Added support for instance weights in dagnn.Loss#1112
Open
Nicholas-Schaub wants to merge 6 commits intovlfeat:masterfrom
Nicholas-Schaub:LossWeights
Open
Added support for instance weights in dagnn.Loss#1112Nicholas-Schaub wants to merge 6 commits intovlfeat:masterfrom Nicholas-Schaub:LossWeights
Nicholas-Schaub wants to merge 6 commits intovlfeat:masterfrom
Nicholas-Schaub:LossWeights
Conversation
Merge with base
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
With the current implementation of dagnn.Loss, it isn't possible to include pass image specific weights to a loss function. The changes in this pull request permit allow a Loss node to receive a third input that contains a set of weights. This addition does not interfere with the current implementation of dagnn.Loss.
A brief example of how to use this with the mnist data set would be to create a DAG Loss node with inputs {'prediction','labels','weights'}. A get_batch function should then return three values: 'inputs', 'labels', and 'weights', where the size of the labels matrix should be the same size as the weights matrix (which would be 1x1x1xSubBatchSize for the mnist example).