Downloads · 30 days
0
late-fusion-stress
TheBgGirl/late-fusion-stress
late-fusion-stress is a machine learning model from TheBgGirl. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for scikit-learn.
Late-fusion stress classifier trained on extracted text and FER features.
Access
Public
Updated Apr 3, 2026
Repo size
876 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pkl876 KB · 65%
At a glance
- Library
- scikit-learn
- Access
- Public
- Created
- Apr 3, 2026
- Updated
- Apr 3, 2026
- SHA
- 9b2b1b8d
Model card
From the Hugging Face model README
TheBgGirl/late-fusion-stress
Late-fusion stress classifier trained on extracted text and FER features.
Required inputs
The model expects a tabular feature frame with the same columns used during training.
Feature columns
- numeric:
prob_not_stressed - numeric:
logit_not_stressed - numeric:
prob_stressed - numeric:
logit_stressed - numeric:
num_frames - numeric:
dominant_emotion_share - numeric:
emotion_variability_mean_std - numeric:
stress_proxy_mean - numeric:
neutral_frame_ratio - numeric:
mean_prob_anger - numeric:
mean_prob_disgust - numeric:
mean_prob_fear - numeric:
mean_prob_happy - numeric:
mean_prob_neutral - numeric:
mean_prob_sadness - numeric:
mean_prob_surprise - categorical:
text - categorical:
predicted_label - categorical:
dominant_emotion
Evaluation
- accuracy: 1.0000
- f1: 1.0000
- macro_f1: 1.0000
- precision: 1.0000
- recall: 1.0000
- roc_auc: 1.0000
Files in this repo
late_fusion_model.pkltraining_metadata.json- optional evaluation artifacts under
evaluation/
- Library
- scikit-learn
- Created
- Apr 3, 2026
- Updated
- Apr 3, 2026