jakwisn/DTU-Advanced-Deep-Learning-In-Computer-Vision

Advanced Deep learning in Computer Vision

Week 1

• create dataloader
• design transformations that are consistent to train/test images and scale them down/crop to small, consistent image.
• create transformations (do not destroy the pictures!)
  • linear
  • exponential
  • logarithmic
  • gamma adjustment (opencv)
  • linear mapping function (https://www.cs.cityu.edu.hk/~rynson/papers/eccv22b.pdf)
• ask Morten for tips on aproaching weight initialization in stable diffusion

Week 2

• implement the stable diffuction model (ground up? using some weights?)
• pick and create metrics
• try training

Week 3

• train using different transformations
• measure the results and add them to table
• compare with some papers
• compare visually

Week 4

• make a poster