/fastai.pytorch.from.scratch

I am implementing from scratch the tools, techniques and best practices I learnt from fast.ai's 2017 offering.

Primary LanguageJupyter NotebookMIT LicenseMIT

fastai.pytorch.from.scratch

I am implementing from scratch the tools, techniques and best practices I learnt from fast.ai's 2017 offering.

The idea is to not use the fastai library and build everything minimally on PyTorch, to see things happening first hand.

I have referred code from the following sources (the exact source is also mentioned in each file):

Code tested on PyTorch v0.2.0, Python 3.6

Data Loading

  • Load from folders segregated into classes
  • Load from csv files assigning classes to images

Data Augmentation

  • Horizontal flip
  • Cropping center
  • Cropping random
  • Cropping custom
  • Scalling

Learning Rate

  • Optimum learning rate finder
  • LR Annealing

Model Training

  • Using pretrained weights
  • Freezing layers
  • Precompute activations
  • Delete/Add Layers

Test time techniques

  • Test Time Augmentation (TTA)

Papers

These papers or reading material was suggested either by Jeremy or other participants in various discussions.