Seven-emotion FER2013 output
According to the model card, the model classifies facial images into angry, disgust, fear, happy, sad, surprise, and neutral.
Open Source Model Profile · trpakov
vit-face-expression
vit-face-expression is an 86M-parameter Vision Transformer from trpakov for facial emotion recognition. According to the model card, it is fine-tuned for seven-emotion classification on the FER2013 dataset.
- Publisher
- trpakov
- Task
- image-classification
- Model type
- vit
- License
- apache-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
vit-face-expression is published by trpakov as an image-classification model for facial expression and emotion recognition. Captured Safetensors metadata reports 85,804,039 parameters, about 86M. According to the model card, it is a Vision Transformer fine-tuned from vit-base-patch16-224-in21k on the FER2013 dataset.
Recorded capabilities
ViT base fine-tune
According to the model card, the checkpoint is fine-tuned from vit-base-patch16-224-in21k.
Documented augmentation
According to the model card, training augmentation applied random rotations, flips, and zooms.
Stated data limitations
According to the model card, performance may reflect training-data bias and generalization depends on dataset diversity.
Use cases in the source record
- Facial emotion classification into the seven FER2013 categories: angry, disgust, fear, happy, sad, surprise, and neutral.
- Vision experiments on preprocessed face inputs using the card's resize and normalization pipeline.
Limitations and unknowns
- No evaluation results were extracted from this record.
- According to the model card, performance may be influenced by biases in the training data.
- According to the model card, generalization to unseen data depends on training-dataset diversity.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: trpakov/vit-face-expression
Captured: Unknown. Processed: 2026-09-07T19:34:59.938191+00:00.
Vision Transformer (ViT) for Facial Expression Recognition Model Card Model Overview Model Name: trpakov/vit-face-expression Task: Facial Expression/Emotion Recognition Dataset: FER2013 Model Architecture: Vision Transformer (ViT) Finetuned from model: vit-base-patch16-224-in21k Model Description The vit-face-expression model is a Vision Transformer fine-tuned for the task of facial emotion recognition. It is trained on the FER2013 dataset, which consists of facial images categorized into seven different emotions: Angry Disgust Fear Happy Sad Surprise Neutral Data Preprocessing The input images are preprocessed before being fed into…
F001F002F003F004F005F006F007F010F011F012F013F014F015F016F017