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.

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

---

The model categorizes images into 2 classes:

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

---

Install dependencies

!pip install -q transformers torch pillow gradio

---

Inference Code

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.