Feature Extraction
Transformers
Safetensors
medical
radiology
vision-language
chest-ct
3d-medical-imaging
glint
custom_code
Instructions to use Deepnoid/GLINT-CT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Deepnoid/GLINT-CT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Deepnoid/GLINT-CT", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Deepnoid/GLINT-CT", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
8 days ago
-
Resample similarity maps onto the input CT grid
Verified signature- similarity_scores_to_volume(scores, model, geometry) returns the map with the input CT's shape and affine (geometry from load_ct_volume(..., return_geometry=True)); without geometry it stays on the 240x384x384 preprocessed grid - load_ct_volume: return_affine -> return_geometry; accepts a NIfTI file or a DICOM series directory - inference.py: saves only similarity_map.nii.gz (no --ct_output); drops the 18 CT-RATE finding scores - README: new API, geometry, raw_spacing axis order (I, P, L), pydicom for DICOM inputdb46ad7
12 days ago
-
Release GLINT-CT
c5a246d