For colab users:
- Look this first: http://preview.d2l.ai/d2l-en/master/chapter_appendix-tools-for-deep-learning/colab.html
- Follow my discussion to download all colab code: Using Google Colab
- Then follow my code:
https://github.com/StevenJokes/D2L_enread/blob/master/Ch13_CV/neural_style.ipynb
One question: I noticed that training stuck at nearly 250 epochs, then jumped to 400 epochs.
Why did it happen?
In Ver2 Chinese edition, when switch to the English version, and then if I want to switch back to Chinese version by clicking the menu on the top-right corner, it will lead me to the Ver1 Chinese edition.
This issue exists in every chapter. Please take a look.
I understand, there is only one English edition, so the menu can’t point to 2 different Chinese versions. But I guess the links should be updated to point to the latest Chinese edition, which is version 2.