIPModel
from PIL import Image
import torch

model = CLIPModel.from_pretrained("BiliSakura/GeoRSCLIP-ViT-B-32")
processor = CLIPProcessor.from_pretrained("BiliSakura/GeoRSCLIP-ViT-B-32")

# Define candidate labels
candidate_labels = [
    "a satellite image of urban area",
    "a satellite image of forest",
    "a satellite image of agricultural land",
    "a satellite image of water body"
]

image = Image.open("path/to/your/image.jpg")
inputs = processor(
    text=candidate_labels,
    images=image,
    return_tensors="pt",
    padding=True
)

with torch.inference_mode():
    outputs = model(**inputs)
    probs = outputs.logits_per_image.softmax(dim=1)

# Get the predicted label
predicted_idx = probs.argmax().item()
print(f"Predicted label: {candidate_labels[predicted_idx]}")
print(f"Confidence: {probs[0][predicted_idx]:.4f}")
```

**Extracting individual features:**

```python
from transformers import CLIPProcessor, CLIPModel
from PIL import Image
import torch

model = CLIPModel.from_pretrained("BiliSakura/GeoRSCLIP-ViT-B-32")
processor = CLIPProcessor.from_pretrained("BiliSakura/GeoRSCLIP-ViT-B-32")

# Get image features only
image = Image.open("path/to/your/image.jpg")
image_inputs = processor(images=image, return_tensors="pt")

with torch.inference_mode():
    image_features = model.get_image_features(**image_inputs)

# Get text features only
text_inputs = processor(
    text=["a satellite image of urban area"],
    return_tensors="pt",
    padding=True,
    truncation=True
)

with torch.inference_mode():
    text_features = model.get_text_features(**text_inputs)

print(f"Image features shape: {image_features.shape}")
print(f"Text features shape: {text_features.shape}")
```

### With `diffusers`

This model's text encoder can be used with Stable Diffusion and other diffusion models:

```python
from diffusers import StableDiffusionPipeline
from transformers import CLIPTextModel, CLIPTokenizer
import torch

# Load the text encoder and tokenizer
text_encoder = CLIPTextModel.from_pretrained(
    "BiliSakura/GeoRSCLIP-ViT-B-32/diffusers",
    subfolder="text_encoder",
    torch_dtype=torch.float16
)
tokenizer = CLIPTokenizer.from_pretrained(
    "BiliSakura/GeoRSCLIP-ViT-B-32"
)

# Encode text prompt
prompt = "a satellite image of a city with buildings and roads"
text_inputs = tokenizer(
    prompt,
    padding="max_length",
    max_length=77,
    truncation=True,
    return_tensors="pt"
)

with torch.inference_mode():
    text_outputs = text_encoder(text_inputs.input_ids)
    text_embeddings = text_outputs.last_hidden_state

print(f"Text embeddings shape: {text_embeddings.shape}")
```

**Using with Stable Diffusion:**

```python
from diffusers import StableDiffusionPipeline
import torch

# Load pipeline with custom text encoder
pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    text_encoder=text_encoder,
    tokenizer=tokenizer,
    torch_dtype=torch.float16
)
pipe = pipe.to("cuda")

# Generate image
prompt = "a high-resolution satellite image of urban area"
image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5).images[0]
image.save("generated_image.png")
```

## Citation
If you use this model in your research, please cite the original work:

```bibtex
@article{zhangRS5MGeoRSCLIPLargeScale2024,
  title = {RS5M} and {GeoRSCLIP}: {A Large-Scale Vision-Language Dataset} and a {Large Vision-Language Model} for {Remote Sensing},
  shorttitle = {RS5M} and {GeoRSCLIP},
  author = {Zhang, Zilun and Zhao, Tiancheng and Guo, Yulong and Yin, Jianwei},
  year = {2024},
  journal = {TGRS},
  volume = {62},
  pages = {1--23},
  issn = {1558-0644},
  doi = {10.1109/TGRS.2024.3449154},
  urldate = {2024-12-15},
  keywords = {Computational modeling,Data models,Domain VLM (DVLM),general VLM (GVLM),image-text paired dataset,Location awareness,parameter efficient tuning,Remote sensing,remote sensing (RS),RS cross-modal text-image retrieval (RSCTIR),semantic localization (SeLo),Semantics,Tuning,vision-language model (VLM),Visualization,zero-shot classification (ZSC)}
}
```