diff --git a/README.ipynb b/README.ipynb
index 9b86b750a644b3d48bc4d5acb698523e2b778d2a..303957ea90358d0f6f55d5f0e6319183611fccc5 100644
--- a/README.ipynb
+++ b/README.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 7,
+ "execution_count": 2,
"metadata": {
"jupyter": {
"source_hidden": true
@@ -42,11 +42,12 @@
"\n",
"\n",
"## Course materials\n",
- "**[<img width=\"50px\" src=\"fidle/img/00-Fidle-pdf.svg\"></img>\n",
- "Get the course slides](https://cloud.univ-grenoble-alpes.fr/index.php/s/wxCztjYBbQ6zwd6)** \n",
"\n",
- "[How to get and install](https://gricad-gitlab.univ-grenoble-alpes.fr/talks/fidle/-/wikis/Install-Fidle) notebooks and datasets \n",
- "Some other useful informations are also available in the [wiki](https://gricad-gitlab.univ-grenoble-alpes.fr/talks/fidle/-/wikis/home)\n",
+ "| | | |\n",
+ "|:--:|:--:|:--:|\n",
+ "| **[<img width=\"50px\" src=\"fidle/img/00-Fidle-pdf.svg\"></img><br>Course slides](https://cloud.univ-grenoble-alpes.fr/index.php/s/wxCztjYBbQ6zwd6)**<br>The course in pdf format<br>(12 Mo)| **[<img width=\"50px\" src=\"fidle/img/00-Notebooks.svg\"></img><br>Notebooks](https://gricad-gitlab.univ-grenoble-alpes.fr/talks/fidle/-/archive/master/fidle-master.zip)**<br> Get a Zip or clone this repository <br>(10 Mo)| **[<img width=\"50px\" src=\"fidle/img/00-Datasets-tar.svg\"></img><br>Datasets](https://cloud.univ-grenoble-alpes.fr/index.php/s/wxCztjYBbQ6zwd6)**<br>All the needed datasets<br>(1.2 Go)|\n",
+ "\n",
+ "Have a look about **[How to get and install](https://gricad-gitlab.univ-grenoble-alpes.fr/talks/fidle/-/wikis/Install-Fidle)** these notebooks and datasets.\n",
"\n",
"\n",
"## Jupyter notebooks\n",
diff --git a/README.md b/README.md
index 91016f90e7613c239deb3d1d3ee994d8dd581e14..f67751a1abd83e91aec9f1e17285b4dd4850cbb2 100644
--- a/README.md
+++ b/README.md
@@ -28,11 +28,12 @@ Current Version : <!-- VERSION_BEGIN -->
## Course materials
-**[<img width="50px" src="fidle/img/00-Fidle-pdf.svg"></img>
-Get the course slides](https://cloud.univ-grenoble-alpes.fr/index.php/s/wxCztjYBbQ6zwd6)**
-[How to get and install](https://gricad-gitlab.univ-grenoble-alpes.fr/talks/fidle/-/wikis/Install-Fidle) notebooks and datasets
-Some other useful informations are also available in the [wiki](https://gricad-gitlab.univ-grenoble-alpes.fr/talks/fidle/-/wikis/home)
+| | | |
+|:--:|:--:|:--:|
+| **[<img width="50px" src="fidle/img/00-Fidle-pdf.svg"></img><br>Course slides](https://cloud.univ-grenoble-alpes.fr/index.php/s/wxCztjYBbQ6zwd6)**<br>The course in pdf format<br>(12 Mo)| **[<img width="50px" src="fidle/img/00-Notebooks.svg"></img><br>Notebooks](https://gricad-gitlab.univ-grenoble-alpes.fr/talks/fidle/-/archive/master/fidle-master.zip)**<br> Get a Zip or clone this repository <br>(10 Mo)| **[<img width="50px" src="fidle/img/00-Datasets-tar.svg"></img><br>Datasets](https://cloud.univ-grenoble-alpes.fr/index.php/s/wxCztjYBbQ6zwd6)**<br>All the needed datasets<br>(1.2 Go)|
+
+Have a look about **[How to get and install](https://gricad-gitlab.univ-grenoble-alpes.fr/talks/fidle/-/wikis/Install-Fidle)** these notebooks and datasets.
## Jupyter notebooks
diff --git a/READMEv2.ipynb b/READMEv2.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..dc44792e7943d66ebf957d3921a9f60e4dd3d878
--- /dev/null
+++ b/READMEv2.ipynb
@@ -0,0 +1,119 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "<a name=\"top\"></a>\n",
+ "\n",
+ "[<img width=\"600px\" src=\"fidle/img/00-Fidle-titre-01.svg\"></img>](#top)\n",
+ "\n",
+ "<!-- --------------------------------------------------- -->\n",
+ "<!-- To correctly view this README under Jupyter Lab -->\n",
+ "<!-- Open the notebook: README.ipynb! -->\n",
+ "<!-- --------------------------------------------------- -->\n",
+ "\n",
+ "\n",
+ "## A propos\n",
+ "\n",
+ "This repository contains all the documents and links of the **Fidle Training** . \n",
+ "Fidle (for Formation Introduction au Deep Learning) is a 2-day training session \n",
+ "co-organized by the Formation Permanente CNRS and the SARI and DEVLOG networks. \n",
+ "\n",
+ "The objectives of this training are :\n",
+ " - Understanding the **bases of Deep Learning** neural networks\n",
+ " - Develop a **first experience** through simple and representative examples\n",
+ " - Understanding **Tensorflow/Keras** and **Jupyter lab** technologies\n",
+ " - Apprehend the **academic computing environments** Tier-2 or Tier-1 with powerfull GPU\n",
+ "\n",
+ "For more information, you can contact us at : \n",
+ "[<img width=\"200px\" style=\"vertical-align:middle\" src=\"fidle/img/00-Mail_contact.svg\"></img>](#top) \n",
+ "Current Version : <!-- VERSION_BEGIN -->\n",
+ "0.6.0 DEV\n",
+ "<!-- VERSION_END -->\n",
+ "\n",
+ "\n",
+ "## Course materials\n",
+ "\n",
+ "| | | |\n",
+ "|:--:|:--:|:--:|\n",
+ "| **[<img width=\"50px\" src=\"fidle/img/00-Fidle-pdf.svg\"></img><br>Course slides](https://cloud.univ-grenoble-alpes.fr/index.php/s/wxCztjYBbQ6zwd6)**<br>The course in pdf format<br>(12 Mo)| **[<img width=\"50px\" src=\"fidle/img/00-Notebooks.svg\"></img><br>Notebooks](https://gricad-gitlab.univ-grenoble-alpes.fr/talks/fidle/-/archive/master/fidle-master.zip)**<br> Get a Zip or clone this repository <br>(10 Mo)| **[<img width=\"50px\" src=\"fidle/img/00-Datasets-tar.svg\"></img><br>Datasets](https://cloud.univ-grenoble-alpes.fr/index.php/s/wxCztjYBbQ6zwd6)**<br>All the needed datasets<br>(1.2 Go)|\n",
+ "\n",
+ "Have a look about **[How to get and install](https://gricad-gitlab.univ-grenoble-alpes.fr/talks/fidle/-/wikis/Install-Fidle)** these notebooks and datasets.\n",
+ "\n",
+ "\n",
+ "## Jupyter notebooks\n",
+ "\n",
+ "<!-- INDEX_BEGIN -->\n",
+ "| | |\n",
+ "|--|--|\n",
+ "|LINR1| [Linear regression with direct resolution](LinearReg/01-Linear-Regression.ipynb)<br>Direct determination of linear regression |\n",
+ "|GRAD1| [Linear regression with gradient descent](LinearReg/02-Gradient-descent.ipynb)<br>An example of gradient descent in the simple case of a linear regression.|\n",
+ "|POLR1| [Complexity Syndrome](LinearReg/03-Polynomial-Regression.ipynb)<br>Illustration of the problem of complexity with the polynomial regression|\n",
+ "|LOGR1| [Logistic regression, in pure Tensorflow](LinearReg/04-Logistic-Regression.ipynb)<br>Logistic Regression with Mini-Batch Gradient Descent using pure TensorFlow. |\n",
+ "|PER57| [Perceptron Model 1957](IRIS/01-Simple-Perceptron.ipynb)<br>A simple perceptron, with the IRIS dataset.|\n",
+ "|BHP1| [Regression with a Dense Network (DNN)](BHPD/01-DNN-Regression.ipynb)<br>A Simple regression with a Dense Neural Network (DNN) - BHPD dataset|\n",
+ "|BHP2| [Regression with a Dense Network (DNN) - Advanced code](BHPD/02-DNN-Regression-Premium.ipynb)<br>More advanced example of DNN network code - BHPD dataset|\n",
+ "|MNIST1| [Simple classification with DNN](MNIST/01-DNN-MNIST.ipynb)<br>Example of classification with a fully connected neural network|\n",
+ "|GTS1| [CNN with GTSRB dataset - Data analysis and preparation](GTSRB/01-Preparation-of-data.ipynb)<br>Episode 1 : Data analysis and creation of a usable dataset|\n",
+ "|GTS2| [CNN with GTSRB dataset - First convolutions](GTSRB/02-First-convolutions.ipynb)<br>Episode 2 : First convolutions and first results|\n",
+ "|GTS3| [CNN with GTSRB dataset - Monitoring ](GTSRB/03-Tracking-and-visualizing.ipynb)<br>Episode 3 : Monitoring and analysing training, managing checkpoints|\n",
+ "|GTS4| [CNN with GTSRB dataset - Data augmentation ](GTSRB/04-Data-augmentation.ipynb)<br>Episode 4 : Improving the results with data augmentation|\n",
+ "|GTS5| [CNN with GTSRB dataset - Full convolutions ](GTSRB/05-Full-convolutions.ipynb)<br>Episode 5 : A lot of models, a lot of datasets and a lot of results.|\n",
+ "|GTS6| [CNN with GTSRB dataset - Full convolutions as a batch](GTSRB/06-Notebook-as-a-batch.ipynb)<br>Episode 6 : Run Full convolution notebook as a batch|\n",
+ "|GTS7| [CNN with GTSRB dataset - Show reports](GTSRB/07-Show-report.ipynb)<br>Episode 7 : Displaying the reports of the different jobs|\n",
+ "|TSB1| [Tensorboard with/from Jupyter ](GTSRB/99-Scripts-Tensorboard.ipynb)<br>4 ways to use Tensorboard from the Jupyter environment|\n",
+ "|IMDB1| [Text embedding with IMDB](IMDB/01-Embedding-Keras.ipynb)<br>A very classical example of word embedding for text classification (sentiment analysis)|\n",
+ "|IMDB2| [Text embedding with IMDB - Reloaded](IMDB/02-Prediction.ipynb)<br>Example of reusing a previously saved model|\n",
+ "|IMDB3| [Text embedding/LSTM model with IMDB](IMDB/03-LSTM-Keras.ipynb)<br>Still the same problem, but with a network combining embedding and LSTM|\n",
+ "|SYNOP1| [Time series with RNN - Preparation of data](SYNOP/01-Preparation-of-data.ipynb)<br>Episode 1 : Data analysis and creation of a usable dataset|\n",
+ "|SYNOP2| [Time series with RNN - Try a prediction](SYNOP/02-First-predictions.ipynb)<br>Episode 2 : Training session and first predictions|\n",
+ "|SYNOP3| [Time series with RNN - 12h predictions](SYNOP/03-12h-predictions.ipynb)<br>Episode 3: Attempt to predict in the longer term |\n",
+ "|VAE1| [Variational AutoEncoder (VAE) with MNIST](VAE/01-VAE-with-MNIST.nbconvert.ipynb)<br>Episode 1 : Model construction and Training|\n",
+ "|VAE2| [Variational AutoEncoder (VAE) with MNIST - Analysis](VAE/02-VAE-with-MNIST-post.ipynb)<br>Episode 2 : Exploring our latent space|\n",
+ "|VAE3| [About the CelebA dataset](VAE/03-About-CelebA.ipynb)<br>Episode 3Â : About the CelebA dataset, a more fun dataset ;-)|\n",
+ "|VAE4| [Preparation of the CelebA dataset](VAE/04-Prepare-CelebA-datasets.ipynb)<br>Episode 4Â : Preparation of a clustered dataset, batchable|\n",
+ "|VAE5| [Checking the clustered CelebA dataset](VAE/05-Check-CelebA.ipynb)<br>Episode 5Â :\tChecking the clustered dataset|\n",
+ "|VAE6| [Variational AutoEncoder (VAE) with CelebA (small)](VAE/06-VAE-with-CelebA-s.nbconvert.ipynb)<br>Episode 6Â : Variational AutoEncoder (VAE) with CelebA (small res.)|\n",
+ "|VAE7| [Variational AutoEncoder (VAE) with CelebA (medium)](VAE/07-VAE-with-CelebA-m.nbconvert.ipynb)<br>Episode 7Â : Variational AutoEncoder (VAE) with CelebA (medium res.)|\n",
+ "|VAE8| [Variational AutoEncoder (VAE) with CelebA - Analysis](VAE/08-VAE-withCelebA-post.ipynb)<br>Episode 8Â : Exploring latent space of our trained models|\n",
+ "|ACTF1| [Activation functions](Misc/Activation-Functions.ipynb)<br>Some activation functions, with their derivatives.|\n",
+ "|NP1| [A short introduction to Numpy](Misc/Numpy.ipynb)<br>Numpy is an essential tool for the Scientific Python.|\n",
+ "<!-- INDEX_END -->\n",
+ "\n",
+ "\n",
+ "## Installation\n",
+ "\n",
+ "A procedure for **configuring** and **starting Jupyter** is available in the **[Wiki](https://gricad-gitlab.univ-grenoble-alpes.fr/talks/fidle/-/wikis/Install-Fidle)**.\n",
+ "\n",
+ "## Licence\n",
+ "\n",
+ "[<img width=\"100px\" src=\"fidle/img/00-fidle-CC BY-NC-SA.svg\"></img>](https://creativecommons.org/licenses/by-nc-sa/4.0/) \n",
+ "\\[en\\] Attribution - NonCommercial - ShareAlike 4.0 International (CC BY-NC-SA 4.0) \n",
+ "\\[Fr\\] Attribution - Pas d’Utilisation Commerciale - Partage dans les Mêmes Conditions 4.0 International \n",
+ "See [License](https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode). \n",
+ "See [Disclaimer](https://creativecommons.org/licenses/by-nc-sa/4.0/#). \n",
+ "\n",
+ "\n",
+ "----\n",
+ "[<img width=\"80px\" src=\"fidle/img/00-Fidle-logo-01.svg\"></img>](#top)\n"
+ ]
+ }
+ ],
+ "metadata": {
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.7.7"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/fidle/Update_index.ipynb b/fidle/Update_index.ipynb
index 71c7fa5262fb0c9a18c8aed36e3b9f6a3b120924..ec42e67c2b9479c5fe821b7ae4677cf41b3981fc 100644
--- a/fidle/Update_index.ipynb
+++ b/fidle/Update_index.ipynb
@@ -207,7 +207,7 @@
"\n",
"# ---- Save it\n",
"#\n",
- "with open('../test.ipynb', mode=\"w\", encoding='utf-8') as fp:\n",
+ "with open('../READMEv2.ipynb', mode=\"w\", encoding='utf-8') as fp:\n",
" nbformat.write(notebook, fp)"
]
},
diff --git a/fidle/img/00-Datasets-tar.svg b/fidle/img/00-Datasets-tar.svg
new file mode 100644
index 0000000000000000000000000000000000000000..9cb96df5c4bb2aa99996ac9cf690f0cbba2851f4
--- /dev/null
+++ b/fidle/img/00-Datasets-tar.svg
@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 36.8447 35.5347"><path d="M19.8818,8.3758V.9771H9.6714A3.2082,3.2082,0,0,0,6.4726,4.1759V27.6783a3.2081,3.2081,0,0,0,3.1988,3.1988H27.2329a3.2082,3.2082,0,0,0,3.1988-3.1988V11.5746H23.0806A3.2082,3.2082,0,0,1,19.8818,8.3758Z" style="fill:none;stroke:#000;stroke-linejoin:round;stroke-width:1.95428428707763px"/><line x1="19.8818" y1="0.9771" x2="30.4555" y2="11.5508" style="fill:none;stroke:#000;stroke-linejoin:round;stroke-width:1.95428428707763px"/><rect y="5.907" width="16.1948" height="17.0887" style="fill:#fff"/><path d="M20.3292,26.3928H24.002V18.63a1.1822,1.1822,0,0,1,1.1807-1.1807h6.208a1.1833,1.1833,0,0,1,1.1807,1.1753l.0351,7.7681h3.4029l-7.6367,8.5855Z" style="fill:#e12229"/><path d="M31.3905,17.8243a.8058.8058,0,0,1,.8058.8021l.0366,8.1415h2.9409l-6.8084,7.6544-7.171-7.6544h3.1827V18.63a.8057.8057,0,0,1,.8057-.8057h6.2077m0-.75H25.1828A1.5575,1.5575,0,0,0,23.6271,18.63v7.3879h-4.163l1.183,1.2628,7.171,7.6545.5617.5995.546-.6139,6.8084-7.6545,1.1105-1.2484H32.98l-.0333-7.3949a1.559,1.559,0,0,0-1.5558-1.5487Z" style="fill:#fff"/><path d="M14.901,9.12l0,.01c-.0174,1.0847-2.8156,1.9623-6.2648,1.9623S2.3887,10.2147,2.3712,9.13l0-.01c0-1.0894,2.8048-1.9725,6.2649-1.9725S14.901,8.03,14.901,9.12Z" style="fill:#e12229"/><path d="M14.9214,19.7408l0,.01c-.0174,1.0847-2.8156,1.9622-6.2648,1.9622s-6.2473-.8775-6.2648-1.9622l0-.01-.0041-2.779,0,.01c.0175,1.0847,2.8157,1.9622,6.2648,1.9622s6.2474-.8775,6.2648-1.9622l0-.01Z" style="fill:#e12229"/><path d="M14.9072,16.2168l0,.01c-.0175,1.0846-2.8157,1.9622-6.2648,1.9622s-6.2474-.8776-6.2648-1.9622l0-.01-.0041-2.779,0,.01C2.3908,14.5328,5.189,15.41,8.6382,15.41s6.2474-.8776,6.2648-1.9622l0-.01Z" style="fill:#e12229"/><path d="M14.9083,12.66l0,.01c-.0175,1.0847-2.8157,1.9622-6.2648,1.9622S2.396,13.7551,2.3786,12.67l0-.01-.0041-2.779,0,.01c.0174,1.0847,2.8156,1.9622,6.2648,1.9622s6.2473-.8775,6.2648-1.9622l0-.01Z" style="fill:#e12229"/></svg>
\ No newline at end of file
diff --git a/fidle/img/00-Notebooks.svg b/fidle/img/00-Notebooks.svg
new file mode 100644
index 0000000000000000000000000000000000000000..7befe0313f9b1b0f69a21e9e5feb9581722d6f37
--- /dev/null
+++ b/fidle/img/00-Notebooks.svg
@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 36.8447 35.5346"><path d="M19.8818,8.3758V.9771H9.6714A3.2082,3.2082,0,0,0,6.4726,4.1759V27.6783a3.2081,3.2081,0,0,0,3.1988,3.1988H27.2329a3.2082,3.2082,0,0,0,3.1988-3.1988V11.5746H23.0806A3.2082,3.2082,0,0,1,19.8818,8.3758Z" style="fill:none;stroke:#000;stroke-linejoin:round;stroke-width:1.95428428707763px"/><line x1="19.8818" y1="0.9771" x2="30.4555" y2="11.5508" style="fill:none;stroke:#000;stroke-linejoin:round;stroke-width:1.95428428707763px"/><rect y="5.907" width="16.1948" height="17.0887" style="fill:#fff"/><path d="M20.3294,26.3927h3.6728V18.63a1.1821,1.1821,0,0,1,1.1807-1.1806H31.39a1.1834,1.1834,0,0,1,1.1807,1.1757l.0351,7.7676h3.4029l-7.6363,8.586Z" style="fill:#e12229"/><path d="M31.3905,17.8244a.8056.8056,0,0,1,.8057.802l.0367,8.1414h2.9409l-6.8084,7.6545-7.171-7.6545h3.1827V18.63a.8056.8056,0,0,1,.8057-.8056h6.2077m0-.75H25.1828A1.5574,1.5574,0,0,0,23.6271,18.63v7.3878h-4.163l1.183,1.2629,7.171,7.6544.5617.5995.546-.6139,6.8084-7.6544,1.1105-1.2485H32.98l-.0334-7.3949a1.5588,1.5588,0,0,0-1.5557-1.5485Z" style="fill:#fff"/><path d="M13.6929,12.4289C12.5982,6.1627,7.3243,6.71,7.3243,6.71l0,0a5.71,5.71,0,0,0-5.7108,5.7108A7.1617,7.1617,0,0,0,3.8012,17.62v4.5846h6.3847V19.8412h2.0285A1.2317,1.2317,0,0,0,13.4452,18.61v-2.05c.4531-.1023,1.5854-.5277,1.5415-.8977C14.9375,15.24,13.6929,12.4289,13.6929,12.4289Zm-2.7057.5477a1.104,1.104,0,0,1-1.552,0,1.1322,1.1322,0,0,1-.3064-.613H7.6953a.864.864,0,0,1-.3459.4251l.4745,1.7794a.6633.6633,0,0,1,.4448.178.6449.6449,0,0,1,0,.89.6291.6291,0,1,1-.7612-.9886l-.4646-1.74a.8835.8835,0,0,1-.7118-.1977l-1.0972.6327a1.0449,1.0449,0,0,1,.079.3954,1.0963,1.0963,0,1,1-.2372-.6723l1.0478-.603a.8683.8683,0,0,1-.0988-.346l-1.6015-.4251a.6291.6291,0,1,1-.9885-.7612.6451.6451,0,0,1,.89,0,.6737.6737,0,0,1,.1878.4449l1.5421.4152a.9791.9791,0,0,1,.3065-.4448l-.5239-.9095a1.0965,1.0965,0,1,1,.692-1.0182,1.0915,1.0915,0,0,1-.3164.771c-.1878.1879.3164.8008.4449,1.0182a.8586.8586,0,0,1,.85.2274l1.2159-1.1862a.642.642,0,0,1,.0989-.7612.6291.6291,0,0,1,.89.89.642.642,0,0,1-.7612.0988L7.7052,11.731a1.0517,1.0517,0,0,1,.0593.3064H9.1288a1.1674,1.1674,0,0,1,.3064-.6129,1.0975,1.0975,0,0,1,1.552,1.5521Z" style="fill:#e12229"/></svg>
\ No newline at end of file