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 :
0.6.1 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
| LINR1 |
Linear regression with direct resolution Direct determination of linear regression |
| GRAD1 |
Linear regression with gradient descent An example of gradient descent in the simple case of a linear regression. |
| POLR1 |
Complexity Syndrome Illustration of the problem of complexity with the polynomial regression |
| LOGR1 |
Logistic regression, with sklearn Logistic Regression using Sklearn |
| PER57 |
Perceptron Model 1957 A simple perceptron, with the IRIS dataset. |
| BHP1 |
Regression with a Dense Network (DNN) A Simple regression with a Dense Neural Network (DNN) - BHPD dataset |
| BHP2 |
Regression with a Dense Network (DNN) - Advanced code More advanced example of DNN network code - BHPD dataset |
| MNIST1 |
Simple classification with DNN Example of classification with a fully connected neural network |
| GTS1 |
CNN with GTSRB dataset - Data analysis and preparation Episode 1 : Data analysis and creation of a usable dataset |
| GTS2 |
CNN with GTSRB dataset - First convolutions Episode 2 : First convolutions and first results |
| GTS3 |
CNN with GTSRB dataset - Monitoring Episode 3 : Monitoring and analysing training, managing checkpoints |
| GTS4 |
CNN with GTSRB dataset - Data augmentation Episode 4 : Improving the results with data augmentation |
| GTS5 |
CNN with GTSRB dataset - Full convolutions Episode 5 : A lot of models, a lot of datasets and a lot of results. |
| GTS6 |
Full convolutions as a batch Episode 6 : Run Full convolution notebook as a batch |
| GTS7 |
CNN with GTSRB dataset - Show reports Episode 7 : Displaying a jobs report |
| TSB1 |
Tensorboard with/from Jupyter 4 ways to use Tensorboard from the Jupyter environment |
| GTS8 |
OAR batch submission Bash script for OAR batch submission of GTSRB notebook |
| GTS9 |
Slurm batch submission Bash script Slurm batch submission of GTSRB notebook |
| 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 |
| 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 |
| VAE1 |
Variational AutoEncoder (VAE) with MNIST Episode 1 : Model construction and Training |
| VAE2 |
Variational AutoEncoder (VAE) with MNIST - Analysis Episode 2 : Exploring our latent space |
| VAE3 |
About the CelebA dataset Episode 3 : About the CelebA dataset, a more fun dataset ;-) |
| VAE4 |
Preparation of the CelebA dataset Episode 4 : Preparation of a clustered dataset, batchable |
| VAE5 |
Checking the clustered CelebA dataset Episode 5 : Checking the clustered dataset |
| VAE6 |
Variational AutoEncoder (VAE) with CelebA (small) Episode 6 : Variational AutoEncoder (VAE) with CelebA (small res.) |
| VAE7 |
Variational AutoEncoder (VAE) with CelebA (medium) Episode 7 : Variational AutoEncoder (VAE) with CelebA (medium res.) |
| VAE8 |
Variational AutoEncoder (VAE) with CelebA - Analysis Episode 8 : Exploring latent space of our trained models |
| BASH1 |
OAR batch script Bash script for OAR batch submission of VAE notebook |
| SH2 |
SLURM batch script Bash script for SLURM batch submission of VAE notebooks |
| ACTF1 |
Activation functions Some activation functions, with their derivatives. |
| NP1 |
A short introduction to Numpy Numpy is an essential tool for the Scientific Python. |
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.
