FROM waringid/docker-pytorch-playground

RUN pip install gfpgan==1.3.8 realesrgan==0.3.0 facexlib==0.3.0 gradio==3.39.0
COPY detection_Resnet50_Final.pth /opt/conda/lib/python3.9/site-packages/facexlib/weights/detection_Resnet50_Final.pth

# 尺寸大一些的模型文件，可以选择使用挂载的方式
# 而不在此处直接 COPY 到容器内部
COPY GFPGANCleanv1-NoCE-C2.pth /GFPGAN.pth

COPY app.py /entrypoint.py
WORKDIR /data
RUN pip install IPython pandas
RUN sed -i -e "s/display(HTML(table))/with open('result.html', 'w') as file:\n        arch = 'clean'
  file.write(HTML(table).data)/" /opt/conda/lib/python3.9/site-packages/towhee/datacollection/mixins/display.py
CMD ["python3", "/entrypoint.py"]

docker build -t pytorch-playground-gfpgan -f Dockerfile .

docker run --rm -it -v `pwd`/model/GFPGANCleanv1-NoCE-C2.pth:/GFPGAN.pth -v `pwd`/data:/data pytorch-playground-gfpgan

import os
import cv2
import gradio as gr
import torch
from basicsr.archs.srvgg_arch import SRVGGNetCompact
from basicsr.archs.rrdbnet_arch import RRDBNet
from gfpgan.utils import GFPGANer
from realesrgan.utils import RealESRGANer

def set_realesrgan(version):
    half=True if torch.cuda.is_available() else False
    if version == 'v3':
        model = SRVGGNetCompact(num_in_ch=3, num_out_ch=3, num_feat=64, num_conv=32, upscale=4, act_type='prelu')
        return RealESRGANer(scale=4, model_path='model/realesr-general-x4v3.pth', model=model, tile=0, tile_pad=10, pre_pad=0, half=half)
    else:
        model = RRDBNet(num_in_ch=3, num_out_ch=3, num_feat=64, num_block=23, num_grow_ch=32, scale=2) channel_multiplier = 2
            model_path='model/GFPGANv1.2.pth'
        elif version == 'v1.3':
        return    arch = 'clean'
       RealESRGANer(scale=2, model_path='model/RealESRGAN_x2plus.pth', model=model, tile=400, tile_pad=10, pre_pad=0, half=half)

def set_face_enhancer(upsampler, version):
    if channel_multiplierversion == 2'RestoreFormer':
        return    GFPGANer(model_path='model/GFPGANv1.3RestoreFormer.pth', upscale=2, arch='RestoreFormer', channel_multiplier=2, bg_upsampler=upsampler)
    else:
        elifif version == 'v1.4CPU':
            arch model_path= 'clean'model/GFPGANCleanv1-NoCE-C2.pth'
        elif    channel_multiplier = 2
version == 'v1':
            arch model_path='model/GFPGANv1.4.pth'

 'original'
       return GFPGANer(model_path=model_path, upscale=2, arch=arch,   channel_multiplier=channel_multiplier, bg_upsampler=upsampler)

os.makedirs('output', exist_ok=True)

def inference(img, realesrgan_version, gfpgan_version, scale):
    if scale > 4:
 = 1
            model_path='model/GFPGANv1.pth'
        elif version == 'v1.2':
         scale = 4
 arch = 'clean'
 elif scale < 0:
        scalechannel_multiplier = 1
2
    try:
        extension = os.path.splitext(os.path.basename(str(img)))[1]model_path='model/GFPGANv1.2.pth'
        imgelif version == cv2.imread(img, cv2.IMREAD_UNCHANGED)
'v1.3':
           if len(img.shape) == 3 and img.shape[2] == 4: arch = 'clean'
            channel_multiplier = 2
            imgmodel_mode path= 'RGBA'model/GFPGANv1.3.pth'
        elif len(img.shape)version == 2:  # for gray inputs'v1.4':
            img_modearch = None'clean'
            imgchannel_multiplier = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR) 2
        else:    model_path='model/GFPGANv1.4.pth'

    return GFPGANer(model_path=model_path, upscale=2, arch=arch, channel_multiplier=channel_multiplier,    img_mode = None

        h, w = img.shape[0:2]
    bg_upsampler=upsampler)

os.makedirs('output', exist_ok=True)

def inference(img, realesrgan_version, gfpgan_version, scale):
    if hscale > 3500 or w > 3500:
4:
        scale = 4
    elif print('too large size')scale < 0:
        scale = 1

  return None, Nonetry:
        extension = os.path.splitext(os.path.basename(str(img)))[1]
        ifimg h < 300:= cv2.imread(img, cv2.IMREAD_UNCHANGED)
        if len(img.shape) == 3 and img.shape[2] == cv2.resize(img, (w * 2, h * 2), interpolation=cv2.INTER_LANCZOS4)

4:
            upsamplerimg_mode = set_realesrgan(realesrgan_version)'RGBA'
        face_enhancer = set_face_enhancer(upsampler, gfpgan_version)
elif len(img.shape) == 2:  # for gray inputs
        try:
    img_mode = None
      _, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True, weight=None  img = cv2.cvtColor(img, cv2.COLOR_GRAY2BGR)
        except RuntimeError as errorelse:
             print('Error', error)

img_mode = None

        h, w = try:img.shape[0:2]
        if h > 3500 ifor scalew !=> 23500:
            print('too large size')
   interpolation = cv2.INTER_AREA if scale < 2 else cv2.INTER_LANCZOS4
 return None, None
        
     h, w = img.shape[0:2]
    if h < 300:
            img output = cv2.resize(outputimg, (int(w * scale /2, h * 2), int(h * scale / 2)), interpolation=interpolation)interpolation=cv2.INTER_LANCZOS4)

        upsampler = set_realesrgan(realesrgan_version)
        face_enhancer = set_face_enhancer(upsampler, gfpgan_version)

        except Exception as errortry:
            print('wrong scale input.', error)
        if img_mode == 'RGBA':  # RGBA images should be saved in png format_, _, output = face_enhancer.enhance(img, has_aligned=False, only_center_face=False, paste_back=True, weight=None)
        except RuntimeError as error:
            extension = 'png'print('Error', error)

        elsetry:
            extension = 'jpg'
        save_path = f'output/out.{extension}'if scale != 2:
        cv2.imwrite(save_path, output)

        outputinterpolation = cv2.cvtColor(output, cv2.COLOR_BGR2RGB)
        return output, save_pathINTER_AREA if scale < 2 else cv2.INTER_LANCZOS4
    except Exception as error:
        print('global exception', error) h, w = img.shape[0:2]
        return None, None

description = r"""Gradio demo for <a href='https://github.com/TencentARC/GFPGAN' target='_blank'>GFPGAN: Towards Real-World Blind Face Restoration with Generative Facial Prior</a>.<br>
这个应用可以被用来修复你的**老照片**或者改善**AI生成的人脸**。<br>
你只需要上传你的图片，就可以使用它。<br>
如果你觉得这个项目帮助到了你，不妨为 <a href='https://github.com/TencentARC/GFPGAN' target='_blank'>它</a> 点个Star吧 :-D <br>
"""

radio_realesrgan_version = gr.Radio(['v3'], type="value", value='v3', label='RealESR GAN version')
radio_gfpgan_version = gr.Radio(['CPU', 'v1.2', 'v1.3', 'v1.4', 'RestoreFormer'], type="value", value='v1.4', label='version')
if os.environ.get('BASICSR_JIT') is not None:
    radio_realesrgan_version = gr.Radio(['v2', 'v3'], type="value", value='v3', label='RealESR GAN version')
    radio_gfpgan_version = gr.Radio(['CPU', 'v1', 'v1.2', 'v1.3', 'v1.4', 'RestoreFormer'], type="value", value='v1.4', label='version')

app = gr.Interface(
    inference, [ 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:
        gr.Image(type="filepath", label="Input"),
   extension = 'jpg'
   radio_realesrgan_version,
     save_path   radio_gfpgan_version,= f'output/out.{extension}'
        grcv2.Number(label="Rescaling factor", value=2),imwrite(save_path, output)

    ], [
   output =    gr.Image(type="numpy", label="Output (The whole image)"),cv2.cvtColor(output, cv2.COLOR_BGR2RGB)
        gr.File(label="Download the output image")return output, save_path
    ],
except Exception as  title="GFPGAN: 实用的人脸修复算法",error:
    description=description,
    article="<p style='text-align: center'>written by: <a href='https://wiki.waringid.me' target='_blank'></a></p>",    # examples=[['AI-generate.jpg', 'v1.4', 2], ['lincoln.jpg', 'v1.4', 2], ['Blake_Lively.jpg', 'v1.4', 2], ['10045.png', 'v1.4', 2]]
)
app.queue()
app.launch(server_name="0.0.0.0")

FROM nvcr.io/nvidia/pytorch:23.04-py3
LABEL org.opencontainers.image.authors="waringid@gmail.com"

RUN pip config set global.index-url https://mirrors.aliyun.com/pypi/simple/
RUN pip install gfpgan==1.3.8 realesrgan==0.3.0 facexlib==0.3.0 gradio==3.39.0

WORKDIR /app
COPY ./app.py ./

CMD ["python", "app

FROM waringid/docker-pytorch-playground

RUN pip install gfpgan==1.3.8 realesrgan==0.3.0 facexlib==0.3.0 gradio==3.39.0
COPY detection_Resnet50_Final.pth /opt/conda/lib/python3.9/site-packages/facexlib/weights/detection_Resnet50_Final.pth

# 尺寸大一些的模型文件，可以选择使用挂载的方式
# 而不在此处直接 COPY 到容器内部
COPY GFPGANCleanv1-NoCE-C2.pth /GFPGAN.pth

COPY app.py /entrypoint.py
WORKDIR /data
RUN pip install IPython pandas
RUN sed -i -e "s/display(HTML(table))/with open('result.html', 'w') as file:\n            file.write(HTML(table).data)/" /opt/conda/lib/python3.9/site-packages/towhee/datacollection/mixins/display.py
CMD ["python3", "/entrypoint.py"]