tahayf/vit-base-patch16-224_ferplus

Fine-Tuned ViT on FERPlus Dataset

This model is a fine-tuned version of ViT on the FERPlus dataset, which is more balanced ferplus dataset as owner claimed.

Model Details

• Base Model: Clip-ViT-Base-Patch16
• Dataset: FERPlus, which contains grayscale images of faces labeled with emotion categories.
• Task: Emotion Classification
• Accuracy %82.4
• Labels:
  • 0: Angry
  • 1: Contempt
  • 2: Disgust
  • 3: Fear
  • 4: Happy
  • 5: Neutral
  • 6: Sad
  • 7: Surprise

Training Hyperparameters

• Batch Size: 16
• Epochs: 1
• Learning Rate: 2e-5
• Weight Decay: 0.01