A propos

This repository contains all the documents and links of the Fidle Training .
Fidle (for Formation Introduction au Deep Learning) is a 2-day training session
co-organized by the Formation Permanente CNRS and the SARI and DEVLOG networks.

The objectives of this training are :

• Understanding the bases of Deep Learning neural networks
• Develop a first experience through simple and representative examples
• Understanding Tensorflow/Keras and Jupyter lab technologies
• Apprehend the academic computing environments Tier-2 or Tier-1 with powerfull GPU

For more information, you can contact us at :
Current Version : 1.2b1 DEV

Course materials

Course slides The course in pdf format (12 Mo)	Notebooks     Get a Zip or clone this repository      (10 Mo)	Datasets All the needed datasets (1.2 Go)

Have a look about How to get and install these notebooks and datasets.

Jupyter notebooks

Linear and logistic regression

• LINR1 - Linear regression with direct resolution
  Low-level implementation, using numpy, of a direct resolution for a linear regression
• GRAD1 - Linear regression with gradient descent
  Low level implementation of a solution by gradient descent. Basic and stochastic approach.
• POLR1 - Complexity Syndrome
  Illustration of the problem of complexity with the polynomial regression
• LOGR1 - Logistic regression
  Simple example of logistic regression with a sklearn solution

Perceptron Model 1957

• PER57 - Perceptron Model 1957
  Example of use of a Perceptron, with sklearn and IRIS dataset of 1936 !

Basic regression using DNN

• BHPD1 - Regression with a Dense Network (DNN)
  Simple example of a regression with the dataset Boston Housing Prices Dataset (BHPD)
• BHPD2 - Regression with a Dense Network (DNN) - Advanced code
  A more advanced implementation of the precedent example

Basic classification using a DNN

• MNIST1 - Simple classification with DNN
  An example of classification using a dense neural network for the famous MNIST dataset

Images classification with Convolutional Neural Networks (CNN)

• GTSRB1 - CNN with GTSRB dataset - Data analysis and preparation
  Episode 1 : Data analysis and creation of a usable dataset
• GTSRB2 - CNN with GTSRB dataset - First convolutions
  Episode 2 : First convolutions and first results
• GTSRB3 - CNN with GTSRB dataset - Monitoring
  Episode 3 : Monitoring and analysing training, managing checkpoints
• GTSRB4 - CNN with GTSRB dataset - Data augmentation
  Episode 4 : Improving the results with data augmentation
• GTSRB5 - CNN with GTSRB dataset - Full convolutions
  Episode 5 : A lot of models, a lot of datasets and a lot of results.
• GTSRB6 - Full convolutions as a batch
  Episode 6 : Run Full convolution notebook as a batch
• GTSRB7 - CNN with GTSRB dataset - Show reports
  Episode 7 : Displaying a jobs report
• GTSRB10 - OAR batch submission
  Bash script for OAR batch submission of GTSRB notebook
• GTSRB11 - SLURM batch script
  Bash script for SLURM batch submission of GTSRB notebooks

Sentiment analysis with word embedding

• IMDB1 - Text embedding with IMDB
  A very classical example of word embedding for text classification (sentiment analysis)
• IMDB2 - Text embedding with IMDB - Reloaded
  Example of reusing a previously saved model
• IMDB3 - Text embedding/LSTM model with IMDB
  Still the same problem, but with a network combining embedding and LSTM

Time series with Recurrent Neural Network (RNN)

• SYNOP1 - Time series with RNN - Preparation of data
  Episode 1 : Data analysis and creation of a usable dataset
• SYNOP2 - Time series with RNN - Try a prediction
  Episode 2 : Training session and first predictions
• SYNOP3 - Time series with RNN - 12h predictions
  Episode 3: Attempt to predict in the longer term

Unsupervised learning with an autoencoder neural network (AE)

• AE1 - AutoEncoder (AE) with MNIST
  Episode 1 : Model construction and Training
• AE2 - AutoEncoder (AE) with MNIST - Analysis
  Episode 2 : Exploring our denoiser

Generative network with Variational Autoencoder (VAE)

• VAE1 - Variational AutoEncoder (VAE) with MNIST
  Building a simple model with the MNIST dataset
• VAE2 - Variational AutoEncoder (VAE) with MNIST - Analysis
  Visualization and analysis of latent space
• VAE3 - About the CelebA dataset
  Presentation of the CelebA dataset and problems related to its size
• VAE6 - Preparation of the CelebA dataset
  Preparation of a clustered dataset, batchable
• VAE7 - Checking the clustered CelebA dataset
  Check the clustered dataset
• VAE8 - Variational AutoEncoder (VAE) with CelebA (small)
  Variational AutoEncoder (VAE) with CelebA (small res. 128x128)
• VAE9 - Variational AutoEncoder (VAE) with CelebA - Analysis
  Exploring latent space of our trained models
• VAE10 - SLURM batch script
  Bash script for SLURM batch submission of VAE notebooks

Miscellaneous

• ACTF1 - Activation functions
  Some activation functions, with their derivatives.
• NP1 - A short introduction to Numpy
  Numpy is an essential tool for the Scientific Python.
• TSB1 - Tensorboard with/from Jupyter
  4 ways to use Tensorboard from the Jupyter environment

Installation

A procedure for configuring and starting Jupyter is available in the Wiki.

Licence

[en] Attribution - NonCommercial - ShareAlike 4.0 International (CC BY-NC-SA 4.0)
[Fr] Attribution - Pas d’Utilisation Commerciale - Partage dans les Mêmes Conditions 4.0 International
See License.
See Disclaimer.

---