Instructions to use Zipeng365/WISP with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Scikit-learn
How to use Zipeng365/WISP with Scikit-learn:
from huggingface_hub import hf_hub_download import joblib model = joblib.load( hf_hub_download("Zipeng365/WISP", "sklearn_model.joblib") ) # only load pickle files from sources you trust # read more about it here https://skops.readthedocs.io/en/stable/persistence.html - Notebooks
- Google Colab
- Kaggle
Download docs/figures/memory_plotted_values.csv from Zipeng365/WISP: direct link, hf CLI and curl.
- Browser
- Download file 1.96 kB
-
https://huggingface.co/Zipeng365/WISP/resolve/main/docs/figures/memory_plotted_values.csv
- Command line
-
hf download hf://Zipeng365/WISP/docs/figures/memory_plotted_values.csv
-
curl -L -o memory_plotted_values.csv https://huggingface.co/Zipeng365/WISP/resolve/main/docs/figures/memory_plotted_values.csv
1.96 kB
| key,name,group,peak_memory_gib,memory_vs_wisp_cis,macro_f1,accuracy,balanced_accuracy,worst_class_f1,streams_measured,largest_stream,memory_source | |
| wisp_random,WISP-Random,wisp_search,4.75,0.535,70.1996,77.2824,70.875,28.2521,10,harmes_left_wrist_accel_v1,"wisp-har benchmarks/memory_final_models.py: train+val fit + test prediction, 1 thread" | |
| wisp_evolution,WISP-Evolution,wisp_search,7.95,0.896,69.5918,76.8443,70.1693,27.9627,10,harmes_left_wrist_accel_v1,"wisp-har benchmarks/memory_final_models.py: train+val fit + test prediction, 1 thread" | |
| wisp_cis,WISP-CIS,wisp_fixed,8.88,1.0,66.1391,74.0655,66.0421,24.7785,10,wisdm_watch_accel_v1,"wisp-har benchmarks/memory_final_models.py: train+val fit + test prediction, 1 thread" | |
| aeon15_rdst_default_v1,RDST,cpu,113.65,12.806,60.0974,70.1516,60.5947,18.0501,10,wisdm_watch_accel_v1,"paper efficiency benchmark: fit on the training split + prediction, 1 thread, Xeon Platinum 8570" | |
| aeon15_mr_hydra_default_v1,MR-Hydra,cpu,104.4,11.763,59.8006,68.4927,60.4243,19.4399,10,wisdm_watch_accel_v1,"paper efficiency benchmark: fit on the training split + prediction, 1 thread, Xeon Platinum 8570" | |
| aeon15_multirocket_default_v1,MultiRocket,cpu,110.3,12.427,59.0983,67.8303,59.7245,19.12,10,wisdm_watch_accel_v1,"paper efficiency benchmark: fit on the training split + prediction, 1 thread, Xeon Platinum 8570" | |
| aeon15_quant_default_v1,QUANT,cpu,4.37,0.492,55.2813,66.1314,55.8404,15.8511,10,iuwds_wrist_accel_v1,"paper efficiency benchmark: fit on the training split + prediction, 1 thread, Xeon Platinum 8570" | |
| minirocket_official_v1,MiniRocket,cpu,21.77,2.453,59.0362,69.3873,59.7813,15.4518,10,wisdm_watch_accel_v1,"paper efficiency benchmark: fit on the training split + prediction, 1 thread, Xeon Platinum 8570" | |
| simple_stats_rf_balanced_v1,Balanced-RF,cpu,2.27,0.256,47.8504,60.3891,48.6058,9.0427,10,wisdm_watch_accel_v1,"paper efficiency benchmark: fit on the training split + prediction, 1 thread, Xeon Platinum 8570" | |