import gradio as gr
import torch
import torch.nn as nn
import torchvision
import torch.backends.cudnn as cudnn
import torch.optim
import os
import sys
import argparse
import time
import dataloader
import model
import numpy as np
from torchvision import transforms
from PIL import Image
import glob
import time

 
def lowlight(image):
	os.environ['CUDA_VISIBLE_DEVICES']=''
	data_lowlight = Image.open(image)

 

	data_lowlight = (np.asarray(data_lowlight)/255.0)


	data_lowlight = torch.from_numpy(data_lowlight).float()
	data_lowlight = data_lowlight.permute(2,0,1)
	data_lowlight = data_lowlight.cpu().unsqueeze(0)

	DCE_net = model.enhance_net_nopool().cpu()
	DCE_net.load_state_dict(torch.load('Epoch99.pth', map_location=torch.device('cpu')))
	start = time.time()
	_,enhanced_image,_ = DCE_net(data_lowlight)

	end_time = (time.time() - start)
	print(end_time)

	torchvision.utils.save_image(enhanced_image, f'01.png')

	return '01.png'


title = "Low-Light Image Enhancement using Zero-DCE"
description = "Low-light image enhancement using Zero-DCE model. Full paper: http://openaccess.thecvf.com/content_CVPR_2020/papers/Guo_Zero-Reference_Deep_Curve_Estimation_for_Low-Light_Image_Enhancement_CVPR_2020_paper.pdf"
article = "<p style='text-align: center'><a href='http://openaccess.thecvf.com/content_CVPR_2020/papers/Guo_Zero-Reference_Deep_Curve_Estimation_for_Low-Light_Image_Enhancement_CVPR_2020_paper.pdf' target='_blank'>Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement</a> | <a href='https://github.com/Li-Chongyi/Zero-DCE' target='_blank'>Github Repo</a></p> <center><img src='https://visitor-badge.glitch.me/badge?page_id=52Hz_CMFNet_deblurring' alt='visitor badge'></center>"

examples = [['01.jpg'], ['02.jpg'], ['03.jpg'],]
gr.Interface(
    lowlight,
    [gr.inputs.Image(type="file", label="Input")],
    outputs = "image",
    title=title,
    description=description,
    article=article,
    allow_flagging=False,
    allow_screenshot=False,
    examples=examples
).launch(debug=True)