Downloads · 30 days
0
tversky-cross-calibration-checkpoints
youqiangao/tversky-cross-calibration-checkpoints
tversky-cross-calibration-checkpoints is a image segmentation model from youqiangao. Use it for the image segmentation task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as other.
These ten inference checkpoints accompany the real-data experiments in Cross-Calibration of Tversky Indices. Each model supplies one set of probability outputs on which the Dice and IoU optimizers are compared. The co…
Access
Public
Updated Aug 22, 2026
Repo size
3.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt3.3 GB · 100%
At a glance
- Task
- Image Segmentation
- Library
- pytorch
- License
- other
- Access
- Public
- Created
- Aug 22, 2026
- Updated
- Aug 22, 2026
- SHA
- 1556cb47
Model card
From the Hugging Face model README
Tversky Cross-Calibration Checkpoints
These ten inference checkpoints accompany the real-data experiments in Cross-Calibration of Tversky Indices. Each model supplies one set of probability outputs on which the Dice and IoU optimizers are compared. The comparison concerns the equivalence of the two metric-specific decisions, not the absolute segmentation performance of the underlying network.
The repository contains U-Net and FCN8 weights for Oxford-IIIT Pet, ISIC 2017,
Kvasir-SEG, Pascal VOC 2012, and Cityscapes. Use the code repository's
scripts/download_checkpoints.py command to download and verify files into the
expected evaluation paths.
The checkpoint files contain model parameters only and are intended for FP32 inference. Dataset access and use remain subject to each dataset provider's license.
- Task
- Image Segmentation
- Library
- pytorch
- License
- other
- Created
- Aug 22, 2026
- Updated
- Aug 22, 2026