Vit-FER

vit-Facial-Expression-Recognition

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the FER 2013,MMI Facial Expression Database, and AffectNet dataset datasets. It achieves the following results on the evaluation set:

• Loss: 0.4503
• Accuracy: 0.8434

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, MMI facial Expression, and AffectNet datasets, which consist 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 the model. The preprocessing steps include:

• Resizing: Images are resized to the specified input size.
• Normalization: Pixel values are normalized to a specific range.
• Data Augmentation: Random transformations such as rotations, flips, and zooms are applied to augment the training dataset.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 1000
• num_epochs: 3

Training results

Framework versions

• Transformers 4.36.0
• Pytorch 2.0.0
• Datasets 2.1.0
• Tokenizers 0.15.0