0.3.12

• Adding presentation and official documentation
• Splitting notebook per sections
• Adding additional comments to the code

0.3.11

• Adding ViT-B/16/S model on 25 epochs with constant learning rate
• Checking on training and validation accuracy/loss parameters according to the training log
• Display results on standalone plots

0.3.10

• Adding evaluation for ResNet18
• Debugging on SAM model evaluation
• Improvment Training Plot support curves on N < 5 lines
• Model adaptation during loading on evaluation (standalone) with adapting on backbones

0.3.9

• Adding ResNet 18 (11M parameters)
• Upload history for loss and accuracy
• Upload epoch 20 dump
• Upload final model checkpoint

0.3.8

• Adding ViT-B/16/SG
• Gradual learning rate every 10 epochs
• SGD optimization
• Adding loss and accuracy histories

0.3.7

• Adding VIT-B/16 model checkpoint using customized learning rate scheduler
• Adding SAM to the model as a optimization algorithm to smooth the loss landscape
• Adding history for training and validation loss
• Adding history for training and validation accuracy

0.3.6

• Configuration of resnet18 with gradual learning rate
• Starting learning rate at 0.01
• Epochs 50 with plateau at 25
• Loading training and validation accuracy histories

0.3.5

• Adding SAM optimization for VIT-B/16
• Defining closure for sharpness-aware minimization efficiency
• Debugging model loader for the checkpoints recovery

0.2.5

• Upload optimal model on AffectNet
• Defines evaluation plots on accuracy and loss values

0.2.4

• Adding gradual learning rate
• Modify dataset with AffectNet in validation and testing set
• Adding scheduler for learning rate adjustment