app.py

from fastapi import FastAPI, File, UploadFile
from fastapi.middleware.cors import CORSMiddleware
from pydantic import BaseModel
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.applications.efficientnet import preprocess_input
from PIL import Image
import numpy as np
import json
import io

# Constants
IMG_SIZE = (300, 300)
MODEL_PATH = "GameNetModel.h5"
LABEL_MAP_PATH = "label_to_index.json"
GENRE_MAP_PATH = "game_genre_map.json"

# Load model & mappings
model = load_model(MODEL_PATH)

with open(LABEL_MAP_PATH) as f:
    label_to_index = json.load(f)
index_to_label = {v: k for k, v in label_to_index.items()}

with open(GENRE_MAP_PATH) as f:
    genre_map = json.load(f)

# Initialize FastAPI app
app = FastAPI()

# Enable CORS (important for frontend calls)
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)

# Response schema
class Prediction(BaseModel):
    game: str
    genre: str
    confidence: float

# Inference route
@app.post("/predict", response_model=Prediction)
async def predict(file: UploadFile = File(...)):
    try:
        image_bytes = await file.read()
        img = Image.open(io.BytesIO(image_bytes)).convert("RGB")
        img = img.resize(IMG_SIZE)
        arr = img_to_array(img)
        arr = preprocess_input(arr)
        arr = np.expand_dims(arr, axis=0)

        preds = model.predict(arr)
        class_idx = int(np.argmax(preds))
        confidence = float(np.max(preds))

        game = index_to_label[class_idx]
        genre = genre_map.get(game, "Unknown")

        return Prediction(game=game, genre=genre, confidence=confidence)

    except Exception as e:
        return {"error": str(e)}