Adding AffineInputTransform
#1461
Closed
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
facebook-github-bot
added
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D40043491 |
Codecov Report
@@ Coverage Diff @@
## main #1461 +/- ##
=========================================
Coverage 100.00% 100.00%
=========================================
Files 134 134
Lines 12384 12384
=========================================
Hits 12384 12384
📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more |
Summary: Pull Request resolved: pytorch#1461 This diff adds `AffineInputTransform`, which applies `(x-b)/a` to an input `x`. Since this generalizes both `Normalize` and `Standardize`, this diff also makes them derived classes of the new class, leading to code sharing between the three classes. Background: For concrete strength prediction, the `log(t + 1`) transformation of the time dimension greatly improves predictive accuracy and uncertainty callibration. It further holds promise for the learning curve prediction problem. Instead of directly implementing the custom transformation, I wrote this generalized affine transformation, which can be composed with `log` to yield the desired transformation. Reviewed By: saitcakmak Differential Revision: D40043491 fbshipit-source-id: 954fd21ec70d89538d1f190395cd0832d39a2404
SebastianAment
force-pushed
the
export-D40043491
branch
from
a59caf6 to
cbe4362
Compare
|
This pull request was exported from Phabricator. Differential Revision: D40043491 |
SebastianAment
added a commit
to SebastianAment/botorch
that referenced
this pull request
Oct 31, 2022
Summary: Pull Request resolved: pytorch#1461 This diff adds `AffineInputTransform`, which applies `(x-b)/a` to an input `x`. Since this generalizes both `Normalize` and `Standardize`, this diff also makes them derived classes of the new class, leading to code sharing between the three classes. Background: For concrete strength prediction, the `log(t + 1`) transformation of the time dimension greatly improves predictive accuracy and uncertainty callibration. It further holds promise for the learning curve prediction problem. Instead of directly implementing the custom transformation, I wrote this generalized affine transformation, which can be composed with `log` to yield the desired transformation. Differential Revision: https://internalfb.com/D40043491 fbshipit-source-id: dd0b73a62b66493ac0a51e372d7e58d3c3910fc6
SebastianAment
added a commit
to SebastianAment/botorch
that referenced
this pull request
Oct 31, 2022
Summary: Pull Request resolved: pytorch#1461 This diff adds `AffineInputTransform`, which applies `(x-b)/a` to an input `x`. Since this generalizes both `Normalize` and `Standardize`, this diff also makes them derived classes of the new class, leading to code sharing between the three classes. Background: For concrete strength prediction, the `log(t + 1`) transformation of the time dimension greatly improves predictive accuracy and uncertainty callibration. It further holds promise for the learning curve prediction problem. Instead of directly implementing the custom transformation, I wrote this generalized affine transformation, which can be composed with `log` to yield the desired transformation. Differential Revision: https://internalfb.com/D40043491 fbshipit-source-id: 95f7b9c440704cf17d342b95288bcdebb4f2a51d
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.
Summary:
This diff adds
AffineInputTransform, which applies(x-b)/ato an inputx. Since this generalizes bothNormalizeandStandardize, this diff also makes them derived classes of the new class, leading to code sharing between the three classes.Background: For concrete strength prediction, the
log(t + 1) transformation of the time dimension greatly improves predictive accuracy and uncertainty callibration. It further holds promise for the learning curve prediction problem. Instead of directly implementing the custom transformation, I wrote this generalized affine transformation, which can be composed withlogto yield the desired transformation.Reviewed By: saitcakmak
Differential Revision: D40043491