πŸ“Š
Dataset

Tinysleepnet Supratak Embeddings

by 4rooms 4rooms/tinysleepnet-supratak-embeddings
Free2AITools Nexus Index
58.6
S: Semantic 50

Query-time baseline · scored live at search

A: Authority 61
P: Popularity 51
R: Recency 66
Q: Quality 50
Tech Context
Vital Performance
Data Integrity 58.6 FNI Score
- Size
- Rows
- Tokens
Dataset Information Summary
Entity Passport
Registry ID 4rooms/tinysleepnet-supratak-embeddings
License Apache-2.0
Provider huggingface
πŸ“œ

Cite this dataset

Academic & Research Attribution

BibTeX
@misc{hf_dataset_4rooms_tinysleepnet_supratak_embeddings,
  author = {4rooms},
  title = {Tinysleepnet Supratak Embeddings Dataset},
  year = {2026},
  howpublished = {\url{https://huggingface.co/datasets/4rooms/tinysleepnet-supratak-embeddings}},
  note = {Accessed via Free2AITools.}
}
APA Style
4rooms. (2026). Tinysleepnet Supratak Embeddings [Dataset]. Free2AITools. https://huggingface.co/datasets/4rooms/tinysleepnet-supratak-embeddings

πŸ”¬Technical Deep Dive

Full Specifications [+]

βš–οΈ Free2AITools Nexus Index V2.0

Semantic (S) 50

Query-time baseline · scored live at search

Authority (A) 61
Popularity (P) 51
Recency (R) 66
Quality (Q) 50

πŸ’¬ Index Insight

FNI V2.0 for Tinysleepnet Supratak Embeddings: Authority (A:61), Popularity (P:51), Recency (R:66), Quality (Q:50). Semantic (S) is a query-time baseline scored live at search.

Free2AITools Nexus Index

Data Sources / Provenance

Open data Updated: Live data
⬇️
Downloads
29,472

πŸ‘οΈ Data Preview

πŸ“Š

Row-level preview not available for this dataset.

Schema structure is shown in the Field Logic panel when available.

πŸ”— Explore Full Dataset β†—

🧬 Field Logic

🧬

Schema not yet indexed for this dataset.

Dataset Specification

TinySleepNet-Supratak Embeddings

Pre-extracted contextualized per-epoch embeddings from TinySleepNet (Supratak & Guo 2020), trained on Sleep-EDF via PhysioEx.

Each subject directory contains:

  • embeddings.npy β€” (n_epochs, 128) contextualized epoch embeddings (bfloat16)
  • labels.npy β€” (n_epochs,) AASM sleep stage labels (W=0, N1=1, N2=2, N3=3, REM=4, unscored=-1)

Usage

python
from physioex.models import load_embeddings

path = load_embeddings("tinysleepnet-supratak", "hmc", verbose=True)

Linear Probe Results (5-fold subject-wise CV)

Dataset Subjects ACC MF1 ΞΊ F1-W F1-N1 F1-N2 F1-N3 F1-REM
sleepedf 153 0.8754 0.8330 0.8278 0.95 0.60 0.89 0.84 0.89
mass_ss05 26 0.8620 0.7873 0.7986 0.82 0.48 0.90 0.87 0.87
mass_ss02 19 0.8545 0.7745 0.7862 0.82 0.44 0.90 0.87 0.83
mass_ss04 40 0.8432 0.7768 0.7746 0.82 0.48 0.90 0.84 0.84
mass_ss03 62 0.8397 0.7751 0.7616 0.84 0.49 0.89 0.82 0.84
dcsm 255 0.8332 0.7212 0.7552 0.91 0.32 0.81 0.82 0.74
shhs_visit2 2651 0.8159 0.7095 0.7375 0.86 0.27 0.85 0.83 0.75
shhs_visit1 5793 0.8044 0.7083 0.7198 0.84 0.31 0.83 0.80 0.75
mass_ss01 53 0.7966 0.7423 0.7124 0.87 0.49 0.86 0.69 0.81
stages_GSDV 232 0.7706 0.6121 0.6261 0.77 0.18 0.84 0.56 0.70
hpap 247 0.7567 0.7040 0.6663 0.81 0.38 0.81 0.79 0.73
mesa 2056 0.7556 0.6648 0.6499 0.82 0.34 0.81 0.62 0.74
stages_MSMI 63 0.7549 0.6706 0.6303 0.78 0.31 0.82 0.69 0.75
stages_GSSW 105 0.7534 0.5568 0.5964 0.

Social Proof

HuggingFace Hub
29.5KDownloads
πŸ”„ Updated daily

Source summary: Based on Hugging Face metadata. Not a recommendation.

πŸ“Š FNI Methodology πŸ“š Knowledge Baseℹ️ Verify with original source

πŸ›‘οΈ Dataset Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

πŸ†” Identity & Source

id
hf-dataset--4rooms--tinysleepnet-supratak-embeddings
slug
4rooms--tinysleepnet-supratak-embeddings
source
huggingface
author
4rooms
license
Apache-2.0
tags
language:en, license:apache-2.0, size_categories:10k<n<100k, region:us, sleep-staging, eeg, embeddings, physioex, tinysleepnet

βš™οΈ Technical Specs

architecture
null
params billions
null
context length
null
pipeline tag

πŸ“Š Engagement & Metrics

downloads
29,472
stars
null
forks
null

Data indexed from public sources. Updated daily.