frozenleaves/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-10-20 17:13:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

[examples] fix do_reduce_labels argument for run_semantic_segmentation_no_trainer (#39322)

Browse Source 
* no use do_reduce_labels argument in model

* use do_reducer_labels in AutoImageProcessor
This commit is contained in:
eromomon
2025-07-14 04:16:49 -06:00
committed by GitHub
parent 8165c703ab
commit 903944a411
1 changed files with 1 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
examples/pytorch/semantic-segmentation/run_semantic_segmentation_no_trainer.py
View File

@ -324,13 +324,12 @@ def main():
args.model_name_or_path, id2label=id2label, label2id=label2id, trust_remote_code=args.trust_remote_code
)
image_processor = AutoImageProcessor.from_pretrained(
args.model_name_or_path, trust_remote_code=args.trust_remote_code
args.model_name_or_path, trust_remote_code=args.trust_remote_code, do_reduce_labels=args.do_reduce_labels
)
model = AutoModelForSemanticSegmentation.from_pretrained(
args.model_name_or_path,
config=config,
trust_remote_code=args.trust_remote_code,
do_reduce_labels=args.do_reduce_labels,
)
# Define transforms to be applied to each image and target.