原图

 convert修改尺寸指令

convert 一寸照.jpg -resize 413x579 一寸照413x579.jpg

目标图

 尺寸已调整，dpi太低了

图片高清修复

提升dpi

https://github.com/microsoft/Bringing-Old-Photos-Back-to-Life

官方安装过程参考

Installation

Clone the Synchronized-BatchNorm-PyTorch repository for

cd Face_Enhancement/models/networks/
git clone https://github.com/vacancy/Synchronized-BatchNorm-PyTorch
cp -rf Synchronized-BatchNorm-PyTorch/sync_batchnorm .
cd ../../../

cd Global/detection_models
git clone https://github.com/vacancy/Synchronized-BatchNorm-PyTorch
cp -rf Synchronized-BatchNorm-PyTorch/sync_batchnorm .
cd ../../

Download the landmark detection pretrained model

cd Face_Detection/
wget http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2
bzip2 -d shape_predictor_68_face_landmarks.dat.bz2
cd ../

Download the pretrained model, put the file Face_Enhancement/checkpoints.zip under ./Face_Enhancement, and put the file Global/checkpoints.zip under ./Global. Then unzip them respectively.

cd Face_Enhancement/
wget https://github.com/microsoft/Bringing-Old-Photos-Back-to-Life/releases/download/v1.0/face_checkpoints.zip
unzip face_checkpoints.zip
cd ../
cd Global/
wget https://github.com/microsoft/Bringing-Old-Photos-Back-to-Life/releases/download/v1.0/global_checkpoints.zip
unzip global_checkpoints.zip
cd ../

Install dependencies:

pip install -r requirements.txt

高清修复

(venv) yeqiang@yeqiang-PC:~/Downloads/ai/Bringing-Old-Photos-Back-to-Life$ python run.py --input_folder /tmp/in --output_folder /tmp/out/ --GPU 0
Running Stage 1: Overall restoration
Mapping: You are using the mapping model without global restoration.
Now you are processing 一寸照413x579.jpg
Finish Stage 1 ...


Running Stage 2: Face Detection
1
Finish Stage 2 ...


Running Stage 3: Face Enhancement
The main GPU is 
0
dataset [FaceTestDataset] of size 1 was created
The size of the latent vector size is [8,8]
Network [SPADEGenerator] was created. Total number of parameters: 92.1 million. To see the architecture, do print(network).
hi :)
Finish Stage 3 ...


Running Stage 4: Blending
Traceback (most recent call last):
  File "/home/yeqiang/Downloads/ai/Bringing-Old-Photos-Back-to-Life/Face_Detection/align_warp_back_multiple_dlib.py", line 428, in <module>
    blended = blur_blending_cv2(warped_back, blended, backward_mask)
  File "/home/yeqiang/Downloads/ai/Bringing-Old-Photos-Back-to-Life/Face_Detection/align_warp_back_multiple_dlib.py", line 219, in blur_blending_cv2
    mask *= 255.0
numpy.core._exceptions._UFuncOutputCastingError: Cannot cast ufunc 'multiply' output from dtype('float64') to dtype('uint8') with casting rule 'same_kind'
Finish Stage 4 ...


All the processing is done. Please check the results.

没有dpi属性了。。。实际效果也一般（这个项目是针对老照片高清修复的）

 

故障处理

ModuleNotFoundError: No module named '_bz2'

 安装libbz2-dev，重新编译python

sudo apt install libbz2-dev

error: implicit declaration of function ‘SSL_CTX_set_keylog_callback’; did you mean ‘SSL_CTX_set_info_callback’?

 解决，手动编译openssl-1.1.1

wget https://www.openssl.org/source/openssl-1.1.1u.tar.gz
tar -xvf openssl-1.1.1u.tar.gz
cd openssl-1.1.1u
./config --prefix=/usr/local
make -j6
sudo make install

重新编译Python

 ./configure --with-openssl=/usr/local
make -j6
sudo make install