Weight Initialization for MS by repeating RGB Channel Weights in the First Layer #170
Conversation
This file contains hidden or 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
ChristopherKotthoff
force-pushed
the
chris/ms-weights-initialization
branch
from
8440321 to
206dbf9
Compare
ChristopherKotthoff
force-pushed
the
chris/ms-weights-initialization
branch
2 times, most recently
from
29b904c to
5b1497f
Compare
ChristopherKotthoff
force-pushed
the
chris/ms-weights-initialization
branch
4 times, most recently
from
005ab85 to
5a17563
Compare
ChristopherKotthoff
force-pushed
the
chris/ms-weights-initialization
branch
from
5a17563 to
a6bfa2d
Compare
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Outdated suggestions cannot be applied.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.
This is a stacked pull request on Overlapping Tiles - More Training Data.
This pull request includes the following updates to improve the ResNet-stem functionality and maintain code quality:
Weight Initialization Fix
Issue Addressed: The weight initialization of the ResNet-stem was not functioning correctly.
Changes Made:
Modified the
resume_or_loadmethod to correctly handle weight loading.When loading RGB model weights for multispectral models, the weights are now repeated appropriately to ensure proper initialization. They are also divided by the times they are repeated to allow for similar output values.
The tutorial file
docs/source/tutorial.rsthas also been change to reflect the new simplified usage.