Labs

This page contains links to the notebooks and to the code used during the labs.

• Lab 01. Polynomial logistic regression versus multi-layer perceptron on toy datasets
  Week 1
  
  Description: We use the scikit-learn library to compare polynomial logistic regression (a hand-made feature engineering approach) and multi-layer perceptron (fully data-driven approach) on toy datasets.
  Files:     tutorial01.ipynb   
  
• Lab 02. (a) Pytorch tensors (b) Using pre-trained neural networks for complex tasks
  Week 1 and 2
  
  Description: In tutorial02a we explore quickly tensors in pytorch, while we use in tutorial02b pre-trained neural networks to caption automatically images coming from your webcam.
  Files:     tutorial02a.ipynb    tutorial02a_correction.ipynb    tutorial02b.ipynb    tutorial02b_correction.ipynb    model.png    giraffe.png   
  Extra files:    https://www.dropbox.com/sh/yn0battb459ysuw/AADUpdx0hzm7mYDvrCxOa48Oa?dl=0
• Lab 03. (a) Homemade MLP (b) MLP training using PyTorch
  Week 2
  Deadline: 2022-01-23 23:59
  
  Description: In tutorial03a we code a multi-layer perceptron algorithm and train it 'by hand'. In tutorial03b we do the same but using the automatic differentiation of PyTorch.
  tutorial03a and tutorial03b are homeworks that are part of your grade for the course
Files:     tutorial03a.ipynb    tutorial03b.ipynb    mlp.svg   
  
• Lab 04. (a) CNN using PyTorch and PyTorch-Lightning (b) Compare a CNN trained from scratch with transfer learning and fine-tuning
  Week 4
  Deadline: 2022-02-06 23:59
  
  Description: In tutorial04a we code a CNN architecture using pytorch and pytorch-lightning, give some tips and use tensorboard to log metrics. Then, you will work on improving what we did. In tutorial04b you will train from scratch a CNN and compare it with a CNN trained by transfer-learning and fine-tuning to classify bees and ants.
  tutorial04a and tutorial04b are homeworks that are part of your grade for the course
Files:     tutorial04a.ipynb    tutorial04b.ipynb    cnn.png