■ Comment exécuter "TensorFlow CNN pour un transfert de style rapide" qui provient de GitHub en utilisant Google Colaboratry

Introduction GitHub:TensorFlow CNN for fast style transfer instructs how to use Tensorflow, and shows example of picture style change below.

Before image.png

After applied wave.ckpt image.png

Setup of Google Colaboratory Environment First, we need to mount on Google Drive, and upload files you want to use.

image.png

Setup Libraries Since some files are programed by its previous version, you need to uninstall new one, and install previous version so that these files can run.

!pip uninstall scipy # Uninstalling scipy-1.4.1:
!pip install scipy==1.1.0
!pip uninstall tensorflow # Uninstalling tensorflow-2.2.0rc3:
!pip install tensorflow==1.1.0

Execution command According to GitHub page, it's shown how to execute these files below. image.png

!python evaluate.py --checkpoint ./wave.ckpt \  # The style file you want to use.
  --in-path ./stata.jpg \  # The original picture you want to transform.
  --out-path ./out.jpg     # name of output file

After execution this command, "out.jpg " is generated below. image.png

Result of Another Sample

image.png

References LINK -> GitHub:TensorFlow CNN for fast style transfer -> Python Cheet Sheet (pour C ++ expérimenté) -> Transfert de style neuronal: explication de la technologie d'arrière-plan de Prisma -> Introduction à Numpy, une bibliothèque de calcul numérique en Python -> Python Basic - Pandas, Numpy

Recommended Posts

■ Comment exécuter "TensorFlow CNN pour un transfert de style rapide" qui provient de GitHub en utilisant Google Colaboratry
Comment exécuter la commande sed plusieurs fois à l'aide de l'instruction for
Comment gérer l'erreur OAuth2 lors de l'utilisation des API Google à partir de Python