docs: Fix docs typos for new labels structure

fastlib · Mar 28, 2023 · 16ac019 · 16ac019
1 parent 4f03fa2
commit 16ac019
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 2 deletions.
diff --git a/documentation/dataset_format.md b/documentation/dataset_format.md
@@ -190,7 +190,7 @@ choose from and allows you to define your own, see [here](explanation_normalizat
 
 Important changes relative to nnU-Net v1:
 - "modality" is now called "channel_names" to remove strong bias to medical images
-- labels are structured differently (name -> int instead if int -> name). This was needed to support [region-based training](region_based_training.md)
+- labels are structured differently (name -> int instead of int -> name). This was needed to support [region-based training](region_based_training.md)
 - "file_ending" is added to support different input file types
 - "overwrite_image_reader_writer" optional! Can be used to specify a certain (custom) ReaderWriter class that should 
 be used with this dataset. If not provided, nnU-Net will automatically determine the ReaderWriter

diff --git a/documentation/tldr_migration_guide_from_v1.md b/documentation/tldr_migration_guide_from_v1.md
@@ -6,7 +6,7 @@
 - Datasets have the same structure (imagesTr, labelsTr, dataset.json) but we now support more 
 [file types](dataset_format.md#supported-file-formats). The dataset.json is simplified. Use `generate_dataset_json` 
 from nnunetv2.dataset_conversion.generate_dataset_json.py. 
-- Careful: labels are now no longer declared as name:value but value:name. This has to do with [hierarchical labels](region_based_training.md). 
+- Careful: labels are now no longer declared as value:name but name:value. This has to do with [hierarchical labels](region_based_training.md). 
 - nnU-Net v2 commands start with `nnUNetv2...`. They work mostly (but not entirely) the same. Just use the `-h` option.
 - You can transfer your V1 raw datasets to V2 with `nnUNetv2_convert_old_nnUNet_dataset`. You cannot transfer trained 
 models. Continue to use the old nnU-Net Version for making inference with those.