qubvel-org/segmentation_models.pytorch
Add upsampling parameter to Segformer
オープン
#1,106 opened on 2025/03/26
featuregood first issue
Repository metrics
- Stars
- (11,704 個のスター)
- PR merge metrics
- (平均マージ 4h 14m) (30d で 24 merged PRs)
説明
I did this locally and it works perfectly well, but I legally cannot make a pull request. It is simple and easy.
On file segmentation_models_pytorch/decoders/segformer/model.py:
Line 60: Add upsampling: int = 4,, after activation param and before aux_params.
Line 85: swap the parameter value from 4 to upsampling.
This is all. I've done it locally and I think the community would benefit.
Thank you