Skip to content
Snippets Groups Projects
Commit 997dbfdd authored by Jean-Luc Parouty's avatar Jean-Luc Parouty
Browse files

Update README

parent a61c2dec
No related branches found
No related tags found
No related merge requests found
Expand all Hide whitespace changes
Inline Side-by-side
Showing
with 22 additions and 3311 deletions
IRIS/01-Simple-Perceptron==done==.ipynb deleted 100644 → 0
+ 0
− 743
View file @ a61c2dec
This diff is collapsed.
LinearReg/01-Linear-Regression==done==.ipynb deleted 100644 → 0
+ 0
− 410
View file @ a61c2dec
This diff is collapsed.
LinearReg/02-Gradient-descent==done==.ipynb deleted 100644 → 0
+ 0
− 722
View file @ a61c2dec
source diff could not be displayed: it is too large. Options to address this: view the blob.
LinearReg/03-Polynomial-Regression==done==.ipynb deleted 100644 → 0
+ 0
− 586
View file @ a61c2dec
This diff is collapsed.
LinearReg/04-Logistic-Regression==done==.ipynb deleted 100644 → 0
+ 0
− 829
View file @ a61c2dec
source diff could not be displayed: it is too large. Options to address this: view the blob.
README.ipynb
+ 12
− 11
View file @ 997dbfdd
%% Cell type:code id:7b719e4f tags:
%% Cell type:code id:b1c7f34f tags:
``` python
from IPython.display import display,Markdown
display(Markdown(open('README.md', 'r').read()))
#
# This README is visible under Jupiter LAb ! :-)
```
%% Output
<a name="top"></a>
[<img width="600px" src="fidle/img/00-Fidle-titre-01.svg"></img>](#top)
<!-- --------------------------------------------------- -->
<!-- To correctly view this README under Jupyter Lab -->
<!-- Open the notebook: README.ipynb! -->
<!-- --------------------------------------------------- -->
## About Fidle
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 Resinfo/SARI and DevLOG CNRS 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, see **https://fidle.cnrs.fr** :
- **[Fidle site](https://fidle.cnrs.fr)**
- **[Presentation of the training](https://fidle.cnrs.fr/presentation)**
- **[Program 2021/2022](https://fidle.cnrs.fr/programme)**
- [Subscribe to the list](https://fidle.cnrs.fr/listeinfo), to stay informed !
- [Find us on youtube](https://fidle.cnrs.fr/youtube)
For more information, you can contact us at :
[<img width="200px" style="vertical-align:middle" src="fidle/img/00-Mail_contact.svg"></img>](#top)
Current Version : <!-- VERSION_BEGIN -->
**2.0.28**
**2.0.29**
<!-- VERSION_END -->
## Course materials
| | | |
|:--:|:--:|:--:|
| **[<img width="50px" src="fidle/img/00-Fidle-pdf.svg"></img><br>Course slides](https://fidle.cnrs.fr/supports)**<br>The course in pdf format<br>(12 Mo)| **[<img width="50px" src="fidle/img/00-Notebooks.svg"></img><br>Notebooks](https://fidle.cnrs.fr/notebooks)**<br> &nbsp;&nbsp;&nbsp;&nbsp;Get a Zip or clone this repository &nbsp;&nbsp;&nbsp;&nbsp;<br>(40 Mo)| **[<img width="50px" src="fidle/img/00-Datasets-tar.svg"></img><br>Datasets](https://fidle.cnrs.fr/fidle-datasets.tar)**<br>All the needed datasets<br>(1.2 Go)|
| | | | |
|:--:|:--:|:--:|:--:|
| **[<img width="50px" src="fidle/img/00-Fidle-pdf.svg"></img><br>Course slides](https://fidle.cnrs.fr/supports)**<br>The course in pdf format<br>(12 Mo)| **[<img width="50px" src="fidle/img/00-Notebooks.svg"></img><br>Notebooks](https://fidle.cnrs.fr/notebooks)**<br> &nbsp;&nbsp;&nbsp;&nbsp;Get a Zip or clone this repository &nbsp;&nbsp;&nbsp;&nbsp;<br>(40 Mo)| **[<img width="50px" src="fidle/img/00-Datasets-tar.svg"></img><br>Datasets](https://fidle.cnrs.fr/fidle-datasets.tar)**<br>All the needed datasets<br>(1.2 Go)|**[<img width="50px" src="fidle/img/00-Videos.svg"></img><br>Videos](https://fidle.cnrs.fr/youtube)**<br>&nbsp;&nbsp;&nbsp;&nbsp;Our Youtube channel&nbsp;&nbsp;&nbsp;&nbsp;<br>&nbsp;|
Have a look about **[How to get and install](https://fidle.cnrs.fr/installation)** these notebooks and datasets.
## Jupyter notebooks
<!-- INDEX_BEGIN -->
### Linear and logistic regression
- **[LINR1](LinearReg/01-Linear-Regression.ipynb)** - [Linear regression with direct resolution](LinearReg/01-Linear-Regression.ipynb)
Low-level implementation, using numpy, of a direct resolution for a linear regression
- **[GRAD1](LinearReg/02-Gradient-descent.ipynb)** - [Linear regression with gradient descent](LinearReg/02-Gradient-descent.ipynb)
Low level implementation of a solution by gradient descent. Basic and stochastic approach.
- **[POLR1](LinearReg/03-Polynomial-Regression.ipynb)** - [Complexity Syndrome](LinearReg/03-Polynomial-Regression.ipynb)
Illustration of the problem of complexity with the polynomial regression
- **[LOGR1](LinearReg/04-Logistic-Regression.ipynb)** - [Logistic regression](LinearReg/04-Logistic-Regression.ipynb)
Simple example of logistic regression with a sklearn solution
### Perceptron Model 1957
- **[PER57](IRIS/01-Simple-Perceptron.ipynb)** - [Perceptron Model 1957](IRIS/01-Simple-Perceptron.ipynb)
Example of use of a Perceptron, with sklearn and IRIS dataset of 1936 !
### Basic regression using DNN
- **[BHPD1](BHPD/01-DNN-Regression.ipynb)** - [Regression with a Dense Network (DNN)](BHPD/01-DNN-Regression.ipynb)
Simple example of a regression with the dataset Boston Housing Prices Dataset (BHPD)
- **[BHPD2](BHPD/02-DNN-Regression-Premium.ipynb)** - [Regression with a Dense Network (DNN) - Advanced code](BHPD/02-DNN-Regression-Premium.ipynb)
A more advanced implementation of the precedent example
### Basic classification using a DNN
- **[MNIST1](MNIST/01-DNN-MNIST.ipynb)** - [Simple classification with DNN](MNIST/01-DNN-MNIST.ipynb)
An example of classification using a dense neural network for the famous MNIST dataset
- **[MNIST2](MNIST/02-CNN-MNIST.ipynb)** - [Simple classification with CNN](MNIST/02-CNN-MNIST.ipynb)
An example of classification using a convolutional neural network for the famous MNIST dataset
### Images classification with Convolutional Neural Networks (CNN)
- **[GTSRB1](GTSRB/01-Preparation-of-data.ipynb)** - [Dataset analysis and preparation](GTSRB/01-Preparation-of-data.ipynb)
Episode 1 : Analysis of the GTSRB dataset and creation of an enhanced dataset
- **[GTSRB2](GTSRB/02-First-convolutions.ipynb)** - [First convolutions](GTSRB/02-First-convolutions.ipynb)
Episode 2 : First convolutions and first classification of our traffic signs
- **[GTSRB3](GTSRB/03-Tracking-and-visualizing.ipynb)** - [Training monitoring](GTSRB/03-Tracking-and-visualizing.ipynb)
Episode 3 : Monitoring, analysis and check points during a training session
- **[GTSRB4](GTSRB/04-Data-augmentation.ipynb)** - [Data augmentation ](GTSRB/04-Data-augmentation.ipynb)
Episode 4 : Adding data by data augmentation when we lack it, to improve our results
- **[GTSRB5](GTSRB/05-Full-convolutions.ipynb)** - [Full convolutions](GTSRB/05-Full-convolutions.ipynb)
Episode 5 : A lot of models, a lot of datasets and a lot of results.
- **[GTSRB6](GTSRB/06-Notebook-as-a-batch.ipynb)** - [Full convolutions as a batch](GTSRB/06-Notebook-as-a-batch.ipynb)
Episode 6 : To compute bigger, use your notebook in batch mode
- **[GTSRB7](GTSRB/07-Show-report.ipynb)** - [Batch reports](GTSRB/07-Show-report.ipynb)
Episode 7 : Displaying our jobs report, and the winner is...
- **[GTSRB10](GTSRB/batch_oar.sh)** - [OAR batch script submission](GTSRB/batch_oar.sh)
Bash script for an OAR batch submission of an ipython code
- **[GTSRB11](GTSRB/batch_slurm.sh)** - [SLURM batch script](GTSRB/batch_slurm.sh)
Bash script for a Slurm batch submission of an ipython code
### Sentiment analysis with word embedding
- **[IMDB1](IMDB/01-One-hot-encoding.ipynb)** - [Sentiment analysis with hot-one encoding](IMDB/01-One-hot-encoding.ipynb)
A basic example of sentiment analysis with sparse encoding, using a dataset from Internet Movie Database (IMDB)
- **[IMDB2](IMDB/02-Keras-embedding.ipynb)** - [Sentiment analysis with text embedding](IMDB/02-Keras-embedding.ipynb)
A very classical example of word embedding with a dataset from Internet Movie Database (IMDB)
- **[IMDB3](IMDB/03-Prediction.ipynb)** - [Reload and reuse a saved model](IMDB/03-Prediction.ipynb)
Retrieving a saved model to perform a sentiment analysis (movie review)
- **[IMDB4](IMDB/04-Show-vectors.ipynb)** - [Reload embedded vectors](IMDB/04-Show-vectors.ipynb)
Retrieving embedded vectors from our trained model
- **[IMDB5](IMDB/05-LSTM-Keras.ipynb)** - [Sentiment analysis with a RNN network](IMDB/05-LSTM-Keras.ipynb)
Still the same problem, but with a network combining embedding and RNN
### Time series with Recurrent Neural Network (RNN)
- **[LADYB1](SYNOP/LADYB1-Ladybug.ipynb)** - [Prediction of a 2D trajectory via RNN](SYNOP/LADYB1-Ladybug.ipynb)
Artificial dataset generation and prediction attempt via a recurrent network
- **[SYNOP1](SYNOP/SYNOP1-Preparation-of-data.ipynb)** - [Preparation of data](SYNOP/SYNOP1-Preparation-of-data.ipynb)
Episode 1 : Data analysis and preparation of a usuable meteorological dataset (SYNOP)
- **[SYNOP2](SYNOP/SYNOP2-First-predictions.ipynb)** - [First predictions at 3h](SYNOP/SYNOP2-First-predictions.ipynb)
Episode 2 : RNN training session for weather prediction attempt at 3h
- **[SYNOP3](SYNOP/SYNOP3-12h-predictions.ipynb)** - [12h predictions](SYNOP/SYNOP3-12h-predictions.ipynb)
Episode 3: Attempt to predict in a more longer term
### Unsupervised learning with an autoencoder neural network (AE)
- **[AE1](AE/01-Prepare-MNIST-dataset.ipynb)** - [Prepare a noisy MNIST dataset](AE/01-Prepare-MNIST-dataset.ipynb)
Episode 1: Preparation of a noisy MNIST dataset
- **[AE2](AE/02-AE-with-MNIST.ipynb)** - [Building and training an AE denoiser model](AE/02-AE-with-MNIST.ipynb)
Episode 1 : Construction of a denoising autoencoder and training of it with a noisy MNIST dataset.
- **[AE3](AE/03-AE-with-MNIST-post.ipynb)** - [Playing with our denoiser model](AE/03-AE-with-MNIST-post.ipynb)
Episode 2 : Using the previously trained autoencoder to denoise data
- **[AE4](AE/04-ExtAE-with-MNIST.ipynb)** - [Denoiser and classifier model](AE/04-ExtAE-with-MNIST.ipynb)
Episode 4 : Construction of a denoiser and classifier model
- **[AE5](AE/05-ExtAE-with-MNIST.ipynb)** - [Advanced denoiser and classifier model](AE/05-ExtAE-with-MNIST.ipynb)
Episode 5 : Construction of an advanced denoiser and classifier model
### Generative network with Variational Autoencoder (VAE)
- **[VAE1](VAE/01-VAE-with-MNIST.ipynb)** - [First VAE, using functional API (MNIST dataset)](VAE/01-VAE-with-MNIST.ipynb)
Construction and training of a VAE, using functional APPI, with a latent space of small dimension.
- **[VAE2](VAE/02-VAE-with-MNIST.ipynb)** - [VAE, using a custom model class (MNIST dataset)](VAE/02-VAE-with-MNIST.ipynb)
Construction and training of a VAE, using model subclass, with a latent space of small dimension.
- **[VAE3](VAE/03-VAE-with-MNIST-post.ipynb)** - [Analysis of the VAE's latent space of MNIST dataset](VAE/03-VAE-with-MNIST-post.ipynb)
Visualization and analysis of the VAE's latent space of the dataset MNIST
- **[VAE5](VAE/05-About-CelebA.ipynb)** - [Another game play : About the CelebA dataset](VAE/05-About-CelebA.ipynb)
Episode 1 : Presentation of the CelebA dataset and problems related to its size
- **[VAE6](VAE/06-Prepare-CelebA-datasets.ipynb)** - [Generation of a clustered dataset](VAE/06-Prepare-CelebA-datasets.ipynb)
Episode 2 : Analysis of the CelebA dataset and creation of an clustered and usable dataset
- **[VAE7](VAE/07-Check-CelebA.ipynb)** - [Checking the clustered dataset](VAE/07-Check-CelebA.ipynb)
Episode : 3 Clustered dataset verification and testing of our datagenerator
- **[VAE8](VAE/08-VAE-with-CelebA.ipynb)** - [Training session for our VAE](VAE/08-VAE-with-CelebA.ipynb)
Episode 4 : Training with our clustered datasets in notebook or batch mode
- **[VAE9](VAE/09-VAE-with-CelebA-post.ipynb)** - [Data generation from latent space](VAE/09-VAE-with-CelebA-post.ipynb)
Episode 5 : Exploring latent space to generate new data
- **[VAE10](VAE/batch_slurm.sh)** - [SLURM batch script](VAE/batch_slurm.sh)
Bash script for SLURM batch submission of VAE8 notebooks
### Generative Adversarial Networks (GANs)
- **[DCGAN01](DCGAN/01-DCGAN-Draw-me-a-sheep.ipynb)** - [A first DCGAN to Draw a Sheep](DCGAN/01-DCGAN-Draw-me-a-sheep.ipynb)
Episode 1 : Draw me a sheep, revisited with a DCGAN
### Miscellaneous
- **[ACTF1](Misc/Activation-Functions.ipynb)** - [Activation functions](Misc/Activation-Functions.ipynb)
Some activation functions, with their derivatives.
- **[NP1](Misc/Numpy.ipynb)** - [A short introduction to Numpy](Misc/Numpy.ipynb)
Numpy is an essential tool for the Scientific Python.
- **[SCRATCH1](Misc/Scratchbook.ipynb)** - [Scratchbook](Misc/Scratchbook.ipynb)
A scratchbook for small examples
- **[TSB1](Misc/Using-Tensorboard.ipynb)** - [Tensorboard with/from Jupyter ](Misc/Using-Tensorboard.ipynb)
4 ways to use Tensorboard from the Jupyter environment
<!-- INDEX_END -->
## Installation
Have a look about **[How to get and install](https://fidle.cnrs.fr/installation)** these notebooks and datasets.
## Licence
[<img width="100px" src="fidle/img/00-fidle-CC BY-NC-SA.svg"></img>](https://creativecommons.org/licenses/by-nc-sa/4.0/)
\[en\] 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](https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode).
See [Disclaimer](https://creativecommons.org/licenses/by-nc-sa/4.0/#).
----
[<img width="80px" src="fidle/img/00-Fidle-logo-01.svg"></img>](#top)
......
README.md
+ 6
− 5
View file @ 997dbfdd
......@@ -20,24 +20,25 @@ The objectives of this training are :
- Apprehend the **academic computing environments** Tier-2 or Tier-1 with powerfull GPU
For more information, see **https://fidle.cnrs.fr** :
- **[Fidle site](https://fidle.cnrs.fr)**
- **[Presentation of the training](https://fidle.cnrs.fr/presentation)**
- **[Program 2021/2022](https://fidle.cnrs.fr/programme)**
- [Subscribe to the list](https://fidle.cnrs.fr/listeinfo), to stay informed !
- [Find us on youtube](https://fidle.cnrs.fr/youtube)
For more information, you can contact us at :
For more information, you can contact us at :
[<img width="200px" style="vertical-align:middle" src="fidle/img/00-Mail_contact.svg"></img>](#top)
Current Version : <!-- VERSION_BEGIN -->
**2.0.28**
**2.0.29**
<!-- VERSION_END -->
## Course materials
| | | |
|:--:|:--:|:--:|
| **[<img width="50px" src="fidle/img/00-Fidle-pdf.svg"></img><br>Course slides](https://fidle.cnrs.fr/supports)**<br>The course in pdf format<br>(12 Mo)| **[<img width="50px" src="fidle/img/00-Notebooks.svg"></img><br>Notebooks](https://fidle.cnrs.fr/notebooks)**<br> &nbsp;&nbsp;&nbsp;&nbsp;Get a Zip or clone this repository &nbsp;&nbsp;&nbsp;&nbsp;<br>(40 Mo)| **[<img width="50px" src="fidle/img/00-Datasets-tar.svg"></img><br>Datasets](https://fidle.cnrs.fr/fidle-datasets.tar)**<br>All the needed datasets<br>(1.2 Go)|
| | | | |
|:--:|:--:|:--:|:--:|
| **[<img width="50px" src="fidle/img/00-Fidle-pdf.svg"></img><br>Course slides](https://fidle.cnrs.fr/supports)**<br>The course in pdf format<br>(12 Mo)| **[<img width="50px" src="fidle/img/00-Notebooks.svg"></img><br>Notebooks](https://fidle.cnrs.fr/notebooks)**<br> &nbsp;&nbsp;&nbsp;&nbsp;Get a Zip or clone this repository &nbsp;&nbsp;&nbsp;&nbsp;<br>(40 Mo)| **[<img width="50px" src="fidle/img/00-Datasets-tar.svg"></img><br>Datasets](https://fidle.cnrs.fr/fidle-datasets.tar)**<br>All the needed datasets<br>(1.2 Go)|**[<img width="50px" src="fidle/img/00-Videos.svg"></img><br>Videos](https://fidle.cnrs.fr/youtube)**<br>&nbsp;&nbsp;&nbsp;&nbsp;Our Youtube channel&nbsp;&nbsp;&nbsp;&nbsp;<br>&nbsp;|
Have a look about **[How to get and install](https://fidle.cnrs.fr/installation)** these notebooks and datasets.
......
fidle/02-running-ci-tests.ipynb
+ 2
− 2
View file @ 997dbfdd
%% Cell type:markdown id: tags:
<img width="800px" src="../fidle/img/00-Fidle-header-01.svg"></img>
# Gestion des tests d'intégration continue
**La liste des notebooks a éxécuter** et de leurs paramètres (override) est définie dans un **profile**.\
Un **rapport d'éxécution** est généré durant l'éxécution des tests.
## Step 1 - Init
%% Cell type:code id: tags:
```
import cookci
import os
import pwk
datasets_dir = pwk.init('RUNCI')
```
%% Cell type:markdown id: tags:
## Step 2 - Profile and parameters
`profile_name`: ci profile name - see en ./ci
`reset`: reset or not the catalog of results
`filters`: regex to define witch notebook will be run, examples :
- `.*`
- `Nb_GTSRB.*|Nb_AE.*`
- `Nb_VAE3`
%% Cell type:code id: tags:
```
profile_name = './ci/small_cpu.yml'
reset = False
filter = 'Nb_LINR1'
reset = True
filter = '.*'
pwk.override('profile_name', 'reset', 'filter')
```
%% Cell type:markdown id: tags:
## Step 3 - Run it
%% Cell type:code id: tags:
```
cookci.run_profile(profile_name, reset, filter)
cookci.build_ci_report(profile_name)
```
%% Cell type:code id: tags:
```
%%bash
# tree ./run/ci
# find .. -name "*==ci==.*" -ls | sort -k11
# rm $(find .. -name "*==ci==.ipynb")
# rm $(find .. -name "*==ci==.html")
```
%% Cell type:markdown id: tags:
---
<img width="80px" src="../fidle/img/00-Fidle-logo-01.svg"></img>
......
fidle/config.py
+ 1
− 1
View file @ 997dbfdd
......@@ -14,7 +14,7 @@
# ---- Version -----------------------------------------------------
#
VERSION = '2.0.28'
VERSION = '2.0.29'
# ---- Default notebook name ---------------------------------------
#
......
fidle/img/00-Videos.svg 0 → 100644
+ 1
− 0
View file @ 997dbfdd
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 37.5373 34.8434"><path d="M19.8236,8.3758V.9771H9.6132A3.2082,3.2082,0,0,0,6.4144,4.1759V27.6783a3.2081,3.2081,0,0,0,3.1988,3.1988H27.1747a3.2082,3.2082,0,0,0,3.1988-3.1988V11.5746H23.0224A3.2082,3.2082,0,0,1,19.8236,8.3758Z" style="fill:#fff;stroke:#000;stroke-linejoin:round;stroke-width:1.95428428707763px"/><line x1="19.8236" y1="0.9771" x2="30.3973" y2="11.5508" style="fill:#fff;stroke:#000;stroke-linejoin:round;stroke-width:1.95428428707763px"/><path d="M28.3957,30.3053H20.6325a1.1822,1.1822,0,0,1-1.1807-1.1806V22.9171a1.184,1.184,0,0,1,1.1753-1.1811l7.7686-.0352V18.298l8.5854,7.6367-8.5854,8.0435Z" style="fill:#e12229"/><path d="M28.7705,19.1336l7.6544,6.8084-7.6544,7.1711V29.93H20.6327a.8057.8057,0,0,1-.8058-.8056V22.9169a.8057.8057,0,0,1,.8021-.8057l8.1415-.0367V19.1336m-.75-1.6709v3.8652l-7.3949.0333a1.5589,1.5589,0,0,0-1.5487,1.5557v6.2078A1.5575,1.5575,0,0,0,20.6327,30.68h7.3878v4.1631l1.2628-1.183,7.6544-7.171.6-.5618-.6139-.546L29.269,18.5731l-1.2485-1.11Z" style="fill:#fff"/><rect x="5.252" y="9.659" width="7.0866" height="7.0866" style="fill:#fff"/><path d="M8.9294,20.0123a30.3254,30.3254,0,0,1-4.9673-.4189C1.8185,19.1344.5,17.7316.5,15.9279V10.3771C.5,8.5739,1.8073,7.18,3.9108,6.7394a30.3865,30.3865,0,0,1,9.9863-.0039c2.107.3872,3.4629,1.8193,3.4629,3.6494v5.5513a3.82,3.82,0,0,1-3.436,3.6631,30.501,30.501,0,0,1-4.9937.413Zm-1.482-4.5947,3.6187-2.2036.06-.0449-3.6787-2.207Z" style="fill:#ed1c24"/><path d="M8.9142,6.8244a29.8856,29.8856,0,0,1,4.9008.4044A3.323,3.323,0,0,1,16.86,10.385v5.5511a3.3355,3.3355,0,0,1-3.0293,3.172,29.9807,29.9807,0,0,1-4.9008.4044A29.6913,29.6913,0,0,1,4.0452,19.1C2.1578,18.6957,1,17.5142,1,15.9281v-5.551c0-1.5623,1.1578-2.76,3.0134-3.1483a29.8874,29.8874,0,0,1,4.9008-.4044M7.3518,15.96a.3812.3812,0,0,0,.1985-.0557l3.965-2.379v-.0238a.4046.4046,0,0,0,0-.682L7.55,10.44a.43.43,0,0,0-.4045,0,.4127.4127,0,0,0-.1982.349v4.7581a.4126.4126,0,0,0,.1982.3648.4548.4548,0,0,0,.1983.0476l.0077,0M8.9142,5.8244A30.9912,30.9912,0,0,0,3.85,6.2423C1.4949,6.7344,0,8.3544,0,10.3771v5.551c0,2.0528,1.47,3.6428,3.8356,4.15a30.8109,30.8109,0,0,0,5.0929.4346,31.0686,31.0686,0,0,0,5.0661-.418c2.3571-.4467,3.8656-2.0774,3.8656-4.1584V10.385c0-2.0833-1.5169-3.7082-3.8644-4.14a31.02,31.02,0,0,0-5.0816-.4209ZM7.9472,14.5l0-2.656L10.16,13.1723,7.9472,14.5Z" style="fill:#fff"/></svg>
\ No newline at end of file
fidle/img/00-fidle-header-02.svg deleted 100755 → 0
+ 0
− 1
View file @ a61c2dec
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 280.2979 16.1665"><title>00-fidle-header-02</title><g id="Calque_2" data-name="Calque 2"><g id="Calque_4" data-name="Calque 4"><path d="M1.26,2.8882h5.874v1.26H2.751V8.1943H6.8145V9.4365H2.751v5.4126H1.26Z" transform="translate(-1.2598 -2.3384)"/><path d="M15.5967,10.5015c0,3.2119-2.0059,4.5249-3.8506,4.5249-2.0947,0-3.7275-1.6148-3.7275-4.4185,0-2.9458,1.7568-4.5254,3.8515-4.5254C14.0527,6.0825,15.5967,7.7686,15.5967,10.5015Zm-6.0518.0708c0,1.7392.834,3.3183,2.2715,3.3183,1.4024,0,2.2539-1.5971,2.2539-3.354,0-1.4194-.5859-3.3-2.2539-3.3C10.1836,7.2363,9.5449,9.0283,9.5449,10.5723Z" transform="translate(-1.2598 -2.3384)"/><path d="M17.4209,8.7979c0-.9229-.0352-1.775-.07-2.5376h1.33l.0537,1.5791h.0537a2.4525,2.4525,0,0,1,2.2178-1.7569,2.6819,2.6819,0,0,1,.3906.0357v1.455a1.8752,1.8752,0,0,0-.4619-.0356,2.0647,2.0647,0,0,0-1.9522,1.9346,3.2524,3.2524,0,0,0-.07.7451v4.6318H17.4209Z" transform="translate(-1.2598 -2.3384)"/><path d="M22.7969,8.5493c0-.9228-.0362-1.58-.0713-2.289h1.3135l.0888,1.2954h.0352A2.6976,2.6976,0,0,1,26.63,6.0825,2.313,2.313,0,0,1,28.8662,7.68h.0352a3.1007,3.1007,0,0,1,.94-1.065,2.5755,2.5755,0,0,1,1.668-.5322c1.1533,0,2.6084.7808,2.6084,3.5137v5.2529H32.6455V9.8447c0-1.5083-.4785-2.52-1.668-2.52A1.8255,1.8255,0,0,0,29.31,8.6914a2.6672,2.6672,0,0,0-.1065.7808v5.3769H27.7305V9.561c0-1.2422-.4795-2.2363-1.6153-2.2363A1.9176,1.9176,0,0,0,24.376,8.833a2.6355,2.6355,0,0,0-.1065.7632v5.2529H22.7969Z" transform="translate(-1.2598 -2.3384)"/><path d="M40.8223,14.8491,40.6982,13.82h-.0537a2.7816,2.7816,0,0,1-2.36,1.2066A2.3594,2.3594,0,0,1,35.8359,12.56c0-2.0943,1.81-3.1768,4.72-3.1592V9.188c0-.834-.23-1.9873-1.792-1.97a3.6244,3.6244,0,0,0-1.9873.5859L36.44,6.7749A5.0212,5.0212,0,0,1,39.03,6.0825c2.36,0,3.0166,1.5972,3.0166,3.39v3.354a14.2009,14.2009,0,0,0,.124,2.0229Zm-.2481-4.4009c-1.3847-.018-3.23.23-3.23,1.9522a1.3141,1.3141,0,0,0,1.331,1.49,1.8725,1.8725,0,0,0,1.8457-1.3838,1.57,1.57,0,0,0,.0537-.497Z" transform="translate(-1.2598 -2.3384)"/><path d="M46.1074,3.8467V6.26H48.166V7.4136H46.1074v4.7558c0,1.0826.32,1.5972,1.083,1.5972a3.0043,3.0043,0,0,0,.7989-.0889l.07,1.1358a3.3042,3.3042,0,0,1-1.2774.1953,2.0434,2.0434,0,0,1-1.5791-.6211,3.175,3.175,0,0,1-.5859-2.2007V7.4136H43.375V6.26h1.2422V4.2549Z" transform="translate(-1.2598 -2.3384)"/><path d="M51.4121,3.9a.8937.8937,0,0,1-.94.94.8713.8713,0,0,1-.8867-.94.9139.9139,0,1,1,1.8271,0Zm-1.668,10.9492V6.26h1.5088v8.5888Z" transform="translate(-1.2598 -2.3384)"/><path d="M60.6563,10.5015c0,3.2119-2.0049,4.5249-3.8506,4.5249-2.0938,0-3.7266-1.6148-3.7266-4.4185,0-2.9458,1.7568-4.5254,3.8506-4.5254C59.1123,6.0825,60.6563,7.7686,60.6563,10.5015Zm-6.0508.0708c0,1.7392.834,3.3183,2.2715,3.3183,1.4013,0,2.2539-1.5971,2.2539-3.354,0-1.4194-.586-3.3-2.2539-3.3C55.2441,7.2363,54.6055,9.0283,54.6055,10.5723Z" transform="translate(-1.2598 -2.3384)"/><path d="M62.4814,8.5493c0-.9228-.0351-1.58-.07-2.289h1.33l.0713,1.2954h.0537A2.8831,2.8831,0,0,1,66.44,6.0825c1.1884,0,2.7324.7632,2.7324,3.46v5.3061h-1.49V9.7207c0-1.2778-.4257-2.396-1.7392-2.396a1.9924,1.9924,0,0,0-1.8633,1.544,2.936,2.936,0,0,0-.0889.7456v5.2348H62.4814Z" transform="translate(-1.2598 -2.3384)"/><path d="M76.5674,2.8882V14.8491h-1.49V2.8882Z" transform="translate(-1.2598 -2.3384)"/><path d="M79.1572,8.5493c0-.9228-.0361-1.58-.0713-2.289H80.417l.0713,1.2954h.0527a2.8843,2.8843,0,0,1,2.5733-1.4732c1.1894,0,2.7334.7632,2.7334,3.46v5.3061H84.3564V9.7207c0-1.2778-.4257-2.396-1.7392-2.396a1.9942,1.9942,0,0,0-1.8633,1.544,2.982,2.982,0,0,0-.0889.7456v5.2348H79.1572Z" transform="translate(-1.2598 -2.3384)"/><path d="M89.9609,3.8467V6.26H92.02V7.4136H89.9609v4.7558c0,1.0826.32,1.5972,1.083,1.5972a3.0037,3.0037,0,0,0,.7989-.0889l.07,1.1358a3.3042,3.3042,0,0,1-1.2774.1953,2.0434,2.0434,0,0,1-1.5791-.6211,3.175,3.175,0,0,1-.5859-2.2007V7.4136H87.2285V6.26h1.2422V4.2549Z" transform="translate(-1.2598 -2.3384)"/><path d="M93.5977,8.7979c0-.9229-.0352-1.775-.07-2.5376h1.33l.0537,1.5791h.0537a2.4525,2.4525,0,0,1,2.2178-1.7569,2.6819,2.6819,0,0,1,.3906.0357v1.455a1.8744,1.8744,0,0,0-.4619-.0356,2.0645,2.0645,0,0,0-1.9521,1.9346,3.2468,3.2468,0,0,0-.07.7451v4.6318H93.5977Z" transform="translate(-1.2598 -2.3384)"/><path d="M105.8057,10.5015c0,3.2119-2.0059,4.5249-3.8506,4.5249-2.0947,0-3.7276-1.6148-3.7276-4.4185,0-2.9458,1.7569-4.5254,3.8516-4.5254C104.2617,6.0825,105.8057,7.7686,105.8057,10.5015Zm-6.0518.0708c0,1.7392.834,3.3183,2.2715,3.3183,1.4023,0,2.2539-1.5971,2.2539-3.354,0-1.4194-.5859-3.3-2.2539-3.3C100.3926,7.2363,99.7539,9.0283,99.7539,10.5723Z" transform="translate(-1.2598 -2.3384)"/><path d="M114.374,2.3384V12.6841c0,.71.0352,1.5972.0713,2.165h-1.331l-.0713-1.3662H112.99a2.7763,2.7763,0,0,1-2.5732,1.5435c-1.8994,0-3.3369-1.7036-3.3369-4.3653,0-2.9282,1.6328-4.5786,3.4785-4.5786a2.4963,2.4963,0,0,1,2.2891,1.2246h.0361V2.3384Zm-1.49,7.3467a4.09,4.09,0,0,0-.0537-.6387A2.066,2.066,0,0,0,110.86,7.29c-1.4727,0-2.254,1.4726-2.254,3.3007,0,1.7744.7452,3.2119,2.2188,3.2119a2.07,2.07,0,0,0,1.9873-1.7392,2.454,2.454,0,0,0,.0713-.6387Z" transform="translate(-1.2598 -2.3384)"/><path d="M123.3154,12.5068c0,.9048.0352,1.668.0713,2.3423h-1.3135l-.0888-1.26h-.0352a2.8975,2.8975,0,0,1-2.5381,1.437c-1.4023,0-2.6972-.8692-2.6972-3.62V6.26h1.49v4.8974c0,1.544.4258,2.6265,1.6865,2.6265a1.9726,1.9726,0,0,0,1.81-1.3487,2.6793,2.6793,0,0,0,.124-.7983V6.26h1.4912Z" transform="translate(-1.2598 -2.3384)"/><path d="M131.2627,14.5649a5.0916,5.0916,0,0,1-2.165.4439c-2.36,0-3.94-1.686-3.94-4.3652a4.2058,4.2058,0,0,1,4.26-4.543,4.4554,4.4554,0,0,1,1.8809.39l-.337,1.1714a3.42,3.42,0,0,0-1.5615-.355c-1.793,0-2.7158,1.5259-2.7158,3.2652,0,2.0053,1.1182,3.2119,2.6973,3.2119a3.8423,3.8423,0,0,0,1.6328-.355Z" transform="translate(-1.2598 -2.3384)"/><path d="M134.9512,3.8467V6.26H137.01V7.4136h-2.0586v4.7558c0,1.0826.3193,1.5972,1.082,1.5972a2.9974,2.9974,0,0,0,.7988-.0889l.0713,1.1358a3.3107,3.3107,0,0,1-1.2773.1953,2.0457,2.0457,0,0,1-1.58-.6211,3.1753,3.1753,0,0,1-.585-2.2007V7.4136h-1.2421V6.26h1.2421V4.2549Z" transform="translate(-1.2598 -2.3384)"/><path d="M140.2549,3.9a.8937.8937,0,0,1-.94.94.8713.8713,0,0,1-.8868-.94.914.914,0,1,1,1.8272,0Zm-1.668,10.9492V6.26h1.5088v8.5888Z" transform="translate(-1.2598 -2.3384)"/><path d="M149.499,10.5015c0,3.2119-2.0049,4.5249-3.8506,4.5249-2.0937,0-3.7265-1.6148-3.7265-4.4185,0-2.9458,1.7568-4.5254,3.8506-4.5254C147.9551,6.0825,149.499,7.7686,149.499,10.5015Zm-6.0508.0708c0,1.7392.834,3.3183,2.2715,3.3183,1.4014,0,2.2539-1.5971,2.2539-3.354,0-1.4194-.5859-3.3-2.2539-3.3C144.0869,7.2363,143.4482,9.0283,143.4482,10.5723Z" transform="translate(-1.2598 -2.3384)"/><path d="M151.3242,8.5493c0-.9228-.0351-1.58-.07-2.289h1.33l.0713,1.2954h.0537a2.8831,2.8831,0,0,1,2.5732-1.4732c1.1885,0,2.7324.7632,2.7324,3.46v5.3061h-1.49V9.7207c0-1.2778-.4258-2.396-1.7392-2.396a1.9924,1.9924,0,0,0-1.8633,1.544,2.936,2.936,0,0,0-.0889.7456v5.2348h-1.5088Z" transform="translate(-1.2598 -2.3384)"/><path d="M168.2148,14.8491l-.124-1.0293h-.0537a2.7816,2.7816,0,0,1-2.36,1.2066,2.3594,2.3594,0,0,1-2.4483-2.4663c0-2.0943,1.81-3.1768,4.72-3.1592V9.188c0-.834-.23-1.9873-1.7919-1.97a3.625,3.625,0,0,0-1.9874.5859l-.3369-1.0293a5.0216,5.0216,0,0,1,2.5909-.6924c2.36,0,3.0166,1.5972,3.0166,3.39v3.354a14.2009,14.2009,0,0,0,.124,2.0229Zm-.248-4.4009c-1.3848-.018-3.2305.23-3.2305,1.9522a1.3142,1.3142,0,0,0,1.3311,1.49,1.8726,1.8726,0,0,0,1.8457-1.3838,1.57,1.57,0,0,0,.0537-.497Z" transform="translate(-1.2598 -2.3384)"/><path d="M178.3447,12.5068c0,.9048.0362,1.668.0713,2.3423h-1.3135l-.0888-1.26h-.0352a2.8946,2.8946,0,0,1-2.5371,1.437c-1.4023,0-2.6982-.8692-2.6982-3.62V6.26h1.4912v4.8974c0,1.544.4258,2.6265,1.6855,2.6265a1.9729,1.9729,0,0,0,1.8106-1.3487,2.7118,2.7118,0,0,0,.124-.7983V6.26h1.49Z" transform="translate(-1.2598 -2.3384)"/><path d="M184.2861,3.0479A16.83,16.83,0,0,1,187.1436,2.8,5.9363,5.9363,0,0,1,191.3672,4.13a5.6506,5.6506,0,0,1,1.668,4.4546,6.55,6.55,0,0,1-1.6329,4.7734,6.4655,6.4655,0,0,1-4.6845,1.58,19.1994,19.1994,0,0,1-2.4317-.1245Zm1.49,10.6123a8.7068,8.7068,0,0,0,1.2422.0708c2.7685,0,4.455-1.6148,4.455-5.0928.0176-2.8926-1.3847-4.6319-4.2422-4.6319a7.517,7.517,0,0,0-1.455.1241Z" transform="translate(-1.2598 -2.3384)"/><path d="M195.835,10.7852c.0351,2.2714,1.2773,3.0522,2.6621,3.0522a5.0467,5.0467,0,0,0,2.0937-.4082l.2666,1.0825a6.2338,6.2338,0,0,1-2.5732.4971c-2.4668,0-3.9043-1.7393-3.9043-4.33,0-2.644,1.4375-4.5962,3.709-4.5962,2.4843,0,3.1943,2.2715,3.1943,3.9575a6.9054,6.9054,0,0,1-.0361.7452Zm4.0107-1.0826c.0176-1.2065-.48-2.52-1.8994-2.52-1.3838,0-1.9873,1.4019-2.0938,2.52Z" transform="translate(-1.2598 -2.3384)"/><path d="M203.9961,10.7852c.0352,2.2714,1.2773,3.0522,2.6611,3.0522a5.0492,5.0492,0,0,0,2.0948-.4082l.2656,1.0825a6.2339,6.2339,0,0,1-2.5733.4971c-2.4668,0-3.9043-1.7393-3.9043-4.33,0-2.644,1.4375-4.5962,3.709-4.5962,2.4844,0,3.1944,2.2715,3.1944,3.9575a7.2036,7.2036,0,0,1-.0352.7452Zm4.01-1.0826c.0185-1.2065-.4786-2.52-1.8985-2.52-1.3838,0-1.9873,1.4019-2.0937,2.52Z" transform="translate(-1.2598 -2.3384)"/><path d="M211.251,9.0283c0-1.1709-.0362-2.0229-.0713-2.768h1.3486L212.6,7.6089h.0352a2.9648,2.9648,0,0,1,2.68-1.5264c1.8994,0,3.3007,1.7036,3.3007,4.3833,0,3.1236-1.7216,4.5606-3.5312,4.5606a2.5779,2.5779,0,0,1-2.3067-1.2422h-.0361v4.5429h-1.49Zm1.49,2.4312a2.5494,2.5494,0,0,0,.0713.6567,2.0815,2.0815,0,0,0,2.0049,1.7212c1.5088,0,2.2715-1.4194,2.2715-3.3184,0-1.7392-.7451-3.2119-2.2354-3.2119a2.2072,2.2072,0,0,0-2.0234,1.81,2.66,2.66,0,0,0-.0889.6387Z" transform="translate(-1.2598 -2.3384)"/><path d="M223.9883,2.8882h1.49V13.5894h4.5967v1.26h-6.0869Z" transform="translate(-1.2598 -2.3384)"/><path d="M232.2559,10.7852c.0351,2.2714,1.2773,3.0522,2.6621,3.0522a5.0471,5.0471,0,0,0,2.0937-.4082l.2666,1.0825a6.2338,6.2338,0,0,1-2.5732.4971c-2.4668,0-3.9043-1.7393-3.9043-4.33,0-2.644,1.4375-4.5962,3.709-4.5962,2.4843,0,3.1943,2.2715,3.1943,3.9575a6.9054,6.9054,0,0,1-.0361.7452Zm4.0107-1.0826c.0176-1.2065-.48-2.52-1.8994-2.52-1.3838,0-1.9873,1.4019-2.0938,2.52Z" transform="translate(-1.2598 -2.3384)"/><path d="M243.877,14.8491l-.125-1.0293h-.0528a2.7829,2.7829,0,0,1-2.36,1.2066A2.36,2.36,0,0,1,238.89,12.56c0-2.0943,1.8106-3.1768,4.7208-3.1592V9.188c0-.834-.2305-1.9873-1.792-1.97a3.63,3.63,0,0,0-1.9883.5859l-.3369-1.0293a5.024,5.024,0,0,1,2.5908-.6924c2.36,0,3.0166,1.5972,3.0166,3.39v3.354a14.1932,14.1932,0,0,0,.125,2.0229Zm-.2491-4.4009c-1.3838-.018-3.23.23-3.23,1.9522a1.3137,1.3137,0,0,0,1.3311,1.49,1.8742,1.8742,0,0,0,1.8457-1.3838,1.5985,1.5985,0,0,0,.0527-.497Z" transform="translate(-1.2598 -2.3384)"/><path d="M247.44,8.7979c0-.9229-.0351-1.775-.07-2.5376h1.33l.0537,1.5791h.0537a2.4525,2.4525,0,0,1,2.2178-1.7569,2.6819,2.6819,0,0,1,.3906.0357v1.455a1.8752,1.8752,0,0,0-.4619-.0356,2.0645,2.0645,0,0,0-1.9521,1.9346,3.2465,3.2465,0,0,0-.07.7451v4.6318H247.44Z" transform="translate(-1.2598 -2.3384)"/><path d="M252.8164,8.5493c0-.9228-.0361-1.58-.0713-2.289h1.3311l.0713,1.2954H254.2a2.8843,2.8843,0,0,1,2.5732-1.4732c1.19,0,2.7334.7632,2.7334,3.46v5.3061h-1.4912V9.7207c0-1.2778-.4258-2.396-1.7392-2.396a1.9941,1.9941,0,0,0-1.8633,1.544,2.982,2.982,0,0,0-.0889.7456v5.2348h-1.5078Z" transform="translate(-1.2598 -2.3384)"/><path d="M263.5313,3.9a.8937.8937,0,0,1-.94.94.8713.8713,0,0,1-.8867-.94.914.914,0,1,1,1.8272,0Zm-1.668,10.9492V6.26h1.5088v8.5888Z" transform="translate(-1.2598 -2.3384)"/><path d="M265.749,8.5493c0-.9228-.0361-1.58-.0713-2.289h1.3311l.0713,1.2954h.0527a2.8843,2.8843,0,0,1,2.5733-1.4732c1.1894,0,2.7334.7632,2.7334,3.46v5.3061h-1.4913V9.7207c0-1.2778-.4257-2.396-1.7392-2.396a1.9942,1.9942,0,0,0-1.8633,1.544,2.982,2.982,0,0,0-.0889.7456v5.2348H265.749Z" transform="translate(-1.2598 -2.3384)"/><path d="M281.5576,6.26c-.0361.603-.0713,1.33-.0713,2.4487v4.9336c0,2.0762-.373,3.1587-1.1006,3.8686a4.0953,4.0953,0,0,1-2.874.9937,4.9748,4.9748,0,0,1-2.5732-.6211l.3545-1.1538a4.4993,4.4993,0,0,0,2.2539.5859c1.4375,0,2.4668-.7807,2.4668-2.8926v-.9228h-.0362a2.65,2.65,0,0,1-2.413,1.313c-1.9522,0-3.3184-1.7744-3.3184-4.2056,0-2.9814,1.7568-4.5254,3.5312-4.5254a2.553,2.553,0,0,1,2.36,1.3667h.0352l.0537-1.1889Zm-1.5615,3.2475a2.839,2.839,0,0,0-.0713-.6748,2.0058,2.0058,0,0,0-1.917-1.5434c-1.331,0-2.2353,1.2773-2.2353,3.247,0,1.8281.7978,3.1236,2.2177,3.1236a1.98,1.98,0,0,0,1.8994-1.5083,3.1157,3.1157,0,0,0,.1065-.7989Z" transform="translate(-1.2598 -2.3384)"/></g></g></svg>
\ No newline at end of file
fidle/img/00-logos-reseaux.png deleted 100755 → 0
+ 0
− 0
View file @ a61c2dec
fidle/img/00-logos-reseaux.png

66.2 KiB

fidle/img/AE2-noisy.png deleted 100755 → 0
+ 0
− 0
View file @ a61c2dec
fidle/img/AE2-noisy.png

7.84 KiB

fidle/img/AE2-predict.png deleted 100755 → 0
+ 0
− 0
View file @ a61c2dec
fidle/img/AE2-predict.png

5.83 KiB

fidle/img/VAE.jpg deleted 100755 → 0
+ 0
− 0
View file @ a61c2dec
fidle/img/VAE.jpg

19.4 KiB

fidle/img/badge_logo.svg deleted 100644 → 0
+ 0
− 1
View file @ a61c2dec
<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" width="109" height="20"><linearGradient id="b" x2="0" y2="100%"><stop offset="0" stop-color="#bbb" stop-opacity=".1"/><stop offset="1" stop-opacity=".1"/></linearGradient><clipPath id="a"><rect width="109" height="20" rx="3" fill="#fff"/></clipPath><g clip-path="url(#a)"><path fill="#555" d="M0 0h64v20H0z"/><path fill="#579aca" d="M64 0h45v20H64z"/><path fill="url(#b)" d="M0 0h109v20H0z"/></g><g fill="#fff" text-anchor="middle" font-family="DejaVu Sans,Verdana,Geneva,sans-serif" font-size="110"><image x="5" y="3" width="14" height="14" xlink:href="data:image/png;base64,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"/> <text x="415" y="150" fill="#010101" fill-opacity=".3" transform="scale(.1)" textLength="370">launch</text><text x="415" y="140" transform="scale(.1)" textLength="370">launch</text><text x="855" y="150" fill="#010101" fill-opacity=".3" transform="scale(.1)" textLength="350">binder</text><text x="855" y="140" transform="scale(.1)" textLength="350">binder</text></g> </svg>
\ No newline at end of file
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment