|
import os |
|
import numpy as np |
|
from skimage import color, io |
|
|
|
import torch |
|
import torch.nn.functional as F |
|
|
|
from PIL import Image |
|
from models import ColorEncoder, ColorUNet |
|
from extractor.manga_panel_extractor import PanelExtractor |
|
|
|
os.environ["CUDA_VISIBLE_DEVICES"] = '0' |
|
|
|
def mkdirs(path): |
|
if not os.path.exists(path): |
|
os.makedirs(path) |
|
|
|
def Lab2RGB_out(img_lab): |
|
img_lab = img_lab.detach().cpu() |
|
img_l = img_lab[:,:1,:,:] |
|
img_ab = img_lab[:,1:,:,:] |
|
img_l = img_l + 50 |
|
pred_lab = torch.cat((img_l, img_ab), 1)[0,...].numpy() |
|
out = (np.clip(color.lab2rgb(pred_lab.transpose(1, 2, 0)), 0, 1)* 255).astype("uint8") |
|
return out |
|
|
|
def RGB2Lab(inputs): |
|
return color.rgb2lab(inputs) |
|
|
|
def Normalize(inputs): |
|
l = inputs[:, :, 0:1] |
|
ab = inputs[:, :, 1:3] |
|
l = l - 50 |
|
lab = np.concatenate((l, ab), 2) |
|
return lab.astype('float32') |
|
|
|
def numpy2tensor(inputs): |
|
out = torch.from_numpy(inputs.transpose(2,0,1)) |
|
return out |
|
|
|
def tensor2numpy(inputs): |
|
out = inputs[0,...].detach().cpu().numpy().transpose(1,2,0) |
|
return out |
|
|
|
def preprocessing(inputs): |
|
img_lab = Normalize(RGB2Lab(inputs)) |
|
img = np.array(inputs, 'float32') |
|
img = numpy2tensor(img) |
|
img_lab = numpy2tensor(img_lab) |
|
return img.unsqueeze(0), img_lab.unsqueeze(0) |
|
|
|
if __name__ == "__main__": |
|
device = "cuda" |
|
|
|
ckpt_path = 'experiments/Color2Manga_gray/074000_gray.pt' |
|
test_dir_path = 'test_datasets/gray_test' |
|
no_extractor = False |
|
ref_img_path = 'path_to_your_reference_image.jpg' |
|
|
|
ckpt = torch.load(ckpt_path, map_location=lambda storage, loc: storage) |
|
|
|
colorEncoder = ColorEncoder().to(device) |
|
colorEncoder.load_state_dict(ckpt["colorEncoder"]) |
|
colorEncoder.eval() |
|
|
|
colorUNet = ColorUNet().to(device) |
|
colorUNet.load_state_dict(ckpt["colorUNet"]) |
|
colorUNet.eval() |
|
|
|
img1 = Image.open(ref_img_path).convert("RGB") |
|
width, height = img1.size |
|
|
|
img1, img1_lab = preprocessing(img1) |
|
img1 = img1.to(device) |
|
img1_lab = img1_lab.to(device) |
|
|
|
while True: |
|
print(f'make sure manga images are under this path: {test_dir_path}') |
|
img_path = input("please input the name of image needed to be colorized (with file extension): ") |
|
img_path = os.path.join(test_dir_path, img_path) |
|
img_name = os.path.basename(img_path) |
|
img_name = os.path.splitext(img_name)[0] |
|
|
|
img2 = Image.open(img_path).convert("RGB") |
|
img2, img2_lab = preprocessing(img2) |
|
img2 = img2.to(device) |
|
img2_lab = img2_lab.to(device) |
|
|
|
with torch.no_grad(): |
|
img2_resize = F.interpolate(img2 / 255., size=(256, 256), mode='bilinear', recompute_scale_factor=False, align_corners=False) |
|
img1_L_resize = F.interpolate(img1_lab[:,:1,:,:] / 50., size=(256, 256), mode='bilinear', recompute_scale_factor=False, align_corners=False) |
|
|
|
color_vector = colorEncoder(img2_resize) |
|
|
|
fake_ab = colorUNet((img1_L_resize, color_vector)) |
|
fake_ab = F.interpolate(fake_ab*110, size=(height, width), mode='bilinear', recompute_scale_factor=False, align_corners=False) |
|
|
|
fake_img = torch.cat((img1_lab[:,:1,:,:], fake_ab), 1) |
|
fake_img = Lab2RGB_out(fake_img) |
|
|
|
out_folder = os.path.dirname(img_path) |
|
out_name = os.path.basename(img_path) |
|
out_name = os.path.splitext(out_name)[0] |
|
out_img_path = os.path.join(out_folder, 'color', f'{out_name}_color.png') |
|
|
|
|
|
Image.fromarray(fake_img).show() |
|
|
|
folder_path = os.path.join(out_folder, 'color') |
|
if not os.path.exists(folder_path): |
|
os.mkdir(folder_path) |
|
io.imsave(out_img_path, fake_img) |
|
|
