Feature Extraction
Transformers
Joblib
Safetensors
English
comodo
imu
wearable-sensing
human-activity-recognition
time-series
cross-modal-distillation
svm
custom_code
Instructions to use CRUISEResearchGroup/COMODO-AnyMo-Bench with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CRUISEResearchGroup/COMODO-AnyMo-Bench with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="CRUISEResearchGroup/COMODO-AnyMo-Bench", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("CRUISEResearchGroup/COMODO-AnyMo-Bench", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
14 days ago
-
Add direct variant loading and simplify model cards
Verified signatureSupport variant="core50" and variant="fine150" in pipeline and AutoClass loaders while retaining subfolder loading. Update the ACM paper link and citation, clarify benchmark input preprocessing, and simplify documentation. Encoder weights, classifiers, and normalization statistics are unchanged.3f224a9 -
Release COMODO on AnyMo Bench with Core50 and Fine150 inference bundles
Verified signaturePublish the shared COMODO IMU encoder, taxonomy-specific fitted SVMs, preprocessing assets, Transformers interface, benchmark results, and licenses.1e4dcb8