From bb4e6b0dde321ef16af0b376bad8a627e891ac39 Mon Sep 17 00:00:00 2001
From: Jean-Luc Parouty <Jean-Luc.Parouty@grenoble-inp.fr>
Date: Sat, 12 Dec 2020 00:48:22 +0100
Subject: [PATCH] Rewrite index generator for README
---
LinearReg/01-Linear-Regression.ipynb | 2 +-
README.ipynb | 124 +++++---------
README.md | 115 +++++--------
fidle/Finished.ipynb | 152 +++++++++++++++++
fidle/Update_index.ipynb | 242 +++++++++++++++++++++++++++
fidle/config.py | 10 +-
fidle/log/catalog_file.json | 226 +++++++++++++++++++++++++
7 files changed, 712 insertions(+), 159 deletions(-)
create mode 100644 fidle/Finished.ipynb
create mode 100644 fidle/Update_index.ipynb
create mode 100644 fidle/log/catalog_file.json
diff --git a/LinearReg/01-Linear-Regression.ipynb b/LinearReg/01-Linear-Regression.ipynb
index 5cc1809..f032d30 100644
--- a/LinearReg/01-Linear-Regression.ipynb
+++ b/LinearReg/01-Linear-Regression.ipynb
@@ -111,7 +111,7 @@
"sys.path.append('..')\n",
"import fidle.pwk as pwk\n",
"\n",
- "datasets_dir = pwk.init('01-Linear-Regression')"
+ "datasets_dir = pwk.init('LINR1')"
]
},
{
diff --git a/README.ipynb b/README.ipynb
index 9158125..9b86b75 100644
--- a/README.ipynb
+++ b/README.ipynb
@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 1,
+ "execution_count": 7,
"metadata": {
"jupyter": {
"source_hidden": true
@@ -21,6 +21,7 @@
"<!-- 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",
@@ -35,7 +36,9 @@
"\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 : 0.5.9\n",
+ "Current Version : <!-- VERSION_BEGIN -->\n",
+ "0.6.0 DEV\n",
+ "<!-- VERSION_END -->\n",
"\n",
"\n",
"## Course materials\n",
@@ -48,83 +51,41 @@
"\n",
"## Jupyter notebooks\n",
"\n",
- "<!-- DO NOT REMOVE THIS TAG !!! -->\n",
- "<!-- INDEX -->\n",
"<!-- INDEX_BEGIN -->\n",
- "[[LINR1] - Linear regression with direct resolution](LinearReg/01-Linear-Regression.ipynb) \n",
- " Direct determination of linear regression \n",
- "[[GRAD1] - Linear regression with gradient descent](LinearReg/02-Gradient-descent.ipynb) \n",
- " An example of gradient descent in the simple case of a linear regression. \n",
- "[[POLR1] - Complexity Syndrome](LinearReg/03-Polynomial-Regression.ipynb) \n",
- " Illustration of the problem of complexity with the polynomial regression \n",
- "[[LOGR1] - Logistic regression, in pure Tensorflow](LinearReg/04-Logistic-Regression.ipynb) \n",
- " Logistic Regression with Mini-Batch Gradient Descent using pure TensorFlow. \n",
- "[[PER57] - Perceptron Model 1957](IRIS/01-Simple-Perceptron.ipynb) \n",
- " A simple perceptron, with the IRIS dataset. \n",
- "[[BHP1] - Regression with a Dense Network (DNN)](BHPD/01-DNN-Regression.ipynb) \n",
- " 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) \n",
- " More advanced example of DNN network code - BHPD dataset \n",
- "[[MNIST1] - Simple classification with DNN](MNIST/01-DNN-MNIST.ipynb) \n",
- " 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) \n",
- " Episode 1 : Data analysis and creation of a usable dataset \n",
- "[[GTS2] - CNN with GTSRB dataset - First convolutions](GTSRB/02-First-convolutions.ipynb) \n",
- " Episode 2 : First convolutions and first results \n",
- "[[GTS3] - CNN with GTSRB dataset - Monitoring ](GTSRB/03-Tracking-and-visualizing.ipynb) \n",
- " Episode 3 : Monitoring and analysing training, managing checkpoints \n",
- "[[GTS4] - CNN with GTSRB dataset - Data augmentation ](GTSRB/04-Data-augmentation.ipynb) \n",
- " Episode 4 : Improving the results with data augmentation \n",
- "[[GTS5] - CNN with GTSRB dataset - Full convolutions ](GTSRB/05-Full-convolutions.ipynb) \n",
- " 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) \n",
- " Episode 6 : Run Full convolution notebook as a batch \n",
- "[[GTS7] - CNN with GTSRB dataset - Show reports](GTSRB/07-Show-report.ipynb) \n",
- " Episode 7 : Displaying the reports of the different jobs \n",
- "[[TSB1] - Tensorboard with/from Jupyter ](GTSRB/99-Scripts-Tensorboard.ipynb) \n",
- " 4 ways to use Tensorboard from the Jupyter environment \n",
- "[[BASH1] - OAR batch script](GTSRB/batch_oar.sh) \n",
- " Bash script for OAR batch submission of GTSRB notebook \n",
- "[[BASH2] - SLURM batch script](GTSRB/batch_slurm.sh) \n",
- " Bash script for SLURM batch submission of GTSRB notebooks \n",
- "[[IMDB1] - Text embedding with IMDB](IMDB/01-Embedding-Keras.ipynb) \n",
- " A very classical example of word embedding for text classification (sentiment analysis) \n",
- "[[IMDB2] - Text embedding with IMDB - Reloaded](IMDB/02-Prediction.ipynb) \n",
- " Example of reusing a previously saved model \n",
- "[[IMDB3] - Text embedding/LSTM model with IMDB](IMDB/03-LSTM-Keras.ipynb) \n",
- " 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) \n",
- " Episode 1 : Data analysis and creation of a usable dataset \n",
- "[[SYNOP2] - Time series with RNN - Try a prediction](SYNOP/02-First-predictions.ipynb) \n",
- " Episode 2 : Training session and first predictions \n",
- "[[SYNOP3] - Time series with RNN - 12h predictions](SYNOP/03-12h-predictions.ipynb) \n",
- " Episode 3: Attempt to predict in the longer term \n",
- "[[VAE1] - Variational AutoEncoder (VAE) with MNIST](VAE/01-VAE-with-MNIST.ipynb) \n",
- " Episode 1 : Model construction and Training \n",
- "[[VAE1] - Variational AutoEncoder (VAE) with MNIST](VAE/01-VAE-with-MNIST.nbconvert.ipynb) \n",
- " Episode 1 : Model construction and Training \n",
- "[[VAE2] - Variational AutoEncoder (VAE) with MNIST - Analysis](VAE/02-VAE-with-MNIST-post.ipynb) \n",
- " Episode 2 : Exploring our latent space \n",
- "[[VAE3] - About the CelebA dataset](VAE/03-About-CelebA.ipynb) \n",
- " Episode 3Â : About the CelebA dataset, a more fun dataset ;-) \n",
- "[[VAE4] - Preparation of the CelebA dataset](VAE/04-Prepare-CelebA-datasets.ipynb) \n",
- " Episode 4Â : Preparation of a clustered dataset, batchable \n",
- "[[VAE5] - Checking the clustered CelebA dataset](VAE/05-Check-CelebA.ipynb) \n",
- " Episode 5Â :\\tChecking the clustered dataset \n",
- "[[VAE6] - Variational AutoEncoder (VAE) with CelebA (small)](VAE/06-VAE-with-CelebA-s.ipynb) \n",
- " Episode 6Â : Variational AutoEncoder (VAE) with CelebA (small res.) \n",
- "[[VAE7] - Variational AutoEncoder (VAE) with CelebA (medium)](VAE/07-VAE-with-CelebA-m.ipynb) \n",
- " Episode 7Â : Variational AutoEncoder (VAE) with CelebA (medium res.) \n",
- "[[VAE8] - Variational AutoEncoder (VAE) with CelebA - Analysis](VAE/08-VAE-withCelebA-post.ipynb) \n",
- " Episode 8Â : Exploring latent space of our trained models \n",
- "[[BASH1] - OAR batch script](VAE/batch_oar.sh) \n",
- " Bash script for OAR batch submission of VAE notebook \n",
- "[[BASH2] - SLURM batch script](VAE/batch_slurm.sh) \n",
- " Bash script for SLURM batch submission of VAE notebooks \n",
- "[[ACTF1] - Activation functions](Misc/Activation-Functions.ipynb) \n",
- " Some activation functions, with their derivatives. \n",
- "[[NP1] - A short introduction to Numpy](Misc/Numpy.ipynb) \n",
- " Numpy is an essential tool for the Scientific Python. \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",
@@ -158,6 +119,13 @@
"#\n",
"# This README is visible under Jupiter LAb ! :-)"
]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
}
],
"metadata": {
diff --git a/README.md b/README.md
index b14c76a..91016f9 100644
--- a/README.md
+++ b/README.md
@@ -7,6 +7,7 @@
<!-- Open the notebook: README.ipynb! -->
<!-- --------------------------------------------------- -->
+
## A propos
This repository contains all the documents and links of the **Fidle Training** .
@@ -21,7 +22,9 @@ The objectives of this training are :
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 : 0.5.9
+Current Version : <!-- VERSION_BEGIN -->
+0.6.0 DEV
+<!-- VERSION_END -->
## Course materials
@@ -34,83 +37,41 @@ Some other useful informations are also available in the [wiki](https://gricad-g
## Jupyter notebooks
-<!-- DO NOT REMOVE THIS TAG !!! -->
-<!-- INDEX -->
<!-- INDEX_BEGIN -->
-[[LINR1] - Linear regression with direct resolution](LinearReg/01-Linear-Regression.ipynb)
- Direct determination of linear regression
-[[GRAD1] - Linear regression with gradient descent](LinearReg/02-Gradient-descent.ipynb)
- An example of gradient descent in the simple case of a linear regression.
-[[POLR1] - Complexity Syndrome](LinearReg/03-Polynomial-Regression.ipynb)
- Illustration of the problem of complexity with the polynomial regression
-[[LOGR1] - Logistic regression, in pure Tensorflow](LinearReg/04-Logistic-Regression.ipynb)
- Logistic Regression with Mini-Batch Gradient Descent using pure TensorFlow.
-[[PER57] - Perceptron Model 1957](IRIS/01-Simple-Perceptron.ipynb)
- A simple perceptron, with the IRIS dataset.
-[[BHP1] - Regression with a Dense Network (DNN)](BHPD/01-DNN-Regression.ipynb)
- A Simple regression with a Dense Neural Network (DNN) - BHPD dataset
-[[BHP2] - Regression with a Dense Network (DNN) - Advanced code](BHPD/02-DNN-Regression-Premium.ipynb)
- More advanced example of DNN network code - BHPD dataset
-[[MNIST1] - Simple classification with DNN](MNIST/01-DNN-MNIST.ipynb)
- Example of classification with a fully connected neural network
-[[GTS1] - CNN with GTSRB dataset - Data analysis and preparation](GTSRB/01-Preparation-of-data.ipynb)
- Episode 1 : Data analysis and creation of a usable dataset
-[[GTS2] - CNN with GTSRB dataset - First convolutions](GTSRB/02-First-convolutions.ipynb)
- Episode 2 : First convolutions and first results
-[[GTS3] - CNN with GTSRB dataset - Monitoring ](GTSRB/03-Tracking-and-visualizing.ipynb)
- Episode 3 : Monitoring and analysing training, managing checkpoints
-[[GTS4] - CNN with GTSRB dataset - Data augmentation ](GTSRB/04-Data-augmentation.ipynb)
- Episode 4 : Improving the results with data augmentation
-[[GTS5] - CNN with GTSRB dataset - Full convolutions ](GTSRB/05-Full-convolutions.ipynb)
- Episode 5 : A lot of models, a lot of datasets and a lot of results.
-[[GTS6] - CNN with GTSRB dataset - Full convolutions as a batch](GTSRB/06-Notebook-as-a-batch.ipynb)
- Episode 6 : Run Full convolution notebook as a batch
-[[GTS7] - CNN with GTSRB dataset - Show reports](GTSRB/07-Show-report.ipynb)
- Episode 7 : Displaying the reports of the different jobs
-[[TSB1] - Tensorboard with/from Jupyter ](GTSRB/99-Scripts-Tensorboard.ipynb)
- 4 ways to use Tensorboard from the Jupyter environment
-[[BASH1] - OAR batch script](GTSRB/batch_oar.sh)
- Bash script for OAR batch submission of GTSRB notebook
-[[BASH2] - SLURM batch script](GTSRB/batch_slurm.sh)
- Bash script for SLURM batch submission of GTSRB notebooks
-[[IMDB1] - Text embedding with IMDB](IMDB/01-Embedding-Keras.ipynb)
- A very classical example of word embedding for text classification (sentiment analysis)
-[[IMDB2] - Text embedding with IMDB - Reloaded](IMDB/02-Prediction.ipynb)
- Example of reusing a previously saved model
-[[IMDB3] - Text embedding/LSTM model with IMDB](IMDB/03-LSTM-Keras.ipynb)
- Still the same problem, but with a network combining embedding and LSTM
-[[SYNOP1] - Time series with RNN - Preparation of data](SYNOP/01-Preparation-of-data.ipynb)
- Episode 1 : Data analysis and creation of a usable dataset
-[[SYNOP2] - Time series with RNN - Try a prediction](SYNOP/02-First-predictions.ipynb)
- Episode 2 : Training session and first predictions
-[[SYNOP3] - Time series with RNN - 12h predictions](SYNOP/03-12h-predictions.ipynb)
- Episode 3: Attempt to predict in the longer term
-[[VAE1] - Variational AutoEncoder (VAE) with MNIST](VAE/01-VAE-with-MNIST.ipynb)
- Episode 1 : Model construction and Training
-[[VAE1] - Variational AutoEncoder (VAE) with MNIST](VAE/01-VAE-with-MNIST.nbconvert.ipynb)
- Episode 1 : Model construction and Training
-[[VAE2] - Variational AutoEncoder (VAE) with MNIST - Analysis](VAE/02-VAE-with-MNIST-post.ipynb)
- Episode 2 : Exploring our latent space
-[[VAE3] - About the CelebA dataset](VAE/03-About-CelebA.ipynb)
- Episode 3Â : About the CelebA dataset, a more fun dataset ;-)
-[[VAE4] - Preparation of the CelebA dataset](VAE/04-Prepare-CelebA-datasets.ipynb)
- Episode 4Â : Preparation of a clustered dataset, batchable
-[[VAE5] - Checking the clustered CelebA dataset](VAE/05-Check-CelebA.ipynb)
- Episode 5Â :\tChecking the clustered dataset
-[[VAE6] - Variational AutoEncoder (VAE) with CelebA (small)](VAE/06-VAE-with-CelebA-s.ipynb)
- Episode 6Â : Variational AutoEncoder (VAE) with CelebA (small res.)
-[[VAE7] - Variational AutoEncoder (VAE) with CelebA (medium)](VAE/07-VAE-with-CelebA-m.ipynb)
- Episode 7Â : Variational AutoEncoder (VAE) with CelebA (medium res.)
-[[VAE8] - Variational AutoEncoder (VAE) with CelebA - Analysis](VAE/08-VAE-withCelebA-post.ipynb)
- Episode 8Â : Exploring latent space of our trained models
-[[BASH1] - OAR batch script](VAE/batch_oar.sh)
- Bash script for OAR batch submission of VAE notebook
-[[BASH2] - SLURM batch script](VAE/batch_slurm.sh)
- Bash script for SLURM batch submission of VAE notebooks
-[[ACTF1] - Activation functions](Misc/Activation-Functions.ipynb)
- Some activation functions, with their derivatives.
-[[NP1] - A short introduction to Numpy](Misc/Numpy.ipynb)
- Numpy is an essential tool for the Scientific Python.
+| | |
+|--|--|
+|LINR1| [Linear regression with direct resolution](LinearReg/01-Linear-Regression.ipynb)<br>Direct determination of linear regression |
+|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.|
+|POLR1| [Complexity Syndrome](LinearReg/03-Polynomial-Regression.ipynb)<br>Illustration of the problem of complexity with the polynomial regression|
+|LOGR1| [Logistic regression, in pure Tensorflow](LinearReg/04-Logistic-Regression.ipynb)<br>Logistic Regression with Mini-Batch Gradient Descent using pure TensorFlow. |
+|PER57| [Perceptron Model 1957](IRIS/01-Simple-Perceptron.ipynb)<br>A simple perceptron, with the IRIS dataset.|
+|BHP1| [Regression with a Dense Network (DNN)](BHPD/01-DNN-Regression.ipynb)<br>A Simple regression with a Dense Neural Network (DNN) - BHPD dataset|
+|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|
+|MNIST1| [Simple classification with DNN](MNIST/01-DNN-MNIST.ipynb)<br>Example of classification with a fully connected neural network|
+|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|
+|GTS2| [CNN with GTSRB dataset - First convolutions](GTSRB/02-First-convolutions.ipynb)<br>Episode 2 : First convolutions and first results|
+|GTS3| [CNN with GTSRB dataset - Monitoring ](GTSRB/03-Tracking-and-visualizing.ipynb)<br>Episode 3 : Monitoring and analysing training, managing checkpoints|
+|GTS4| [CNN with GTSRB dataset - Data augmentation ](GTSRB/04-Data-augmentation.ipynb)<br>Episode 4 : Improving the results with data augmentation|
+|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.|
+|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|
+|GTS7| [CNN with GTSRB dataset - Show reports](GTSRB/07-Show-report.ipynb)<br>Episode 7 : Displaying the reports of the different jobs|
+|TSB1| [Tensorboard with/from Jupyter ](GTSRB/99-Scripts-Tensorboard.ipynb)<br>4 ways to use Tensorboard from the Jupyter environment|
+|IMDB1| [Text embedding with IMDB](IMDB/01-Embedding-Keras.ipynb)<br>A very classical example of word embedding for text classification (sentiment analysis)|
+|IMDB2| [Text embedding with IMDB - Reloaded](IMDB/02-Prediction.ipynb)<br>Example of reusing a previously saved model|
+|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|
+|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|
+|SYNOP2| [Time series with RNN - Try a prediction](SYNOP/02-First-predictions.ipynb)<br>Episode 2 : Training session and first predictions|
+|SYNOP3| [Time series with RNN - 12h predictions](SYNOP/03-12h-predictions.ipynb)<br>Episode 3: Attempt to predict in the longer term |
+|VAE1| [Variational AutoEncoder (VAE) with MNIST](VAE/01-VAE-with-MNIST.nbconvert.ipynb)<br>Episode 1 : Model construction and Training|
+|VAE2| [Variational AutoEncoder (VAE) with MNIST - Analysis](VAE/02-VAE-with-MNIST-post.ipynb)<br>Episode 2 : Exploring our latent space|
+|VAE3| [About the CelebA dataset](VAE/03-About-CelebA.ipynb)<br>Episode 3Â : About the CelebA dataset, a more fun dataset ;-)|
+|VAE4| [Preparation of the CelebA dataset](VAE/04-Prepare-CelebA-datasets.ipynb)<br>Episode 4Â : Preparation of a clustered dataset, batchable|
+|VAE5| [Checking the clustered CelebA dataset](VAE/05-Check-CelebA.ipynb)<br>Episode 5Â : Checking the clustered dataset|
+|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.)|
+|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.)|
+|VAE8| [Variational AutoEncoder (VAE) with CelebA - Analysis](VAE/08-VAE-withCelebA-post.ipynb)<br>Episode 8Â : Exploring latent space of our trained models|
+|ACTF1| [Activation functions](Misc/Activation-Functions.ipynb)<br>Some activation functions, with their derivatives.|
+|NP1| [A short introduction to Numpy](Misc/Numpy.ipynb)<br>Numpy is an essential tool for the Scientific Python.|
<!-- INDEX_END -->
diff --git a/fidle/Finished.ipynb b/fidle/Finished.ipynb
new file mode 100644
index 0000000..8faeb77
--- /dev/null
+++ b/fidle/Finished.ipynb
@@ -0,0 +1,152 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "<img width=\"800px\" src=\"../fidle/img/00-Fidle-header-01.svg\"></img>\n",
+ "\n",
+ "\n",
+ "## Notebook Performance Statistics (Continuous integration)\n",
+ " - List of executed notebooks \n",
+ " - Runtime and status \n",
+ "\n",
+ "Each notebook indicates its start and end of execution:\n",
+ " - at the beginning, during `pwk.init()`\n",
+ " - at the end, with a `pwk.end()`\n",
+ "This information is saved in a json file (FINISHED_FILE, cf config.py)."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import os,sys,glob,json\n",
+ "from pathlib import Path\n",
+ "import pandas as pd\n",
+ "from IPython.display import display, Markdown, HTML\n",
+ "\n",
+ "sys.path.append('..')\n",
+ "import fidle.pwk as pwk\n",
+ "import fidle.config as config"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 32,
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>Notebook</th>\n",
+ " <th>path</th>\n",
+ " <th>start</th>\n",
+ " <th>end</th>\n",
+ " <th>duration</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td><a href=\"/home/pjluc/dev/fidle/LinearReg/01-Linear-Regression.ipynb\">01-Linear-Regression</a></td>\n",
+ " <td>/home/pjluc/dev/fidle/LinearReg</td>\n",
+ " <td>Wednesday 9 December 2020, 20:16:41</td>\n",
+ " <td>Wednesday 9 December 2020, 20:16:41</td>\n",
+ " <td>00:00:00 256ms</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td><a href=\"/home/pjluc/dev/fidle/LinearReg/02-Gradient-descent.ipynb\">02-Gradient-descent</a></td>\n",
+ " <td>/home/pjluc/dev/fidle/LinearReg</td>\n",
+ " <td>Wednesday 9 December 2020, 20:16:56</td>\n",
+ " <td>Wednesday 9 December 2020, 20:17:00</td>\n",
+ " <td>00:00:03 279ms</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td><a href=\"/home/pjluc/dev/fidle/LinearReg/03-Polynomial-Regression.ipynb\">03-Polynomial-Regression</a></td>\n",
+ " <td>/home/pjluc/dev/fidle/LinearReg</td>\n",
+ " <td>Wednesday 9 December 2020, 20:20:32</td>\n",
+ " <td>Wednesday 9 December 2020, 20:20:33</td>\n",
+ " <td>00:00:01 682ms</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>"
+ ],
+ "text/plain": [
+ "<IPython.core.display.HTML object>"
+ ]
+ },
+ "execution_count": 32,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "with open(config.FINISHED_FILE) as infile:\n",
+ " dict_finished = json.load( infile )\n",
+ "\n",
+ "df=pd.DataFrame(dict_finished).transpose()\n",
+ "\n",
+ "df.reset_index(inplace=True)\n",
+ "df.rename(columns = {'index':'Notebook'}, inplace=True)\n",
+ "\n",
+ "# df['Notebook'] = '<a href=\"{}/{}.ipynb\">{}</a>'.format(df['path'],df['Notebook'],df['Notebook'])\n",
+ "\n",
+ "df['Notebook'] = df.apply(\n",
+ " lambda x: '<a href=\"{}/{}.ipynb\">{}</a>'.format(x['path'],x['Notebook'],x['Notebook']), axis=1\n",
+ " )\n",
+ " \n",
+ "\n",
+ "\n",
+ "HTML(df.to_html(\n",
+ " render_links=True,\n",
+ " escape=False))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "---\n",
+ "<img width=\"80px\" src=\"../fidle/img/00-Fidle-logo-01.svg\"></img>"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "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
new file mode 100644
index 0000000..a53d231
--- /dev/null
+++ b/fidle/Update_index.ipynb
@@ -0,0 +1,242 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import nbformat\n",
+ "import re\n",
+ "import sys, os, glob\n",
+ "import json\n",
+ "from collections import OrderedDict\n",
+ "\n",
+ "sys.path.append('..')\n",
+ "# import fidle.pwk as pwk\n",
+ "import fidle.config as config\n",
+ " "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "directories_to_index = ['LinearReg', 'IRIS', 'BHPD', 'MNIST', 'GTSRB', 'IMDB', 'SYNOP', 'VAE', 'Misc']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "\n",
+ "def get_notebooks(directories, top_dir='..'):\n",
+ " '''\n",
+ " Return a list of notebooks from a given list of directories\n",
+ " args:\n",
+ " directories : list of directories\n",
+ " top_dir : location of theses directories\n",
+ " return:\n",
+ " notebooks : notebooks filename list (without top_dir prefix)\n",
+ " '''\n",
+ " notebooks = []\n",
+ " \n",
+ " for d in directories:\n",
+ " filenames = glob.glob( f'{top_dir}/{d}/*.ipynb')\n",
+ " filenames.sort()\n",
+ " notebooks.extend(filenames)\n",
+ "\n",
+ " notebooks = [ x.replace(f'{top_dir}/','') for x in notebooks]\n",
+ " return notebooks\n",
+ "\n",
+ "\n",
+ "def get_infos(filename, top_dir='..'):\n",
+ " '''\n",
+ " Extract informations from a fidle notebook.\n",
+ " Informations are dirname, basename, id, title, description and are extracted from comments tags in markdown.\n",
+ " args:\n",
+ " filename : Notebook filename\n",
+ " return:\n",
+ " dict : with infos.\n",
+ " '''\n",
+ "\n",
+ " about={}\n",
+ " about['dirname'] = os.path.dirname(filename)\n",
+ " about['basename'] = os.path.basename(filename)\n",
+ " about['id'] = '??'\n",
+ " about['title'] = '??'\n",
+ " about['description'] = '??'\n",
+ " \n",
+ " # ---- Read notebook\n",
+ " #\n",
+ " notebook = nbformat.read(f'{top_dir}/{filename}', nbformat.NO_CONVERT)\n",
+ " \n",
+ " # ---- Get id, title and desc tags\n",
+ " #\n",
+ " for cell in notebook.cells:\n",
+ "\n",
+ " if cell['cell_type'] == 'markdown':\n",
+ "\n",
+ " find = re.findall(r'<\\!-- TITLE -->\\s*\\[(.*)\\]\\s*-\\s*(.*)\\n',cell.source)\n",
+ " if find:\n",
+ " about['id'] = find[0][0]\n",
+ " about['title'] = find[0][1]\n",
+ "\n",
+ " find = re.findall(r'<\\!-- DESC -->\\s*(.*)\\n',cell.source)\n",
+ " if find:\n",
+ " about['description'] = find[0]\n",
+ "\n",
+ " return about\n",
+ " \n",
+ "\n",
+ "def get_catalog(notebooks_list, top_dir='..'):\n",
+ " '''\n",
+ " Return an OrderedDict of notebooks attributes.\n",
+ " Keys are notebooks id.\n",
+ " args:\n",
+ " notebooks_list : list of notebooks filenames\n",
+ " top_dir : Location of theses notebooks\n",
+ " return:\n",
+ " OrderedDict : {<notebook id> : { description} }\n",
+ " '''\n",
+ " \n",
+ " catalog = OrderedDict()\n",
+ "\n",
+ " for nb in notebooks_list:\n",
+ " about = get_infos(nb, top_dir='..')\n",
+ " id=about['id']\n",
+ " catalog[id] = about\n",
+ "\n",
+ " return catalog\n",
+ " \n",
+ " "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "README.md is updated.\n"
+ ]
+ }
+ ],
+ "source": [
+ "\n",
+ "# ---- Get the notebook list\n",
+ "#\n",
+ "notebooks_list = get_notebooks(directories_to_index)\n",
+ "\n",
+ "# ---- Get a detailled catalog for this list\n",
+ "#\n",
+ "catalog = get_catalog(notebooks_list)\n",
+ "\n",
+ "with open(config.CATALOG_FILE,'wt') as fp:\n",
+ " json.dump(catalog,fp,indent=4)\n",
+ "\n",
+ "# ---- Create a markdown index\n",
+ "#\n",
+ "lines=['| | |','|--|--|']\n",
+ "tab=' '*5\n",
+ "for id, about in catalog.items():\n",
+ " id = about['id']\n",
+ " dirname = about['dirname']\n",
+ " basename = about['basename']\n",
+ " title = about['title']\n",
+ " description = about['description']\n",
+ " \n",
+ "# lines.append( f'[[{id}] - {title}]({dirname}/{basename}) ' )\n",
+ "# lines.append( f'{tab}{description} ')\n",
+ " lines.append( f'|{id}| [{title}]({dirname}/{basename})<br>{description}|')\n",
+ "\n",
+ "index = '\\n'.join(lines)\n",
+ " \n",
+ "# ---- Load README.md\n",
+ "#\n",
+ "with open('../README.md','r') as fp:\n",
+ " readme=fp.read()\n",
+ " \n",
+ "# ---- Update index\n",
+ "#\n",
+ "debut = '<!-- INDEX_BEGIN -->'\n",
+ "fin = '<!-- INDEX_END -->'\n",
+ "\n",
+ "readme = re.sub(f'{debut}.*{fin}',f'{debut}\\n{index}\\n{fin}',readme, flags=re.DOTALL)\n",
+ "\n",
+ "# ---- Update version\n",
+ "#\n",
+ "debut = '<!-- VERSION_BEGIN -->'\n",
+ "fin = '<!-- VERSION_END -->'\n",
+ "\n",
+ "readme = re.sub(f'{debut}.*{fin}',f'{debut}\\n{config.VERSION}\\n{fin}',readme, flags=re.DOTALL)\n",
+ "\n",
+ "# ---- Save it\n",
+ "#\n",
+ "with open('../README.md','wt') as fp:\n",
+ " fp.write(readme)\n",
+ "\n",
+ "print('README.md is updated.')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {},
+ "outputs": [
+ {
+ "ename": "NameError",
+ "evalue": "name 'nbf' is not defined",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)",
+ "\u001b[0;32m<ipython-input-9-85936a69f607>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0mnbformat\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mv4\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnew_markdown_cell\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msource\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mreadme\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mopen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'../test.ipynb'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'w'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mnbf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwrite\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnnb\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
+ "\u001b[0;31mNameError\u001b[0m: name 'nbf' is not defined"
+ ]
+ }
+ ],
+ "source": [
+ "nnb = nbformat.v4.new_notebook()\n",
+ "nbformat.v4.new_markdown_cell(source=readme)\n",
+ "with open('../test.ipynb', 'w') as f:\n",
+ " nbf.write(nnb, f)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "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/config.py b/fidle/config.py
index 4181215..425ddf9 100644
--- a/fidle/config.py
+++ b/fidle/config.py
@@ -12,9 +12,9 @@
# Jean-Luc Parouty 2020
-# ---- Current version ---------------------------------------------
+# ---- Version -----------------------------------------------------
#
-VERSION = '0.7 DEV'
+VERSION = '0.6.0 DEV'
# ---- Default notebook name ---------------------------------------
#
@@ -27,4 +27,8 @@ FIDLE_CSSFILE = '../fidle/css/custom.css'
# ---- Done file, to keep track of finished notebooks --------------
#
-FINISHED_FILE = '../fidle/log/finished_file.json'
\ No newline at end of file
+FINISHED_FILE = '../fidle/log/finished_file.json'
+
+# ---- Catalog file, a json description of all notebooks
+#
+CATALOG_FILE = '../fidle/log/catalog_file.json'
\ No newline at end of file
diff --git a/fidle/log/catalog_file.json b/fidle/log/catalog_file.json
new file mode 100644
index 0000000..8a6b68e
--- /dev/null
+++ b/fidle/log/catalog_file.json
@@ -0,0 +1,226 @@
+{
+ "LINR1": {
+ "dirname": "LinearReg",
+ "basename": "01-Linear-Regression.ipynb",
+ "id": "LINR1",
+ "title": "Linear regression with direct resolution",
+ "description": "Direct determination of linear regression "
+ },
+ "GRAD1": {
+ "dirname": "LinearReg",
+ "basename": "02-Gradient-descent.ipynb",
+ "id": "GRAD1",
+ "title": "Linear regression with gradient descent",
+ "description": "An example of gradient descent in the simple case of a linear regression."
+ },
+ "POLR1": {
+ "dirname": "LinearReg",
+ "basename": "03-Polynomial-Regression.ipynb",
+ "id": "POLR1",
+ "title": "Complexity Syndrome",
+ "description": "Illustration of the problem of complexity with the polynomial regression"
+ },
+ "LOGR1": {
+ "dirname": "LinearReg",
+ "basename": "04-Logistic-Regression.ipynb",
+ "id": "LOGR1",
+ "title": "Logistic regression, in pure Tensorflow",
+ "description": "Logistic Regression with Mini-Batch Gradient Descent using pure TensorFlow. "
+ },
+ "PER57": {
+ "dirname": "IRIS",
+ "basename": "01-Simple-Perceptron.ipynb",
+ "id": "PER57",
+ "title": "Perceptron Model 1957",
+ "description": "A simple perceptron, with the IRIS dataset."
+ },
+ "BHP1": {
+ "dirname": "BHPD",
+ "basename": "01-DNN-Regression.ipynb",
+ "id": "BHP1",
+ "title": "Regression with a Dense Network (DNN)",
+ "description": "A Simple regression with a Dense Neural Network (DNN) - BHPD dataset"
+ },
+ "BHP2": {
+ "dirname": "BHPD",
+ "basename": "02-DNN-Regression-Premium.ipynb",
+ "id": "BHP2",
+ "title": "Regression with a Dense Network (DNN) - Advanced code",
+ "description": "More advanced example of DNN network code - BHPD dataset"
+ },
+ "MNIST1": {
+ "dirname": "MNIST",
+ "basename": "01-DNN-MNIST.ipynb",
+ "id": "MNIST1",
+ "title": "Simple classification with DNN",
+ "description": "Example of classification with a fully connected neural network"
+ },
+ "GTS1": {
+ "dirname": "GTSRB",
+ "basename": "01-Preparation-of-data.ipynb",
+ "id": "GTS1",
+ "title": "CNN with GTSRB dataset - Data analysis and preparation",
+ "description": "Episode 1 : Data analysis and creation of a usable dataset"
+ },
+ "GTS2": {
+ "dirname": "GTSRB",
+ "basename": "02-First-convolutions.ipynb",
+ "id": "GTS2",
+ "title": "CNN with GTSRB dataset - First convolutions",
+ "description": "Episode 2 : First convolutions and first results"
+ },
+ "GTS3": {
+ "dirname": "GTSRB",
+ "basename": "03-Tracking-and-visualizing.ipynb",
+ "id": "GTS3",
+ "title": "CNN with GTSRB dataset - Monitoring ",
+ "description": "Episode 3 : Monitoring and analysing training, managing checkpoints"
+ },
+ "GTS4": {
+ "dirname": "GTSRB",
+ "basename": "04-Data-augmentation.ipynb",
+ "id": "GTS4",
+ "title": "CNN with GTSRB dataset - Data augmentation ",
+ "description": "Episode 4 : Improving the results with data augmentation"
+ },
+ "GTS5": {
+ "dirname": "GTSRB",
+ "basename": "05-Full-convolutions.ipynb",
+ "id": "GTS5",
+ "title": "CNN with GTSRB dataset - Full convolutions ",
+ "description": "Episode 5 : A lot of models, a lot of datasets and a lot of results."
+ },
+ "GTS6": {
+ "dirname": "GTSRB",
+ "basename": "06-Notebook-as-a-batch.ipynb",
+ "id": "GTS6",
+ "title": "CNN with GTSRB dataset - Full convolutions as a batch",
+ "description": "Episode 6 : Run Full convolution notebook as a batch"
+ },
+ "GTS7": {
+ "dirname": "GTSRB",
+ "basename": "07-Show-report.ipynb",
+ "id": "GTS7",
+ "title": "CNN with GTSRB dataset - Show reports",
+ "description": "Episode 7 : Displaying the reports of the different jobs"
+ },
+ "TSB1": {
+ "dirname": "GTSRB",
+ "basename": "99-Scripts-Tensorboard.ipynb",
+ "id": "TSB1",
+ "title": "Tensorboard with/from Jupyter ",
+ "description": "4 ways to use Tensorboard from the Jupyter environment"
+ },
+ "IMDB1": {
+ "dirname": "IMDB",
+ "basename": "01-Embedding-Keras.ipynb",
+ "id": "IMDB1",
+ "title": "Text embedding with IMDB",
+ "description": "A very classical example of word embedding for text classification (sentiment analysis)"
+ },
+ "IMDB2": {
+ "dirname": "IMDB",
+ "basename": "02-Prediction.ipynb",
+ "id": "IMDB2",
+ "title": "Text embedding with IMDB - Reloaded",
+ "description": "Example of reusing a previously saved model"
+ },
+ "IMDB3": {
+ "dirname": "IMDB",
+ "basename": "03-LSTM-Keras.ipynb",
+ "id": "IMDB3",
+ "title": "Text embedding/LSTM model with IMDB",
+ "description": "Still the same problem, but with a network combining embedding and LSTM"
+ },
+ "SYNOP1": {
+ "dirname": "SYNOP",
+ "basename": "01-Preparation-of-data.ipynb",
+ "id": "SYNOP1",
+ "title": "Time series with RNN - Preparation of data",
+ "description": "Episode 1 : Data analysis and creation of a usable dataset"
+ },
+ "SYNOP2": {
+ "dirname": "SYNOP",
+ "basename": "02-First-predictions.ipynb",
+ "id": "SYNOP2",
+ "title": "Time series with RNN - Try a prediction",
+ "description": "Episode 2 : Training session and first predictions"
+ },
+ "SYNOP3": {
+ "dirname": "SYNOP",
+ "basename": "03-12h-predictions.ipynb",
+ "id": "SYNOP3",
+ "title": "Time series with RNN - 12h predictions",
+ "description": "Episode 3: Attempt to predict in the longer term "
+ },
+ "VAE1": {
+ "dirname": "VAE",
+ "basename": "01-VAE-with-MNIST.nbconvert.ipynb",
+ "id": "VAE1",
+ "title": "Variational AutoEncoder (VAE) with MNIST",
+ "description": "Episode 1 : Model construction and Training"
+ },
+ "VAE2": {
+ "dirname": "VAE",
+ "basename": "02-VAE-with-MNIST-post.ipynb",
+ "id": "VAE2",
+ "title": "Variational AutoEncoder (VAE) with MNIST - Analysis",
+ "description": "Episode 2 : Exploring our latent space"
+ },
+ "VAE3": {
+ "dirname": "VAE",
+ "basename": "03-About-CelebA.ipynb",
+ "id": "VAE3",
+ "title": "About the CelebA dataset",
+ "description": "Episode 3\u00a0: About the CelebA dataset, a more fun dataset ;-)"
+ },
+ "VAE4": {
+ "dirname": "VAE",
+ "basename": "04-Prepare-CelebA-datasets.ipynb",
+ "id": "VAE4",
+ "title": "Preparation of the CelebA dataset",
+ "description": "Episode 4\u00a0: Preparation of a clustered dataset, batchable"
+ },
+ "VAE5": {
+ "dirname": "VAE",
+ "basename": "05-Check-CelebA.ipynb",
+ "id": "VAE5",
+ "title": "Checking the clustered CelebA dataset",
+ "description": "Episode 5\u00a0:\tChecking the clustered dataset"
+ },
+ "VAE6": {
+ "dirname": "VAE",
+ "basename": "06-VAE-with-CelebA-s.nbconvert.ipynb",
+ "id": "VAE6",
+ "title": "Variational AutoEncoder (VAE) with CelebA (small)",
+ "description": "Episode 6\u00a0: Variational AutoEncoder (VAE) with CelebA (small res.)"
+ },
+ "VAE7": {
+ "dirname": "VAE",
+ "basename": "07-VAE-with-CelebA-m.nbconvert.ipynb",
+ "id": "VAE7",
+ "title": "Variational AutoEncoder (VAE) with CelebA (medium)",
+ "description": "Episode 7\u00a0: Variational AutoEncoder (VAE) with CelebA (medium res.)"
+ },
+ "VAE8": {
+ "dirname": "VAE",
+ "basename": "08-VAE-withCelebA-post.ipynb",
+ "id": "VAE8",
+ "title": "Variational AutoEncoder (VAE) with CelebA - Analysis",
+ "description": "Episode 8\u00a0: Exploring latent space of our trained models"
+ },
+ "ACTF1": {
+ "dirname": "Misc",
+ "basename": "Activation-Functions.ipynb",
+ "id": "ACTF1",
+ "title": "Activation functions",
+ "description": "Some activation functions, with their derivatives."
+ },
+ "NP1": {
+ "dirname": "Misc",
+ "basename": "Numpy.ipynb",
+ "id": "NP1",
+ "title": "A short introduction to Numpy",
+ "description": "Numpy is an essential tool for the Scientific Python."
+ }
+}
\ No newline at end of file
--
GitLab