app.py

"""
Batik Classifier API - CNN Model (VGG16-based)
24 batik classes from Indonesia
Stable H5 deployment version
"""

import os
import io
import json
import numpy as np
from flask import Flask, request, jsonify
from flask_cors import CORS
from PIL import Image

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import tensorflow as tf

app = Flask(__name__)
CORS(app)

model = None
class_names = None

def preprocess_image(image, target_size=(224, 224)):
    """Preprocess for VGG16-based model"""
    if image.mode != 'RGB':
        image = image.convert('RGB')
    image = image.resize(target_size, Image.Resampling.LANCZOS)
    img_array = np.array(image, dtype=np.float32) / 255.0
    return np.expand_dims(img_array, axis=0)

def load_models():
    global model, class_names
    
    try:
        model_path = "models/batik_model.h5"
        print(f"Loading model from {model_path}...")
        model = tf.keras.models.load_model(model_path, compile=False)
        print(f"Model loaded: {model.input_shape} -> {model.output_shape}")
        
        with open("models/batik_classes.json") as f:
            data = json.load(f)
            class_names = data if isinstance(data, list) else data.get("classes", [])
        print(f"Loaded {len(class_names)} classes")
        
        return True
    except Exception as e:
        print(f"Error: {e}")
        import traceback
        traceback.print_exc()
        return False

@app.route('/')
def index():
    return jsonify({
        "name": "Batik Classifier API",
        "model": "CNN (VGG16-based)",
        "classes": len(class_names) if class_names else 0,
        "input_size": "224x224",
        "status": "ready" if model and class_names else "error"
    })

@app.route('/health')
def health():
    return jsonify({
        "status": "healthy" if model else "unhealthy",
        "model_loaded": model is not None,
        "classes_loaded": class_names is not None
    })

@app.route('/classes')
def get_classes():
    if not class_names:
        return jsonify({"error": "Not loaded"}), 500
    return jsonify({"classes": class_names, "total": len(class_names)})

@app.route('/predict', methods=['POST'])
def predict():
    if not model or not class_names:
        return jsonify({"error": "Model not loaded"}), 500
    
    if 'image' not in request.files:
        return jsonify({"error": "No image"}), 400
    
    try:
        image = Image.open(io.BytesIO(request.files['image'].read()))
        processed = preprocess_image(image)
        
        preds = model.predict(processed, verbose=0)
        idx = np.argmax(preds[0])
        conf = float(preds[0][idx])
        
        top5 = np.argsort(preds[0])[-5:][::-1]
        top5_preds = [{"class": class_names[i], "confidence": float(preds[0][i])} for i in top5]
        
        return jsonify({
            "predicted_class": class_names[idx],
            "confidence": conf,
            "top5_predictions": top5_preds,
            "model": "CNN-VGG16"
        })
    except Exception as e:
        import traceback
        return jsonify({"error": str(e), "trace": traceback.format_exc()}), 500

print("="*70)
print("Loading Batik Classifier (24 classes)...")
print("="*70)

if load_models():
    print("="*70)
    print("Ready!")
    print("="*70)
else:
    print("="*70)
    print("Failed to load")
    print("="*70)

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=7860)