A propos

This repository contains all the documents and links of the Fidle Training.

The objectives of this training, co-organized by the Formation Permanente CNRS and the SARI and DEVLOG networks, are :

• Understanding the bases of deep learning neural networks (Deep Learning)
• Develop a first experience through simple and representative examples
• Understand the different types of networks, their architectures and their use cases.
• Understanding Tensorflow/Keras and Jupyter lab technologies on the GPU
• Apprehend the academic computing environments Tier-2 (meso) and/or Tier-1 (national)

Course materials

Get the course slides

Useful information is also available in the wiki

Jupyter notebooks

1. [NP1] - A short introduction to Numpy
         Numpy is an essential tool for the Scientific Python.
2. [LINR1] - Linear regression with direct resolution
         Direct determination of linear regression
3. [GRAD1] - Linear regression with gradient descent
         An example of gradient descent in the simple case of a linear regression.
4. [FIT1] - Complexity Syndrome
         Illustration of the problem of complexity with the polynomial regression
5. [LOGR1] - Logistic regression, in pure Tensorflow
         Logistic Regression with Mini-Batch Gradient Descent using pure TensorFlow.
6. [MNIST1] - Simple classification with DNN
         Example of classification with a fully connected neural network
7. [BHP1] - Regression with a Dense Network (DNN)
         A Simple regression with a Dense Neural Network (DNN) - BHPD dataset
8. [BHP2] - Regression with a Dense Network (DNN) - Advanced code
         More advanced example of DNN network code - BHPD dataset
9. [GTS1] - CNN with GTSRB dataset - Data analysis and preparation
         Episode 1: Data analysis and creation of a usable dataset
10. [GTS2] - CNN with GTSRB dataset - First convolutions
          Episode 2 : First convolutions and first results
11. [GTS3] - CNN with GTSRB dataset - Monitoring
          Episode 3: Monitoring and analysing training, managing checkpoints
12. [GTS4] - CNN with GTSRB dataset - Data augmentation
          Episode 4: Improving the results with data augmentation
13. [GTS5] - CNN with GTSRB dataset - Full convolutions
          Episode 5: A lot of models, a lot of datasets and a lot of results.
14. [GTS6] - CNN with GTSRB dataset - Full convolutions as a batch
          Episode 6 : Run Full convolution notebook as a batch
15. [GTS7] - Full convolutions Report
          Displaying the reports of the different jobs
16. [TSB1] - Tensorboard with/from Jupyter
          4 ways to use Tensorboard from the Jupyter environment
17. [IMDB1] - Text embedding with IMDB
          A very classical example of word embedding for text classification (sentiment analysis)
18. [IMDB2] - Text embedding with IMDB - Reloaded
          Example of reusing a previously saved model
19. [IMDB3] - Text embedding/LSTM model with IMDB
          Still the same problem, but with a network combining embedding and LSTM

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.

---