Downloads · 30 days
0
3Class-Gel-Segmentation-Expanded-Aug-2026
Gertrude01/3Class-Gel-Segmentation-Expanded-Aug-2026
3Class-Gel-Segmentation-Expanded-Aug-2026 is a machine learning model from Gertrude01. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This SMP-UNet model was trained on a subset of the GelGenie training dataset (185 images). It builds upon the GelGenie-Universal-Dec-2023 model, extending it from 2-class to 3-class segmentation (background, bands, an…
Access
Public
Updated Sep 4, 2026
Repo size
709 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pdf364 MB · 51%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Aug 23, 2026
- Updated
- Sep 4, 2026
- SHA
- b4a993cc
Model card
From the Hugging Face model README
This SMP-UNet model was trained on a subset of the GelGenie training dataset (185 images). It builds upon the GelGenie-Universal-Dec-2023 model, extending it from 2-class to 3-class segmentation (background, bands, and wells).
The model was initialised from the GelGenie-Universal-Dec-2023 checkpoint and fine-tuned for 3-class segmentation from epoch 579 to epoch 1000. Epoch 998 was selected as the final checkpoint.
Acknowledgements
Research supported with Cloud TPUs from Google's TPU Research Cloud (TRC).
- License
- apache-2.0
- Created
- Aug 23, 2026
- Updated
- Sep 4, 2026