app.py

import gradio as gr
from dotenv import load_dotenv
from roboflow import Roboflow
import tempfile
import os
import requests
import cv2
import numpy as np
import subprocess

# ========== Load Environment Variables ==========
load_dotenv()

# Roboflow Config
rf_api_key = os.getenv("ROBOFLOW_API_KEY")
workspace = os.getenv("ROBOFLOW_WORKSPACE")
project_name = os.getenv("ROBOFLOW_PROJECT")
model_version = int(os.getenv("ROBOFLOW_MODEL_VERSION"))

# CountGD Config
COUNTGD_API_KEY = os.getenv("COUNTGD_API_KEY")

# Inisialisasi YOLO Model dari Roboflow
rf = Roboflow(api_key=rf_api_key)
project = rf.workspace(workspace).project(project_name)
yolo_model = project.version(model_version).model

# ========== Fungsi untuk Menghitung IoU ==========
def iou(boxA, boxB):
    xA = max(boxA[0], boxB[0])
    yA = max(boxA[1], boxB[1])
    xB = min(boxA[2], boxB[2])
    yB = min(boxA[3], boxB[3])

    interArea = max(0, xB - xA) * max(0, yB - yA)
    boxAArea = (boxA[2] - boxA[0]) * (boxA[3] - boxA[1])
    boxBArea = (boxB[2] - boxB[0]) * (boxB[3] - boxB[1])

    return interArea / float(boxAArea + boxBArea - interArea) if (boxAArea + boxBArea - interArea) > 0 else 0

# ========== Fungsi Deteksi Kombinasi ==========
def detect_combined(image):
    with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as temp_file:
        image.save(temp_file, format="JPEG")
        temp_path = temp_file.name

    try:
        # YOLO Detection (Produk Nestlé)
        yolo_pred = yolo_model.predict(temp_path, confidence=50, overlap=80).json()
        nestle_class_count = {}
        nestle_boxes = []  # (x_center, y_center, width, height)
        for pred in yolo_pred['predictions']:
            class_name = pred['class']
            nestle_class_count[class_name] = nestle_class_count.get(class_name, 0) + 1
            nestle_boxes.append((pred['x'], pred['y'], pred['width'], pred['height']))

        total_nestle = sum(nestle_class_count.values())

        # CountGD Detection (Produk Kompetitor)
        url = "https://api.landing.ai/v1/tools/text-to-object-detection"
        competitor_class_count = {}
        competitor_boxes = []
        COUNTGD_PROMPTS = ["cans", "bottle", "mixed box"]
        headers = {"Authorization": f"Basic {COUNTGD_API_KEY}"}

        for prompt in COUNTGD_PROMPTS:
            with open(temp_path, "rb") as f:
                files = {"image": f}
                data = {"prompts": [prompt], "model": "countgd"}
                response = requests.post(url, files=files, data=data, headers=headers)
            result = response.json()

            if 'data' in result and result['data']:
                detections = result['data'][0]
                detections_sorted = sorted(detections, key=lambda obj: obj.get('confidence', 0), reverse=True)

                for obj in detections_sorted:
                    if 'bounding_box' in obj:
                        x1, y1, x2, y2 = obj['bounding_box']
                        countgd_box = (x1, y1, x2, y2)

                        # Hapus duplikasi dengan deteksi YOLO
                        if any(iou(countgd_box, yolo_box) > 0.3 for yolo_box in nestle_boxes):
                            continue

                        # Hapus duplikasi antar deteksi CountGD
                        if any(iou(countgd_box, existing_box) > 0.3 for existing_box in competitor_boxes):
                            continue

                        label = obj.get('label', prompt)
                        
                        # Hapus "mixed box" jika ada "cans" atau "bottle" yang lebih spesifik
                        if label == "mixed box" and ("cans" in competitor_class_count or "bottle" in competitor_class_count):
                            continue

                        competitor_class_count[label] = competitor_class_count.get(label, 0) + 1
                        competitor_boxes.append(countgd_box)

        total_competitor = sum(competitor_class_count.values())

        # Format Output Text
        result_text = "Product Nestlé\n\n"
        for class_name, count in nestle_class_count.items():
            result_text += f"{class_name}: {count}\n"
        result_text += f"\nTotal Products Nestlé: {total_nestle}\n\n"
        
        if total_competitor:
            result_text += f"\nTotal Unclassified Products: {total_competitor}\n"
        else:
            result_text += "No Unclassified Products detected\n"

        # Visualisasi Bounding Box
        img = cv2.imread(temp_path)
        for pred in yolo_pred['predictions']:
            x, y, w, h = pred['x'], pred['y'], pred['width'], pred['height']
            pt1 = (int(x - w/2), int(y - h/2))
            pt2 = (int(x + w/2), int(y + h/2))
            cv2.rectangle(img, pt1, pt2, (0, 255, 0), 2)
            cv2.putText(img, pred['class'], (pt1[0], pt1[1]-10), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0,255,0), 3)

        for box in competitor_boxes:
            x1, y1, x2, y2 = box
            cv2.rectangle(img, (int(x1), int(y1)), (int(x2), int(y2)), (0, 0, 255), 2)
            cv2.putText(img, "unclassified", (int(x1), int(y1)-10), cv2.FONT_HERSHEY_SIMPLEX, 1.0, (0,0,255), 3)

        output_path = "/tmp/combined_output.jpg"
        cv2.imwrite(output_path, img)
        return output_path, result_text

    except Exception as e:
        return temp_path, f"Error: {str(e)}"

    finally:
        if os.path.exists(temp_path):
            os.remove(temp_path)

# ========== Gradio Interface ==========
with gr.Blocks(theme=gr.themes.Base(primary_hue="teal", secondary_hue="teal", neutral_hue="slate")) as iface:
    gr.Markdown("""<div style="text-align: center;"><h1>NESTLE - STOCK COUNTING</h1></div>""")
    
    with gr.Row():
        with gr.Column():
            input_image = gr.Image(type="pil", label="Input Image")
            detect_image_button = gr.Button("Detect Image")
            output_image = gr.Image(label="Detect Object")
            output_text = gr.Textbox(label="Counting Object")
            detect_image_button.click(fn=detect_combined, inputs=input_image, outputs=[output_image, output_text])

iface.launch()