Train Notebook: Request for Improvements about fast-neural-style-pytorch HOT 3 CLOSED

from fast-neural-style-pytorch.

link directing to google colab notebook containing improved code

https://colab.research.google.com/drive/1lL81ANjjehOAudXy6CHNUHmQ9aFdJvLg#scrollTo=KhEWjKxMb0oO

from fast-neural-style-pytorch.

Hi @p-rit . Thank you improving the notebook. Some comments:

• Before moving on to downloading the models, go back to the content directory (i.e. %cd ..)
• Edit the lines downloading the helper codes and style image. The current notebook downloads the html files, instead of the raw files that the links are pointing to.
  e.g. instead of

instead of 

!wget https://github.com/iamRusty/fast-neural-style-pytorch/blob/master/transformer.py

do

!wget https://raw.githubusercontent.com/iamRusty/fast-neural-style-pytorch/master/transformer.py

• You don't need to put the cell containing itot, ttoi, etc. utils.py already has the more updated version of the helper codes. So yeah, you may delete that cell.

• Lastly, display the image after saving the sample image. You may use:

utils.show(sample_image)

Edit: One more thing, there's a typo with the import of the models from torchvision
Edit2: Also, change the content weight and style weight to 2e-6 and 50 respectively. The current settings were used for udnie, not mosaic. the mosaic style needs more weight on content :)

from fast-neural-style-pytorch.