app.py

import gradio as gr
from PIL import Image
import torch
from transformers import AutoImageProcessor, AutoModelForImageClassification

# Load model
processor = AutoImageProcessor.from_pretrained("prithivMLmods/Weather-Image-Classification")
model = AutoModelForImageClassification.from_pretrained("prithivMLmods/Weather-Image-Classification")

# Inference function
def classify_weather(image_input):
    try:
        # PIL image guaranteed by Gradio
        inputs = processor(images=[image_input], return_tensors="pt")

        with torch.no_grad():
            outputs = model(**inputs)
            logits = outputs.logits.squeeze()
            probs = torch.softmax(logits, dim=-1).tolist()
            labels = [model.config.id2label[i] for i in range(len(probs))]
            return dict(zip(labels, probs))
    except Exception:
        return {"Error": 1.0}

# Gradio interface
iface = gr.Interface(
    fn=classify_weather,
    inputs=gr.Image(type="pil"),  # ✅ PIL input
    outputs=gr.Label(num_top_classes=5, label="Weather Condition"),
    title="Weather Image Classification",
    description="Upload an image to classify the weather condition (sun, rain, snow, fog, or clouds)."
)

if __name__ == "__main__":
    iface.launch(show_error=True)