Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Changed key for SegKDLoss #1620

Merged
merged 5 commits into from
Nov 10, 2023
Merged

Changed key for SegKDLoss #1620

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
5ba3c92
Changed key for SegKDLoss, added + sign to instructions for overridin…
hakuryuu96 Nov 7, 2023
eb82158
Merge branch 'master' into bug/recipes_fix
hakuryuu96 Nov 7, 2023
e1b6878
Merge branch 'master' into bug/recipes_fix
hakuryuu96 Nov 9, 2023
2a1a188
Updated instructions for cityscapes_kd_base
hakuryuu96 Nov 9, 2023
25ab6f4
Merge branch 'master' into bug/recipes_fix
BloodAxe Nov 10, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 4 additions & 2 deletions src/super_gradients/recipes/cityscapes_kd_base.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,9 @@
# Distillation for semantic segmentation on Cityscapes dataset.
#
# Instructions:
# 0. Make sure that the data is stored in dataset_params.dataset_dir or add "dataset_params.data_dir=<PATH-TO-DATASET>" at the end of the command below (feel free to check ReadMe)
# 0. Make sure that the data is stored in dataset_params.[train/val]_dataset_params.root_dir or
# add "dataset_params.[train/val]_dataset_params.root_dir=<PATH-TO-DATASET>" at the end of the
# command below (feel free to check ReadMe)
# 1. Move to the project root (where you will find the ReadMe and src folder)
# 2. Run the command:
# DDRNet23: python -m super_gradients.train_from_kd_recipe --config-name=cityscapes_kd_base student_architecture=ddrnet_23
Expand Down Expand Up @@ -55,7 +57,7 @@ training_hyperparams:
weights: [ 1. ]
kd_loss_weights: [1., 6.]

KDLogitsLoss:
kd_loss:
_target_: super_gradients.training.losses.cwd_loss.ChannelWiseKnowledgeDistillationLoss
temperature: 3.
normalization_mode: channel_wise
Expand Down