Lab05

Lab

---

Lab Notebook: Augmentations.ipynb

---

Lab Assignment: Assignment.pdf (Deadline: PR by End-of-Day Monday, 13.11.2023).

---

For self-study:

• SGD implementation: https://pytorch.org/docs/stable/_modules/torch/optim/sgd.html#SGD
• Check the references (and past references if not done yet)
• Adam paper: https://arxiv.org/abs/1412.6980

---

References:

• RandAugment:
  • RandAugment: Practical automated data augmentation with a reduced search space
  • RandAugment in torchvision: https://pytorch.org/vision/main/generated/torchvision.transforms.v2.RandAugment.html
• CutMix:
  • Regularization Strategy to Train Strong Classifiers with Localizable Features
  • CutMix in torchvision: https://pytorch.org/vision/main/generated/torchvision.transforms.v2.CutMix.html
• MixUp:
  • mixup: Beyond Empirical Risk Minimization
  • MixUp in torchvision: https://pytorch.org/vision/main/generated/torchvision.transforms.v2.MixUp.html
• How to use CutMix and MixUp: https://pytorch.org/vision/main/auto_examples/transforms/plot_cutmix_mixup.html
• CIFAR-10:
  • Dataset class: https://pytorch.org/vision/main/generated/torchvision.datasets.CIFAR10.html
  • CIFAR-10 training example: https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html (you must not use convolutions in your homework!)
• TorchVision transforms getting started: https://pytorch.org/vision/main/auto_examples/transforms/plot_transforms_getting_started.html
• TorchVision examples: https://pytorch.org/vision/stable/auto_examples/transforms/plot_transforms_illustrations.html#sphx-glr-auto-examples-transforms-plot-transforms-illustrations-py
• Optimizers:
  • Optimizers, Learning Rate Schedulers & other advanced techniques: https://pytorch.org/docs/stable/optim.html
  • SAM implementation: https://github.com/davda54/sam
• Tensorboard: https://pytorch.org/docs/stable/tensorboard.html
• Weights and Biases: https://docs.wandb.ai/guides/integrations/pytorch