95 lines
3.6 KiB
Python
95 lines
3.6 KiB
Python
import os, pathlib
|
|
import cv2
|
|
import gradio as gr
|
|
import torch
|
|
from basicsr.archs.srvgg_arch import SRVGGNetCompact
|
|
from gfpgan.utils import GFPGANer
|
|
from realesrgan.utils import RealESRGANer
|
|
os.system("hub install deoldify==1.0.1")
|
|
import paddlehub as hub
|
|
os.system("pip freeze")
|
|
|
|
|
|
# download weights
|
|
if not os.path.exists('GFPGANv1.4.pth'):
|
|
os.system("wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.4.pth -P .")
|
|
|
|
model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
|
|
model_path = 'realesr-general-x4v3.pth'
|
|
half = True if torch.cuda.is_available() else False
|
|
upsampler = RealESRGANer(scale=4, model_path=model_path, model=model, tile=0, tile_pad=10, pre_pad=0, half=half)
|
|
|
|
os.makedirs('output', exist_ok=True)
|
|
|
|
colorizer = hub.Module(name='deoldify')
|
|
render_factor=5
|
|
|
|
def colorize_image(image):
|
|
color_image = colorizer.predict(image)
|
|
return color_image
|
|
|
|
|
|
def inference(img, scale):
|
|
print(img, scale)
|
|
try:
|
|
extension = os.path.splitext(os.path.basename(str(img)))[1]
|
|
img = cv2.imread(img, cv2.IMREAD_UNCHANGED)
|
|
if len(img.shape) == 3 and img.shape[2] == 4:
|
|
img_mode = 'RGBA'
|
|
elif len(img.shape) == 2: # for gray inputs
|
|
img_mode = None
|
|
img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
|
|
else:
|
|
img_mode = None
|
|
|
|
h, w = img.shape[0:2]
|
|
if h < 300:
|
|
img = cv2.resize(img, (w * 2, h * 2), interpolation=cv2.INTER_LANCZOS4)
|
|
face_enhancer = GFPGANer(model_path='GFPGANv1.4.pth', upscale=2, arch='clean', channel_multiplier=2, bg_upsampler=upsampler)
|
|
try:
|
|
# _, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True, weight=weight)
|
|
_, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True)
|
|
except RuntimeError as error:
|
|
print('Error', error)
|
|
|
|
try:
|
|
if scale != 2:
|
|
interpolation = cv2.INTER_AREA if scale < 2 else cv2.INTER_LANCZOS4
|
|
h, w = img.shape[0:2]
|
|
output = cv2.resize(output, (int(w * scale / 2), int(h * scale / 2)), interpolation=interpolation)
|
|
except Exception as error:
|
|
print('wrong scale input.', error)
|
|
if img_mode == 'RGBA': # RGBA images should be saved in png format
|
|
extension = 'png'
|
|
else:
|
|
extension = 'jpg'
|
|
save_path = f'output/out.{extension}'
|
|
output = cv2.cvtColor(output, cv2.COLOR_BGR2RGB)
|
|
cv2.imwrite(save_path, output)
|
|
print('upsampled image!')
|
|
output_img = colorize_image(save_path)
|
|
outputim = output_img[1]
|
|
print(type(outputim))
|
|
print('colorized image!')
|
|
return pathlib.Path(outputim)
|
|
except Exception as error:
|
|
print('global exception', error)
|
|
return None, None
|
|
|
|
|
|
|
|
with gr.Blocks(css = "footer {visibility: hidden}" ) as demo:
|
|
with gr.Row():
|
|
with gr.Column():
|
|
in_image = gr.inputs.Image(type="filepath", label="Input")
|
|
factor = gr.Slider(2, 10, value=2, step = 1, label="Rescaling factor")
|
|
#gr.inputs.Number(, default=2)
|
|
btn = gr.Button("着色")
|
|
with gr.Column():
|
|
gallery = gr.Image()
|
|
#out_image = gr.outputs.Image(type="numpy", label="Output (The whole image)")
|
|
#dld = gr.outputs.File(label="Download the output image")
|
|
btn.click(fn=inference, inputs=[in_image,factor], outputs=gallery)
|
|
|
|
demo.launch(server_name="0.0.0.0", share=True)
|