import gradio as gr

import torch
from fastai.vision.all import *
from PIL import ImageFilter, ImageEnhance, ImageDraw
from diffusers.utils import make_image_grid
from tqdm import tqdm
from diffusers import AutoPipelineForInpainting, LCMScheduler, DDIMScheduler
from diffusers import StableDiffusionControlNetInpaintPipeline, ControlNetModel
import numpy as np
from PIL import Image
from datetime import datetime

preferred_dtype = torch.float32
preferred_device = "cuda" if torch.cuda.is_available() else "cpu"

def label_func(fn): return path/"labels"/f"{fn.stem}_P{fn.suffix}"

segmodel = load_learner("camvid-512.pkl")

working_size = (512, 512)

seg_vocabulary = ['Animal', 'Archway', 'Bicyclist', 'Bridge', 'Building', 'Car',
       'CartLuggagePram', 'Child', 'Column_Pole', 'Fence', 'LaneMkgsDriv',
       'LaneMkgsNonDriv', 'Misc_Text', 'MotorcycleScooter', 'OtherMoving',
       'ParkingBlock', 'Pedestrian', 'Road', 'RoadShoulder', 'Sidewalk',
       'SignSymbol', 'Sky', 'SUVPickupTruck', 'TrafficCone',
       'TrafficLight', 'Train', 'Tree', 'Truck_Bus', 'Tunnel',
       'VegetationMisc', 'Void', 'Wall']

ban_cars_mask = np.array([0, 0, 0, 0, 0, 1,
                 0, 0, 1, 0, 1,
                 1, 1, 0, 0,
                 1, 0, 1, 1, 1,
                 1, 0, 1, 1,
                 1, 0, 0, 0, 1,
                 0, 1, 0], dtype=np.uint8)

def get_seg_mask(img):
    mask = segmodel.predict(img)[0]
    return mask

def display_mask(img, mask):
    # Convert the grayscale mask to RGB
    mask_rgb = np.stack([np.zeros_like(mask), mask, np.zeros_like(mask)], axis=-1)
    # Convert the image to PIL format
    img_pil = Image.fromarray(img)
    # Convert the mask to PIL format
    mask_pil = Image.fromarray((mask_rgb * 255).astype(np.uint8))
    # Overlay the mask on the image
    overlaid_img = Image.blend(img_pil, mask_pil, alpha=0.5)
    return overlaid_img

def redact_image(img):
    img = img.resize((256, 256))
    mask = get_seg_mask(img)
    car_mask = ban_cars_mask[mask]
    return display_mask(img, car_mask)

def flip(img):
    return np.flipud(img)


def app(img):
    start_time = datetime.now().timestamp()
    img = img.resize(working_size)
    mask = ban_cars_mask[get_seg_mask(img)]
    overlay_img = Image.fromarray(np.stack([img[:, :, 0], mask / 2, img[:,:,2]], axis=-1))
    end_time = datetime.now().timestamp()
    draw = ImageDraw.Draw(overlay_img)
    draw.text((10, 10), f"Duration: {int(1000 * (end_time - start_time))}ms", fill=(255, 255, 255))
    return overlay_img

#ideally:
#iface = gr.Interface(app, gr.Image(sources=["webcam"], streaming=True), "image", live=True)
iface = gr.Interface(app, gr.Image(), "image")
iface.launch()