Release 0.1.0/sparsify 2019 02 18 #11
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
PyTorch's boolean comparison crap isn't useful and makes it a pain to test exact tensor values. * Will resume later
It's a painfully simple function that has worked every time I've used it. - No it doesn't handle every edge case + Yes, it gets the job done and can be packaged for the general case
It was as easy as I wanted it to be.
* The complexity is how to handle a given nested layer
+ Those will get implemented with a given feature
- Need to program feature detection
TODO:
+ Implement the resizing on a layer-by-layer case, to
make the shrinking a bit different
+ Instead of applying the data transformation uniformly,
each layer gets
+ Those factors will be computed as 1 - percent_waste(layer)
> The thought is that channel depth doesn't change the output dimensions for CNNs, and that's attribute we're concerned with in the convulotional case... * Linear layers only have two dimensions, so it's a huge deal there. * RNNs do linear things over 'timesteps', so it's a big deal there. * Residual/identity/skip-connections in CNNs need this. > __It's decided__. The attribute stays
|
This PR completes #4 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What kind of change does this PR introduce? (Bug fix, feature, docs update, ...)
Prove that
sparsifydoes what it should do, and that there's a way to prune for the rest of the implementation.What is the current behavior? (You can also link to an open issue here)
Nothing of the sort.
What is the new behavior (if this is a feature change)?
Uniform shrinking of the network is actually trivial. Shrinking based on sparsity is much more troublesome, but also not technically infeasible.
Does this PR introduce a breaking change? (What changes might users need to make in their application due to this PR?)
no