ENS Paris-Saclay M1 IA&ML: Image and video - 2025

Gabriele Facciolo

General info

ENS Paris-Saclay

Each course will have a part of Lecture and a part of Practical Session. The Practical Session will be based on Keras and Pytorch using colab notebooks.

Please, make sure to bring your own laptop

Schedule

  1. – Tuesday 16/9 (1M07): 9h30-12h00 - Intro NN, backprop and CNN for classification

  2. – Friday 19/9 (1Z25): 14h00-16h30 - Semantic segmentation

  3. – Monday 22/9 (1B14): 14h00-16h30 - Object detection

  4. – Tuesday 30/9 (1Z25): 14h00-16h30 - Transfer learning and representation learning

Projects file

Soutenances TBD

Slides and notebooks

  1. Slides 1

    Notebook 0: jupyter notebook tutorial

    Notebook 0.5: not pytorch tutorial

    Notebook 1: Classification CNNs - pytorch

  1. Slides 2

    Notebook 2: Semantic segmentation - pytorch

    Notebook 2.5: More semantic segmentation with pytorch

  1. Slides 3

    Notebook 3.1: YoloV2 Step-by-Step

    Notebook 3.2: Mask R-CNN semantic segmentation with pytorch

    Notebook 3.3: Human pose estimation

  2. Slides 4

    Notebook 4.1: Transfer learning with pytorch

    Notebook 4.1: Transfer learning with keras (old)

    Notebook 4.2: Interacting with CLIP

    Notebook 4.2.5: Training CLIP (much more details)