/pytorch-notebooks

code for deep learning courses

Primary LanguageJupyter NotebookApache License 2.0Apache-2.0

Dataflowr

Code and notebooks for the deep learning course dataflowr. Here is the schedule followed at école polytechnique in 2023:

🌻Session1️⃣

Things to remember
  • you do not need to understand everything to run a deep learning model! But the main goal of this course will be to come back to each step done today and understand them...
  • to use the dataloader from Pytorch, you need to follow the API (i.e. for classification store your dataset in folders)
  • using a pretrained model and modifying it to adapt it to a similar task is easy.
  • if you do not understand why we take this loss, that's fine, we'll cover that in Module 3.
  • even with a GPU, avoid unnecessary computations!

🌻Session2️⃣

Things to remember
  • Pytorch tensors = Numpy on GPU + gradients!
  • Automatic differentiation is not only the chain rule! Backpropagation algorithm or dual numbers are clever algorithms to implement automatic differentiation...
  • Loss vs Accuracy. Know your loss for a classification task!

🌻Session3️⃣

Things to remember
  • know your loss for a classification task!
  • know your optimizer (Module 4 done at home)
  • know how to build a neural net with torch.nn.module (Module 5 done at home)
  • know how to use convolution and pooling layers (kernel, stride, padding)
  • know how to use dropout

🌻Session4️⃣

TBC

Twitter URL

🌻 All notebooks

Usage

If you want to run locally, follow the instructions of Module 0 - Running the notebooks locally

2020 version of the course

Archives are available on the archive-2020 branch.