Skip to content

Releases: kode-git/vfer

0.3.12

16 May 11:36
Compare
Choose a tag to compare
  • Adding presentation and official documentation
  • Splitting notebook per sections
  • Adding additional comments to the code

0.3.11

14 May 19:19
Compare
Choose a tag to compare
  • 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

13 May 19:56
Compare
Choose a tag to compare
  • 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

12 May 08:45
Compare
Choose a tag to compare
  • Adding ResNet 18 (11M parameters)
  • Upload history for loss and accuracy
  • Upload epoch 20 dump
  • Upload final model checkpoint

0.3.8

11 May 22:10
Compare
Choose a tag to compare
  • Adding ViT-B/16/SG
  • Gradual learning rate every 10 epochs
  • SGD optimization
  • Adding loss and accuracy histories

0.3.7

11 May 08:59
Compare
Choose a tag to compare
  • 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

09 May 23:07
Compare
Choose a tag to compare
  • 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

09 May 15:12
Compare
Choose a tag to compare
  • Adding SAM optimization for VIT-B/16
  • Defining closure for sharpness-aware minimization efficiency
  • Debugging model loader for the checkpoints recovery

0.2.5

07 May 16:37
Compare
Choose a tag to compare
  • Upload optimal model on AffectNet
  • Defines evaluation plots on accuracy and loss values

0.2.4

06 May 14:25
Compare
Choose a tag to compare
  • Adding gradual learning rate
  • Modify dataset with AffectNet in validation and testing set
  • Adding scheduler for learning rate adjustment