Spaces:
Paused
Paused
| import numpy as np | |
| import torch | |
| import torch.nn as nn | |
| import functools | |
| import os | |
| import cv2 | |
| from einops import rearrange | |
| from modules import devices | |
| from annotator.annotator_path import models_path | |
| class UnetGenerator(nn.Module): | |
| """Create a Unet-based generator""" | |
| def __init__(self, input_nc, output_nc, num_downs, ngf=64, norm_layer=nn.BatchNorm2d, use_dropout=False): | |
| """Construct a Unet generator | |
| Parameters: | |
| input_nc (int) -- the number of channels in input images | |
| output_nc (int) -- the number of channels in output images | |
| num_downs (int) -- the number of downsamplings in UNet. For example, # if |num_downs| == 7, | |
| image of size 128x128 will become of size 1x1 # at the bottleneck | |
| ngf (int) -- the number of filters in the last conv layer | |
| norm_layer -- normalization layer | |
| We construct the U-Net from the innermost layer to the outermost layer. | |
| It is a recursive process. | |
| """ | |
| super(UnetGenerator, self).__init__() | |
| # construct unet structure | |
| unet_block = UnetSkipConnectionBlock(ngf * 8, ngf * 8, input_nc=None, submodule=None, norm_layer=norm_layer, innermost=True) # add the innermost layer | |
| for _ in range(num_downs - 5): # add intermediate layers with ngf * 8 filters | |
| unet_block = UnetSkipConnectionBlock(ngf * 8, ngf * 8, input_nc=None, submodule=unet_block, norm_layer=norm_layer, use_dropout=use_dropout) | |
| # gradually reduce the number of filters from ngf * 8 to ngf | |
| unet_block = UnetSkipConnectionBlock(ngf * 4, ngf * 8, input_nc=None, submodule=unet_block, norm_layer=norm_layer) | |
| unet_block = UnetSkipConnectionBlock(ngf * 2, ngf * 4, input_nc=None, submodule=unet_block, norm_layer=norm_layer) | |
| unet_block = UnetSkipConnectionBlock(ngf, ngf * 2, input_nc=None, submodule=unet_block, norm_layer=norm_layer) | |
| self.model = UnetSkipConnectionBlock(output_nc, ngf, input_nc=input_nc, submodule=unet_block, outermost=True, norm_layer=norm_layer) # add the outermost layer | |
| def forward(self, input): | |
| """Standard forward""" | |
| return self.model(input) | |
| class UnetSkipConnectionBlock(nn.Module): | |
| """Defines the Unet submodule with skip connection. | |
| X -------------------identity---------------------- | |
| |-- downsampling -- |submodule| -- upsampling --| | |
| """ | |
| def __init__(self, outer_nc, inner_nc, input_nc=None, | |
| submodule=None, outermost=False, innermost=False, norm_layer=nn.BatchNorm2d, use_dropout=False): | |
| """Construct a Unet submodule with skip connections. | |
| Parameters: | |
| outer_nc (int) -- the number of filters in the outer conv layer | |
| inner_nc (int) -- the number of filters in the inner conv layer | |
| input_nc (int) -- the number of channels in input images/features | |
| submodule (UnetSkipConnectionBlock) -- previously defined submodules | |
| outermost (bool) -- if this module is the outermost module | |
| innermost (bool) -- if this module is the innermost module | |
| norm_layer -- normalization layer | |
| use_dropout (bool) -- if use dropout layers. | |
| """ | |
| super(UnetSkipConnectionBlock, self).__init__() | |
| self.outermost = outermost | |
| if type(norm_layer) == functools.partial: | |
| use_bias = norm_layer.func == nn.InstanceNorm2d | |
| else: | |
| use_bias = norm_layer == nn.InstanceNorm2d | |
| if input_nc is None: | |
| input_nc = outer_nc | |
| downconv = nn.Conv2d(input_nc, inner_nc, kernel_size=4, | |
| stride=2, padding=1, bias=use_bias) | |
| downrelu = nn.LeakyReLU(0.2, True) | |
| downnorm = norm_layer(inner_nc) | |
| uprelu = nn.ReLU(True) | |
| upnorm = norm_layer(outer_nc) | |
| if outermost: | |
| upconv = nn.ConvTranspose2d(inner_nc * 2, outer_nc, | |
| kernel_size=4, stride=2, | |
| padding=1) | |
| down = [downconv] | |
| up = [uprelu, upconv, nn.Tanh()] | |
| model = down + [submodule] + up | |
| elif innermost: | |
| upconv = nn.ConvTranspose2d(inner_nc, outer_nc, | |
| kernel_size=4, stride=2, | |
| padding=1, bias=use_bias) | |
| down = [downrelu, downconv] | |
| up = [uprelu, upconv, upnorm] | |
| model = down + up | |
| else: | |
| upconv = nn.ConvTranspose2d(inner_nc * 2, outer_nc, | |
| kernel_size=4, stride=2, | |
| padding=1, bias=use_bias) | |
| down = [downrelu, downconv, downnorm] | |
| up = [uprelu, upconv, upnorm] | |
| if use_dropout: | |
| model = down + [submodule] + up + [nn.Dropout(0.5)] | |
| else: | |
| model = down + [submodule] + up | |
| self.model = nn.Sequential(*model) | |
| def forward(self, x): | |
| if self.outermost: | |
| return self.model(x) | |
| else: # add skip connections | |
| return torch.cat([x, self.model(x)], 1) | |
| class LineartAnimeDetector: | |
| model_dir = os.path.join(models_path, "lineart_anime") | |
| def __init__(self): | |
| self.model = None | |
| self.device = devices.get_device_for("controlnet") | |
| def load_model(self): | |
| remote_model_path = "https://huggingface.co/lllyasviel/Annotators/resolve/main/netG.pth" | |
| modelpath = os.path.join(self.model_dir, "netG.pth") | |
| if not os.path.exists(modelpath): | |
| from basicsr.utils.download_util import load_file_from_url | |
| load_file_from_url(remote_model_path, model_dir=self.model_dir) | |
| norm_layer = functools.partial(nn.InstanceNorm2d, affine=False, track_running_stats=False) | |
| net = UnetGenerator(3, 1, 8, 64, norm_layer=norm_layer, use_dropout=False) | |
| ckpt = torch.load(modelpath) | |
| for key in list(ckpt.keys()): | |
| if 'module.' in key: | |
| ckpt[key.replace('module.', '')] = ckpt[key] | |
| del ckpt[key] | |
| net.load_state_dict(ckpt) | |
| net.eval() | |
| self.model = net.to(self.device) | |
| def unload_model(self): | |
| if self.model is not None: | |
| self.model.cpu() | |
| def __call__(self, input_image): | |
| if self.model is None: | |
| self.load_model() | |
| self.model.to(self.device) | |
| H, W, C = input_image.shape | |
| Hn = 256 * int(np.ceil(float(H) / 256.0)) | |
| Wn = 256 * int(np.ceil(float(W) / 256.0)) | |
| img = cv2.resize(input_image, (Wn, Hn), interpolation=cv2.INTER_CUBIC) | |
| with torch.no_grad(): | |
| image_feed = torch.from_numpy(img).float().to(self.device) | |
| image_feed = image_feed / 127.5 - 1.0 | |
| image_feed = rearrange(image_feed, 'h w c -> 1 c h w') | |
| line = self.model(image_feed)[0, 0] * 127.5 + 127.5 | |
| line = line.cpu().numpy() | |
| line = cv2.resize(line, (W, H), interpolation=cv2.INTER_CUBIC) | |
| line = line.clip(0, 255).astype(np.uint8) | |
| return line | |