Skip to content

Fix argument name in README for create_mednext_v1 #38

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

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
Open

Fix argument name in README for create_mednext_v1 #38

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
0195c9c
inplace checks
toufiqmusah Mar 16, 2025
e111d04
Fix arg name in README for create_mednext_v1
toufiqmusah Mar 30, 2025
0800e2e
Merge pull request #1 from toufiqmusah/arg-'num_channels'-to-'num_inp…
toufiqmusah Mar 30, 2025
217fd4c
Revert "inplace checks"
toufiqmusah Mar 30, 2025
91c66d2
Merge branch 'main' of https://github.com/toufiqmusah/MedNeXt
toufiqmusah Mar 30, 2025
86e8d26
Update model_restore.py, weights_only=False
toufiqmusah May 1, 2025
13bbf26
Merge branch 'MIC-DKFZ:main' into main
toufiqmusah May 21, 2025
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
4 changes: 2 additions & 2 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,7 +111,7 @@ Utility functions have been defined for re-creating these architectures (with or
from nnunet_mednext import create_mednext_v1

model = create_mednext_v1(
num_channels = 3,
num_input_channels = 3,
num_classes = 10,
model_id = 'B', # S, B, M and L are valid model ids
kernel_size = 3, # 3x3x3 and 5x5x5 were tested in publication
Expand Down Expand Up @@ -228,4 +228,4 @@ mednextv1_train 3d_fullres nnUNetTrainerV2_MedNeXt_S_kernel5 Task040_KiTS2019 0
The `-resample_weights` flag as it is responsible to triggering the UpKern algorithm.

### A note on 2D MedNeXt:
Please note that while the MedNeXt can run on 2D, it has not been tested in 2D mode.
Please note that while the MedNeXt can run on 2D, it has not been tested in 2D mode.
2 changes: 1 addition & 1 deletion nnunet_mednext/training/model_restore.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -144,7 +144,7 @@ def load_model_and_checkpoint_files(folder, folds=None, mixed_precision=None, ch
trainer.initialize(False)
all_best_model_files = [join(i, "%s.model" % checkpoint_name) for i in folds]
print("using the following model files: ", all_best_model_files)
all_params = [torch.load(i, map_location=torch.device('cpu')) for i in all_best_model_files]
all_params = [torch.load(i, map_location=torch.device('cpu'), weights_only=False) for i in all_best_model_files]
return trainer, all_params


Expand Down