File size: 8,845 Bytes
9842c28 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 |
import argparse
import cv2
import glob
import os
from basicsr.archs.rrdbnet_arch import RRDBNet
from basicsr.utils.download_util import load_file_from_url
from realesrgan import RealESRGANer
from realesrgan.archs.srvgg_arch import SRVGGNetCompact
def main():
"""Inference demo for Real-ESRGAN."""
parser = argparse.ArgumentParser()
parser.add_argument(
"-i", "--input", type=str, default="inputs", help="Input image or folder"
)
parser.add_argument(
"-n",
"--model_name",
type=str,
default="RealESRGAN_x4plus",
help=(
"Model names: RealESRGAN_x4plus | RealESRNet_x4plus | RealESRGAN_x4plus_anime_6B | RealESRGAN_x2plus | "
"realesr-animevideov3 | realesr-general-x4v3"
),
)
parser.add_argument(
"-o", "--output", type=str, default="results", help="Output folder"
)
parser.add_argument(
"-dn",
"--denoise_strength",
type=float,
default=0.5,
help=(
"Denoise strength. 0 for weak denoise (keep noise), 1 for strong denoise ability. "
"Only used for the realesr-general-x4v3 model"
),
)
parser.add_argument(
"-s",
"--outscale",
type=float,
default=4,
help="The final upsampling scale of the image",
)
parser.add_argument(
"--model_path",
type=str,
default=None,
help="[Option] Model path. Usually, you do not need to specify it",
)
parser.add_argument(
"--suffix", type=str, default="out", help="Suffix of the restored image"
)
parser.add_argument(
"-t",
"--tile",
type=int,
default=0,
help="Tile size, 0 for no tile during testing",
)
parser.add_argument("--tile_pad", type=int, default=10, help="Tile padding")
parser.add_argument(
"--pre_pad", type=int, default=0, help="Pre padding size at each border"
)
parser.add_argument(
"--face_enhance", action="store_true", help="Use GFPGAN to enhance face"
)
parser.add_argument(
"--fp32",
action="store_true",
help="Use fp32 precision during inference. Default: fp16 (half precision).",
)
parser.add_argument(
"--alpha_upsampler",
type=str,
default="realesrgan",
help="The upsampler for the alpha channels. Options: realesrgan | bicubic",
)
parser.add_argument(
"--ext",
type=str,
default="auto",
help="Image extension. Options: auto | jpg | png, auto means using the same extension as inputs",
)
parser.add_argument(
"-g",
"--gpu-id",
type=int,
default=None,
help="gpu device to use (default=None) can be 0,1,2 for multi-gpu",
)
args = parser.parse_args()
# determine models according to model names
args.model_name = args.model_name.split(".")[0]
if args.model_name == "RealESRGAN_x4plus": # x4 RRDBNet model
model = RRDBNet(
num_in_ch=3,
num_out_ch=3,
num_feat=64,
num_block=23,
num_grow_ch=32,
scale=4,
)
netscale = 4
file_url = [
"https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.0/RealESRGAN_x4plus.pth"
]
elif args.model_name == "RealESRNet_x4plus": # x4 RRDBNet model
model = RRDBNet(
num_in_ch=3,
num_out_ch=3,
num_feat=64,
num_block=23,
num_grow_ch=32,
scale=4,
)
netscale = 4
file_url = [
"https://github.com/xinntao/Real-ESRGAN/releases/download/v0.1.1/RealESRNet_x4plus.pth"
]
elif (
args.model_name == "RealESRGAN_x4plus_anime_6B"
): # x4 RRDBNet model with 6 blocks
model = RRDBNet(
num_in_ch=3, num_out_ch=3, num_feat=64, num_block=6, num_grow_ch=32, scale=4
)
netscale = 4
file_url = [
"https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.2.4/RealESRGAN_x4plus_anime_6B.pth"
]
elif args.model_name == "RealESRGAN_x2plus": # x2 RRDBNet model
model = RRDBNet(
num_in_ch=3,
num_out_ch=3,
num_feat=64,
num_block=23,
num_grow_ch=32,
scale=2,
)
netscale = 2
file_url = [
"https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.1/RealESRGAN_x2plus.pth"
]
elif args.model_name == "realesr-animevideov3": # x4 VGG-style model (XS size)
model = SRVGGNetCompact(
num_in_ch=3,
num_out_ch=3,
num_feat=64,
num_conv=16,
upscale=4,
act_type="prelu",
)
netscale = 4
file_url = [
"https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth"
]
elif args.model_name == "realesr-general-x4v3": # x4 VGG-style model (S size)
model = SRVGGNetCompact(
num_in_ch=3,
num_out_ch=3,
num_feat=64,
num_conv=32,
upscale=4,
act_type="prelu",
)
netscale = 4
file_url = [
"https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-wdn-x4v3.pth",
"https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-general-x4v3.pth",
]
# determine model paths
if args.model_path is not None:
model_path = args.model_path
else:
model_path = os.path.join("weights", args.model_name + ".pth")
if not os.path.isfile(model_path):
ROOT_DIR = os.path.dirname(os.path.abspath(__file__))
for url in file_url:
# model_path will be updated
model_path = load_file_from_url(
url=url,
model_dir=os.path.join(ROOT_DIR, "weights"),
progress=True,
file_name=None,
)
# use dni to control the denoise strength
dni_weight = None
if args.model_name == "realesr-general-x4v3" and args.denoise_strength != 1:
wdn_model_path = model_path.replace(
"realesr-general-x4v3", "realesr-general-wdn-x4v3"
)
model_path = [model_path, wdn_model_path]
dni_weight = [args.denoise_strength, 1 - args.denoise_strength]
# restorer
upsampler = RealESRGANer(
scale=netscale,
model_path=model_path,
dni_weight=dni_weight,
model=model,
tile=args.tile,
tile_pad=args.tile_pad,
pre_pad=args.pre_pad,
half=not args.fp32,
gpu_id=args.gpu_id,
)
if args.face_enhance: # Use GFPGAN for face enhancement
from gfpgan import GFPGANer
face_enhancer = GFPGANer(
model_path="https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth",
upscale=args.outscale,
arch="clean",
channel_multiplier=2,
bg_upsampler=upsampler,
)
os.makedirs(args.output, exist_ok=True)
if os.path.isfile(args.input):
paths = [args.input]
else:
paths = sorted(glob.glob(os.path.join(args.input, "*")))
for idx, path in enumerate(paths):
imgname, extension = os.path.splitext(os.path.basename(path))
print("Testing", idx, imgname)
img = cv2.imread(path, cv2.IMREAD_UNCHANGED)
if len(img.shape) == 3 and img.shape[2] == 4:
img_mode = "RGBA"
else:
img_mode = None
try:
if args.face_enhance:
_, _, output = face_enhancer.enhance(
img, has_aligned=False, only_center_face=False, paste_back=True
)
else:
output, _ = upsampler.enhance(img, outscale=args.outscale)
except RuntimeError as error:
print("Error", error)
print(
"If you encounter CUDA out of memory, try to set --tile with a smaller number."
)
else:
if args.ext == "auto":
extension = extension[1:]
else:
extension = args.ext
if img_mode == "RGBA": # RGBA images should be saved in png format
extension = "png"
if args.suffix == "":
save_path = os.path.join(args.output, f"{imgname}.{extension}")
else:
save_path = os.path.join(
args.output, f"{imgname}_{args.suffix}.{extension}"
)
cv2.imwrite(save_path, output)
if __name__ == "__main__":
main()
|