Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

resize_layers isn't a descriptive name #2

Closed
stephenjfox opened this issue Feb 15, 2019 · 2 comments
Closed

resize_layers isn't a descriptive name #2

stephenjfox opened this issue Feb 15, 2019 · 2 comments

Comments

@stephenjfox
Copy link
Owner

stephenjfox commented Feb 15, 2019

Does it resize the current layers, or does it do the fitting?
Does the function need to be broken up?
See also issue #3

@stephenjfox
Copy link
Owner Author

See also issue #4

@stephenjfox stephenjfox mentioned this issue Feb 16, 2019
3 tasks
stephenjfox added a commit that referenced this issue Feb 17, 2019
Need a 'fit_layers', for when shrinking/pruning clips out too
  many neuron connections
stephenjfox added a commit that referenced this issue Feb 17, 2019
* Use more utilities, new abstraction

* Add layer inspectors

* Add errors and utils

* Calculate a new layer's size

Rather than having to reinstatiate layers, or some
  sub-optimal traversal of a neural architectures' nn.Modules,
  just do the math for 'in-size' and 'out-size' for a given
  layer to make the math easier.

* Clarify demo.py

* Trim down resize_layers in nn.widen module

* Complete resize_layers for #2

Need a 'fit_layers', for when shrinking/pruning clips out too
  many neuron connections
@stephenjfox
Copy link
Owner Author

The naming wasn't so much of an issue as was the lack of documentation

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant