Downloads · 30 days
0
melanoma-classifier
Shivakarthik12/melanoma-classifier
melanoma-classifier is a machine learning model from Shivakarthik12. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This Space packages the existing notebook inference path. It uses the checkpoint metadata for the Swin V2 model configuration, class names, preprocessing, and threshold.
Access
Public
Updated Sep 1, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pyc9.8 KB · 56%
At a glance
- Access
- Public
- Created
- Sep 1, 2026
- Updated
- Sep 1, 2026
- SHA
- 5b321e02
Model card
From the Hugging Face model README
Melanoma classifier
This Space packages the existing notebook inference path. It uses the checkpoint metadata for the Swin V2 model configuration, class names, preprocessing, and threshold.
The notebook's saved single-image inference function is deterministic Resize -> Normalize -> ToTensorV2, followed by one model forward pass and thresholding of the melanoma probability. Its evaluation-only TTA/calibration experiments are not applied here because they are not part of that current single-image inference function.
Upload best_swin_checkpoint.pth to this repository. The checkpoint is intentionally not converted or replaced.
- Created
- Sep 1, 2026
- Updated
- Sep 1, 2026