README.md

---
license: apache-2.0
datasets:
- prithivMLmods/BnW-vs-Colored-10K
language:
- en
base_model:
- google/siglip2-so400m-patch16-512
pipeline_tag: image-classification
library_name: transformers
tags:
- B&W
- Colored
- art
- SigLIP2
---

![ChatGPT Image Apr 24, 2025, 09_44_31 AM.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/l-C5O9g4CNLdVyWnRn-UG.png)

# **BnW-vs-Colored-Detection**

> **BnW-vs-Colored-Detection** is an image classification vision-language encoder model fine-tuned from **google/siglip2-base-patch16-224** for a single-label classification task. It is designed to distinguish between black & white and colored images using the **SiglipForImageClassification** architecture.

```py
Classification Report:
              precision    recall  f1-score   support

       B & W     0.9982    0.9996    0.9989      5000
     Colored     0.9996    0.9982    0.9989      5000

    accuracy                         0.9989     10000
   macro avg     0.9989    0.9989    0.9989     10000
weighted avg     0.9989    0.9989    0.9989     10000
```

![download.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/1ylOG64XFJgD1uvlTaehx.png)

---

The model categorizes images into 2 classes:

```
    Class 0: "B & W"
    Class 1: "Colored"
```

---

## **Install dependencies**

```python
!pip install -q transformers torch pillow gradio
```

---

## **Inference Code**

```python
import gradio as gr
from transformers import AutoImageProcessor, SiglipForImageClassification
from PIL import Image
import torch

# Load model and processor
model_name = "prithivMLmods/BnW-vs-Colored-Detection"  # Updated model name
model = SiglipForImageClassification.from_pretrained(model_name)
processor = AutoImageProcessor.from_pretrained(model_name)

def classify_bw_colored(image):
    """Predicts if an image is Black & White or Colored."""
    image = Image.fromarray(image).convert("RGB")
    inputs = processor(images=image, return_tensors="pt")
    
    with torch.no_grad():
        outputs = model(**inputs)
        logits = outputs.logits
        probs = torch.nn.functional.softmax(logits, dim=1).squeeze().tolist()
    
    labels = {
        "0": "B & W", "1": "Colored"
    }
    predictions = {labels[str(i)]: round(probs[i], 3) for i in range(len(probs))}
    
    return predictions

# Create Gradio interface
iface = gr.Interface(
    fn=classify_bw_colored,
    inputs=gr.Image(type="numpy"),
    outputs=gr.Label(label="Prediction Scores"),
    title="BnW vs Colored Detection",
    description="Upload an image to detect if it is Black & White or Colored."
)

if __name__ == "__main__":
    iface.launch()
```

---

## **Intended Use:**

The **BnW-vs-Colored-Detection** model is designed to classify images by color mode. Potential use cases include:

- **Archive Organization:** Separate historical B&W images from modern colored ones.
- **Data Filtering:** Preprocess image datasets by removing or labeling specific types.
- **Digital Restoration:** Assist in determining candidates for colorization.
- **Search & Categorization:** Enable efficient tagging and filtering in image libraries.