# -*- coding: utf-8 -*-
"""DDColor_colab.ipynb

Automatically generated by Colaboratory.

Original file is located at
    https://colab.research.google.com/github/camenduru/DDColor-colab/blob/main/DDColor_colab.ipynb
"""

# Commented out IPython magic to ensure Python compatibility.
# %cd /content
!git clone -b dev https://github.com/camenduru/DDColor

!apt -y install -qq aria2
!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/camenduru/cv_ddcolor_image-colorization/resolve/main/pytorch_model.pt -d /content/DDColor/models -o pytorch_model.pt

!wget https://modelscope.oss-cn-beijing.aliyuncs.com/test/images/audrey_hepburn.jpg -O /content/DDColor/in.jpg
!pip install -q timm

# %cd /content/DDColor

!sed -i 's/from \.version import __gitsha__, __version__/# from \.version import __gitsha__, __version__/' /content/DDColor/basicsr/__init__.py

import argparse
import cv2
import numpy as np
import os
from tqdm import tqdm
import torch
from basicsr.archs.ddcolor_arch import DDColor
import torch.nn.functional as F

class ImageColorizationPipeline(object):

    def __init__(self, model_path, input_size=256, model_size='large'):

        self.input_size = input_size
        if torch.cuda.is_available():
            self.device = torch.device('cuda')
        else:
            self.device = torch.device('cpu')

        if model_size == 'tiny':
            self.encoder_name = 'convnext-t'
        else:
            self.encoder_name = 'convnext-l'

        self.decoder_type = "MultiScaleColorDecoder"

        if self.decoder_type == 'MultiScaleColorDecoder':
            self.model = DDColor(
                encoder_name=self.encoder_name,
                decoder_name='MultiScaleColorDecoder',
                input_size=[self.input_size, self.input_size],
                num_output_channels=2,
                last_norm='Spectral',
                do_normalize=False,
                num_queries=100,
                num_scales=3,
                dec_layers=9,
            ).to(self.device)
        else:
            self.model = DDColor(
                encoder_name=self.encoder_name,
                decoder_name='SingleColorDecoder',
                input_size=[self.input_size, self.input_size],
                num_output_channels=2,
                last_norm='Spectral',
                do_normalize=False,
                num_queries=256,
            ).to(self.device)

        self.model.load_state_dict(
            torch.load(model_path, map_location=torch.device('cpu'))['params'],
            strict=False)
        self.model.eval()

    @torch.no_grad()
    def process(self, img):
        self.height, self.width = img.shape[:2]
        # print(self.width, self.height)
        # if self.width * self.height < 100000:
        #     self.input_size = 256

        img = (img / 255.0).astype(np.float32)
        orig_l = cv2.cvtColor(img, cv2.COLOR_BGR2Lab)[:, :, :1]  # (h, w, 1)

        # resize rgb image -> lab -> get grey -> rgb
        img = cv2.resize(img, (self.input_size, self.input_size))
        img_l = cv2.cvtColor(img, cv2.COLOR_BGR2Lab)[:, :, :1]
        img_gray_lab = np.concatenate((img_l, np.zeros_like(img_l), np.zeros_like(img_l)), axis=-1)
        img_gray_rgb = cv2.cvtColor(img_gray_lab, cv2.COLOR_LAB2RGB)

        tensor_gray_rgb = torch.from_numpy(img_gray_rgb.transpose((2, 0, 1))).float().unsqueeze(0).to(self.device)
        output_ab = self.model(tensor_gray_rgb).cpu()  # (1, 2, self.height, self.width)

        # resize ab -> concat original l -> rgb
        output_ab_resize = F.interpolate(output_ab, size=(self.height, self.width))[0].float().numpy().transpose(1, 2, 0)
        output_lab = np.concatenate((orig_l, output_ab_resize), axis=-1)
        output_bgr = cv2.cvtColor(output_lab, cv2.COLOR_LAB2BGR)

        output_img = (output_bgr * 255.0).round().astype(np.uint8)

        return output_img

colorizer = ImageColorizationPipeline(model_path='/content/DDColor/models/pytorch_model.pt', input_size=512)

# helper function taken from: https://huggingface.co/blog/stable_diffusion
from PIL import Image
def image_grid(imgs, rows, cols):
    assert len(imgs) == rows*cols

    w, h = imgs[0].size
    grid = Image.new('RGB', size=(cols*w, rows*h))
    grid_w, grid_h = grid.size

    for i, img in enumerate(imgs):
        grid.paste(img, box=(i%cols*w, i//cols*h))
    return grid

image_in = cv2.imread('/content/DDColor/in.jpg')
image_out = colorizer.process(image_in)
cv2.imwrite('/content/DDColor/out.jpg', image_out)
image_in_pil = Image.fromarray(cv2.cvtColor(image_in, cv2.COLOR_BGR2RGB))
image_out_pil = Image.fromarray(cv2.cvtColor(image_out, cv2.COLOR_BGR2RGB))
images = [image_in_pil, image_out_pil]
grid = image_grid(images, rows=1, cols=2)
grid