app.py

from fastapi import FastAPI, UploadFile, File
from transformers import AutoImageProcessor, AutoModelForImageClassification
from PIL import Image
import torch
import io
import logging

# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

app = FastAPI()

# ✅ working model on HuggingFace
MODEL_NAME = "Zodex/my-final-food-model-v29-full"

# Load the processor and model
try:
    logger.info(f"Loading model '{MODEL_NAME}'...")
    processor = AutoImageProcessor.from_pretrained(MODEL_NAME)
    model = AutoModelForImageClassification.from_pretrained(MODEL_NAME)
    model.eval()  # ✅ just to be safe
    logger.info("Model and processor loaded successfully!")
except Exception as e:
    logger.error(f"Failed to load model: {str(e)}")
    raise

@app.get("/")
async def read_root():
    return {"message": "Food Recognition API is running."}

@app.post("/predict")
async def predict_image(file: UploadFile = File(...)):
    try:
        contents = await file.read()
        image = Image.open(io.BytesIO(contents)).convert("RGB")

        # Preprocess
        inputs = processor(images=image, return_tensors="pt")

        # Get model predictions
        with torch.no_grad():
            logits = model(**inputs).logits

        probabilities = torch.nn.functional.softmax(logits, dim=-1)

        top_k = 3
        values, indices = torch.topk(logits, top_k)

        results = []
        for i in range(top_k):
            pred_index = indices[0][i].item()
            label = model.config.id2label[pred_index]
            score = float(probabilities[0][pred_index].item())
            results.append({
                "food_name": label.replace("_", " ").title(),
                "confidence": round(score, 4),
            })

        return {"success": True, "predictions": results}

    except Exception as e:
        logger.error(f"Error processing image: {str(e)}")
        return {"success": False, "error": str(e)}