#超分辨率重建
import os
import cv2
import gradio as gr
import torch
from basicsr.archs.srvgg_arch import SRVGGNetCompact
from gfpgan.utils import GFPGANer
from realesrgan.utils import RealESRGANer


# background enhancer with RealESRGAN
model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
model_path = 'realesr-general-x4v3.pth'
half = True if torch.cuda.is_available() else False
upsampler = RealESRGANer(scale=4, model_path=model_path, model=model, tile=0, tile_pad=10, pre_pad=0, half=half)

# Use GFPGAN for face enhancement
face_enhancer_v3 = GFPGANer(
    model_path='GFPGANv1.3.pth', upscale=2, arch='clean', channel_multiplier=2, bg_upsampler=upsampler)

os.makedirs('output', exist_ok=True)


def inference(img):
    scale = 2
    try:
        img = cv2.imread(img, cv2.IMREAD_UNCHANGED)
        if len(img.shape) == 3 and img.shape[2] == 4:
            img_mode = 'RGBA'
        else:
            img_mode = None

        h, w = img.shape[0:2]
        if h < 300:
            img = cv2.resize(img, (w * 2, h * 2), interpolation=cv2.INTER_LANCZOS4)

        face_enhancer = face_enhancer_v3
        
        try:
            _, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True)
        except RuntimeError as error:
            print('Error', error)
        else:
            extension = 'png'

        try:
            if scale != 2:
                interpolation = cv2.INTER_AREA if scale < 2 else cv2.INTER_LANCZOS4
                h, w = img.shape[0:2]
                output = cv2.resize(output, (int(w * scale / 2), int(h * scale / 2)), interpolation=interpolation)
        except Exception as error:
            print('wrong scale input.', error)
        if img_mode == 'RGBA':  # RGBA images should be saved in png format
            extension = 'png'
        else:
            extension = 'jpg'
        save_path = f'output/out.{extension}'
        cv2.imwrite(save_path, output)

        output = cv2.cvtColor(output, cv2.COLOR_BGR2RGB)
        return output
    except Exception as error:
        print('global exception', error)
        return None


demo = gr.Interface(
            inference,
            gr.inputs.Image(type="filepath"),
            gr.Image(),
            title = "图像超分辨率重建",
	    allow_flagging="never",
            examples = ['1.jpg', '2.jpg', '4.jpg'])


if __name__ == '__main__':
    demo.queue().launch(server_name = "0.0.0.0", server_port = 7004, max_threads=40, show_error=True)