Code Monkey home page Code Monkey logo

iodine's Issues

Double exponentiation of mask logits

I'm also trying to implement/adapt IODINE and trying to clarify some things that weren't totally clear to me from the paper. Your implementation has been very helpful with that - thanks for sharing it!

I did run into one thing that seems wrong to me. In l. 140-141 of iodine.py you do the following:

p_mask_individual = (deviation/(2.*self.var_x)).exp().prod(dim=2,keepdim=True) ## (N,K,1,H,W)
p_masks = torch.nn.functional.softmax(p_mask_individual, dim=1) ## (N,K,1,H,W)

It seems to me that this (incorrectly) applies the exponential function twice: once explicitly on the first line, and once again as part of the softmax on the second line. Is that a bug or am I missing or misunderstanding something?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.