Skip to content

Instantly share code, notes, and snippets.

@czotti

czotti/tiramisu.ipynb

Last active November 28, 2018 06:03
Show Gist options
  • Save czotti/b1e34c23a92e64490be83f3b8908bdbe to your computer and use it in GitHub Desktop.
Save czotti/b1e34c23a92e64490be83f3b8908bdbe to your computer and use it in GitHub Desktop.
Download ZIP
Tiramisu keras implementation
Display the source blob
Display the rendered blob
Raw
tiramisu.ipynb
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@lemairecarl
Copy link

lemairecarl commented May 18, 2017 •
edited
Loading

Nice work, thanks!

Question: At the end of dense_block(), don't x_stack and connections contain the same data? And in transition_up(), you take the list of tensors coming from connections and you concatenate them together. Couldn't you just use x_stack?

@lemairecarl
Copy link

Other question: in the "Encoded filtering" part, it looks like a dense block. It seems like you could have used dense_block() there. Am I missing something?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment