Spaces:
Runtime error
Runtime error
File size: 5,758 Bytes
f2dbf59 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 |
import os
import warnings
import cv2
import numpy as np
import torch
import torch.nn as nn
from einops import rearrange
from PIL import Image
from common import HWC3, resize_image_with_pad, common_input_validate, custom_hf_download
norm_layer = nn.InstanceNorm2d
class ResidualBlock(nn.Module):
def __init__(self, in_features):
super(ResidualBlock, self).__init__()
conv_block = [ nn.ReflectionPad2d(1),
nn.Conv2d(in_features, in_features, 3),
norm_layer(in_features),
nn.ReLU(inplace=True),
nn.ReflectionPad2d(1),
nn.Conv2d(in_features, in_features, 3),
norm_layer(in_features)
]
self.conv_block = nn.Sequential(*conv_block)
def forward(self, x):
return x + self.conv_block(x)
class Generator(nn.Module):
def __init__(self, input_nc, output_nc, n_residual_blocks=9, sigmoid=True):
super(Generator, self).__init__()
# Initial convolution block
model0 = [ nn.ReflectionPad2d(3),
nn.Conv2d(input_nc, 64, 7),
norm_layer(64),
nn.ReLU(inplace=True) ]
self.model0 = nn.Sequential(*model0)
# Downsampling
model1 = []
in_features = 64
out_features = in_features*2
for _ in range(2):
model1 += [ nn.Conv2d(in_features, out_features, 3, stride=2, padding=1),
norm_layer(out_features),
nn.ReLU(inplace=True) ]
in_features = out_features
out_features = in_features*2
self.model1 = nn.Sequential(*model1)
model2 = []
# Residual blocks
for _ in range(n_residual_blocks):
model2 += [ResidualBlock(in_features)]
self.model2 = nn.Sequential(*model2)
# Upsampling
model3 = []
out_features = in_features//2
for _ in range(2):
model3 += [ nn.ConvTranspose2d(in_features, out_features, 3, stride=2, padding=1, output_padding=1),
norm_layer(out_features),
nn.ReLU(inplace=True) ]
in_features = out_features
out_features = in_features//2
self.model3 = nn.Sequential(*model3)
# Output layer
model4 = [ nn.ReflectionPad2d(3),
nn.Conv2d(64, output_nc, 7)]
if sigmoid:
model4 += [nn.Sigmoid()]
self.model4 = nn.Sequential(*model4)
def forward(self, x, cond=None):
out = self.model0(x)
out = self.model1(out)
out = self.model2(out)
out = self.model3(out)
out = self.model4(out)
return out
HF_MODEL_NAME = "lllyasviel/Annotators"
class LineartDetector:
def __init__(self, model, coarse_model):
self.model = model
self.model_coarse = coarse_model
self.device = "cpu"
@classmethod
def from_pretrained(cls, pretrained_model_or_path=HF_MODEL_NAME, filename="sk_model.pth", coarse_filename="sk_model2.pth"):
model_path = custom_hf_download(pretrained_model_or_path, filename)
coarse_model_path = custom_hf_download(pretrained_model_or_path, coarse_filename)
model = Generator(3, 1, 3)
model.load_state_dict(torch.load(model_path, map_location=torch.device('cpu')))
model.eval()
coarse_model = Generator(3, 1, 3)
coarse_model.load_state_dict(torch.load(coarse_model_path, map_location=torch.device('cpu')))
coarse_model.eval()
return cls(model, coarse_model)
def to(self, device):
self.model.to(device)
self.model_coarse.to(device)
self.device = device
return self
def __call__(self, input_image, coarse=False, detect_resolution=512, output_type="pil", upscale_method="INTER_CUBIC", **kwargs):
input_image, output_type = common_input_validate(input_image, output_type, **kwargs)
detected_map, remove_pad = resize_image_with_pad(input_image, detect_resolution, upscale_method)
model = self.model_coarse if coarse else self.model
assert detected_map.ndim == 3
with torch.no_grad():
image = torch.from_numpy(detected_map).float().to(self.device)
image = image / 255.0
image = rearrange(image, 'h w c -> 1 c h w')
line = model(image)[0][0]
line = line.cpu().numpy()
line = (line * 255.0).clip(0, 255).astype(np.uint8)
detected_map = HWC3(line)
detected_map = remove_pad(255 - detected_map)
if output_type == "pil":
detected_map = Image.fromarray(detected_map)
return detected_map
class LineartStandardDetector:
def __call__(self, input_image=None, guassian_sigma=6.0, intensity_threshold=8, detect_resolution=512, output_type=None, upscale_method="INTER_CUBIC", **kwargs):
input_image, output_type = common_input_validate(input_image, output_type, **kwargs)
input_image, remove_pad = resize_image_with_pad(input_image, detect_resolution, upscale_method)
x = input_image.astype(np.float32)
g = cv2.GaussianBlur(x, (0, 0), guassian_sigma)
intensity = np.min(g - x, axis=2).clip(0, 255)
intensity /= max(16, np.median(intensity[intensity > intensity_threshold]))
intensity *= 127
detected_map = intensity.clip(0, 255).astype(np.uint8)
detected_map = HWC3(remove_pad(detected_map))
if output_type == "pil":
detected_map = Image.fromarray(detected_map)
return detected_map |