Skip to content

Conversation

@KumoLiu
Copy link
Contributor

@KumoLiu KumoLiu commented Sep 1, 2023

Fixes #6923.

Description

Add support for BCEWithLogitsLoss for single-class.

Types of changes

  • Non-breaking change (fix or new feature that would not break existing functionality).
  • Breaking change (fix or new feature that would cause existing functionality to change).
  • New tests added to cover the changes.
  • Integration tests passed locally by running ./runtests.sh -f -u --net --coverage.
  • Quick tests passed locally by running ./runtests.sh --quick --unittests --disttests.
  • In-line docstrings updated.
  • Documentation updated, tested make html command in the docs/ folder.

Signed-off-by: KumoLiu <yunl@nvidia.com>
@KumoLiu KumoLiu requested review from Nic-Ma, ericspod and wyli September 1, 2023 03:15
KumoLiu and others added 6 commits September 1, 2023 11:25
Signed-off-by: KumoLiu <yunl@nvidia.com>
Signed-off-by: KumoLiu <yunl@nvidia.com>
Signed-off-by: KumoLiu <yunl@nvidia.com>
Signed-off-by: KumoLiu <yunl@nvidia.com>
Signed-off-by: KumoLiu <yunl@nvidia.com>
@KumoLiu KumoLiu changed the title Raise error in single-channel scenario for DiceCELoss Add support for BCEWithLogitsLoss in DiceCELoss Sep 1, 2023
Copy link
Contributor

@wyli wyli left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks, it looks good to me, for single channel prediction of a binary target, the crossentropyloss doesn't work directly

@wyli
Copy link
Contributor

wyli commented Sep 2, 2023

/build

@wyli wyli enabled auto-merge (squash) September 2, 2023 08:25
@wyli wyli merged commit 50e66fa into Project-MONAI:dev Sep 2, 2023
@KumoLiu KumoLiu deleted the DiceCELoss branch September 3, 2023 07:19
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

Successfully merging this pull request may close these issues.

DiceCELoss gets 0 CE component for binary segmentation

2 participants