diff --git a/BHPD/03-DNN-Wine-Regression.ipynb b/BHPD/03-DNN-Wine-Regression.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..ecb36fa60975f6dd355cbc17af4b63ddb8d19232
--- /dev/null
+++ b/BHPD/03-DNN-Wine-Regression.ipynb
@@ -0,0 +1,482 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "<img width=\"800px\" src=\"../fidle/img/00-Fidle-header-01.svg\"></img>\n",
+ "\n",
+ "# <!-- TITLE --> [WINE1] - Wine quality prediction with a Dense Network (DNN)\n",
+ " <!-- DESC --> Another example of regression, with a wine quality prediction!\n",
+ " <!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
+ "\n",
+ "## Objectives :\n",
+ " - Predict the **quality of wines**, based on their analysis\n",
+ " - Understanding the principle and the architecture of a regression with a dense neural network with backup and restore of the trained model. \n",
+ "\n",
+ "The **[Wine Quality datasets](https://archive.ics.uci.edu/ml/datasets/wine+Quality)** are made up of analyses of a large number of wines, with an associated quality (between 0 and 10) \n",
+ "This dataset is provide by : \n",
+ "Paulo Cortez, University of Minho, Guimarães, Portugal, http://www3.dsi.uminho.pt/pcortez \n",
+ "A. Cerdeira, F. Almeida, T. Matos and J. Reis, Viticulture Commission of the Vinho Verde Region(CVRVV), Porto, Portugal, @2009 \n",
+ "This dataset can be retreive at [University of California Irvine (UCI)](https://archive-beta.ics.uci.edu/ml/datasets/wine+quality)\n",
+ "\n",
+ "\n",
+ "Due to privacy and logistic issues, only physicochemical and sensory variables are available \n",
+ "There is no data about grape types, wine brand, wine selling price, etc.\n",
+ "\n",
+ "- fixed acidity\n",
+ "- volatile acidity\n",
+ "- citric acid\n",
+ "- residual sugar\n",
+ "- chlorides\n",
+ "- free sulfur dioxide\n",
+ "- total sulfur dioxide\n",
+ "- density\n",
+ "- pH\n",
+ "- sulphates\n",
+ "- alcohol\n",
+ "- quality (score between 0 and 10)\n",
+ "\n",
+ "## What we're going to do :\n",
+ "\n",
+ " - (Retrieve data)\n",
+ " - (Preparing the data)\n",
+ " - (Build a model)\n",
+ " - Train and save the model\n",
+ " - Restore saved model\n",
+ " - Evaluate the model\n",
+ " - Make some predictions\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 1 - Import and init\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# import os\n",
+ "# os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'\n",
+ "\n",
+ "import tensorflow as tf\n",
+ "from tensorflow import keras\n",
+ "\n",
+ "import numpy as np\n",
+ "import matplotlib.pyplot as plt\n",
+ "import pandas as pd\n",
+ "import os,sys\n",
+ "\n",
+ "from IPython.display import Markdown\n",
+ "from importlib import reload\n",
+ "\n",
+ "import fidle\n",
+ "\n",
+ "# Init Fidle environment\n",
+ "run_id, run_dir, datasets_dir = fidle.init('WINE1')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Verbosity during training : \n",
+ "- 0 = silent\n",
+ "- 1 = progress bar\n",
+ "- 2 = one line per epoch"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "fit_verbosity = 1\n",
+ "dataset_name = 'winequality-red.csv'"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Override parameters (batch mode) - Just forget this cell"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "fidle.override('fit_verbosity', 'dataset_name')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 2 - Retrieve data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "data = pd.read_csv(f'{datasets_dir}/WineQuality/origine/{dataset_name}', header=0,sep=';')\n",
+ "\n",
+ "display(data.head(5).style.format(\"{0:.2f}\"))\n",
+ "print('Missing Data : ',data.isna().sum().sum(), ' Shape is : ', data.shape)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 3 - Preparing the data\n",
+ "### 3.1 - Split data\n",
+ "We will use 80% of the data for training and 20% for validation. \n",
+ "x will be the data of the analysis and y the quality"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# ---- Split => train, test\n",
+ "#\n",
+ "data = data.sample(frac=1., axis=0) # Shuffle\n",
+ "data_train = data.sample(frac=0.8, axis=0) # get 80 %\n",
+ "data_test = data.drop(data_train.index) # test = all - train\n",
+ "\n",
+ "# ---- Split => x,y (medv is price)\n",
+ "#\n",
+ "x_train = data_train.drop('quality', axis=1)\n",
+ "y_train = data_train['quality']\n",
+ "x_test = data_test.drop('quality', axis=1)\n",
+ "y_test = data_test['quality']\n",
+ "\n",
+ "print('Original data shape was : ',data.shape)\n",
+ "print('x_train : ',x_train.shape, 'y_train : ',y_train.shape)\n",
+ "print('x_test : ',x_test.shape, 'y_test : ',y_test.shape)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 3.2 - Data normalization\n",
+ "**Note :** \n",
+ " - All input data must be normalized, train and test. \n",
+ " - To do this we will subtract the mean and divide by the standard deviation. \n",
+ " - But test data should not be used in any way, even for normalization. \n",
+ " - The mean and the standard deviation will therefore only be calculated with the train data."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "display(x_train.describe().style.format(\"{0:.2f}\").set_caption(\"Before normalization :\"))\n",
+ "\n",
+ "mean = x_train.mean()\n",
+ "std = x_train.std()\n",
+ "x_train = (x_train - mean) / std\n",
+ "x_test = (x_test - mean) / std\n",
+ "\n",
+ "display(x_train.describe().style.format(\"{0:.2f}\").set_caption(\"After normalization :\"))\n",
+ "\n",
+ "# Convert ou DataFrame to numpy array\n",
+ "x_train, y_train = np.array(x_train), np.array(y_train)\n",
+ "x_test, y_test = np.array(x_test), np.array(y_test)\n"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 4 - Build a model\n",
+ "More informations about : \n",
+ " - [Optimizer](https://www.tensorflow.org/api_docs/python/tf/keras/optimizers)\n",
+ " - [Activation](https://www.tensorflow.org/api_docs/python/tf/keras/activations)\n",
+ " - [Loss](https://www.tensorflow.org/api_docs/python/tf/keras/losses)\n",
+ " - [Metrics](https://www.tensorflow.org/api_docs/python/tf/keras/metrics)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def get_model_v1(shape):\n",
+ " \n",
+ " model = keras.models.Sequential()\n",
+ " model.add(keras.layers.Input(shape, name=\"InputLayer\"))\n",
+ " model.add(keras.layers.Dense(64, activation='relu', name='Dense_n1'))\n",
+ " model.add(keras.layers.Dense(64, activation='relu', name='Dense_n2'))\n",
+ " model.add(keras.layers.Dense(1, name='Output'))\n",
+ "\n",
+ " model.compile(optimizer = 'rmsprop',\n",
+ " loss = 'mse',\n",
+ " metrics = ['mae', 'mse'] )\n",
+ " return model"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## 5 - Train the model\n",
+ "### 5.1 - Get it"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "model=get_model_v1( (11,) )\n",
+ "\n",
+ "model.summary()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 5.2 - Add callback"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "os.makedirs('./run/models', mode=0o750, exist_ok=True)\n",
+ "save_dir = \"./run/models/best_model.h5\"\n",
+ "\n",
+ "savemodel_callback = tf.keras.callbacks.ModelCheckpoint(filepath=save_dir, verbose=0, save_best_only=True)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 5.3 - Train it"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "history = model.fit(x_train,\n",
+ " y_train,\n",
+ " epochs = 100,\n",
+ " batch_size = 10,\n",
+ " verbose = fit_verbosity,\n",
+ " validation_data = (x_test, y_test),\n",
+ " callbacks = [savemodel_callback])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 6 - Evaluate\n",
+ "### 6.1 - Model evaluation\n",
+ "MAE = Mean Absolute Error (between the labels and predictions) \n",
+ "A mae equal to 3 represents an average error in prediction of $3k."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "score = model.evaluate(x_test, y_test, verbose=0)\n",
+ "\n",
+ "print('x_test / loss : {:5.4f}'.format(score[0]))\n",
+ "print('x_test / mae : {:5.4f}'.format(score[1]))\n",
+ "print('x_test / mse : {:5.4f}'.format(score[2]))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 6.2 - Training history\n",
+ "What was the best result during our training ?"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "print(\"min( val_mae ) : {:.4f}\".format( min(history.history[\"val_mae\"]) ) )"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "fidle.scrawler.history( history, plot={'MSE' :['mse', 'val_mse'],\n",
+ " 'MAE' :['mae', 'val_mae'],\n",
+ " 'LOSS':['loss','val_loss']}, save_as='01-history')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 7 - Restore a model :"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 7.1 - Reload model"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "loaded_model = tf.keras.models.load_model('./run/models/best_model.h5')\n",
+ "loaded_model.summary()\n",
+ "print(\"Loaded.\")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 7.2 - Evaluate it :"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "score = loaded_model.evaluate(x_test, y_test, verbose=0)\n",
+ "\n",
+ "print('x_test / loss : {:5.4f}'.format(score[0]))\n",
+ "print('x_test / mae : {:5.4f}'.format(score[1]))\n",
+ "print('x_test / mse : {:5.4f}'.format(score[2]))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### 7.3 - Make a prediction"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# ---- Pick n entries from our test set\n",
+ "n = 200\n",
+ "ii = np.random.randint(1,len(x_test),n)\n",
+ "x_sample = x_test[ii]\n",
+ "y_sample = y_test[ii]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# ---- Make a predictions\n",
+ "y_pred = loaded_model.predict( x_sample, verbose=2 )"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# ---- Show it\n",
+ "print('Wine Prediction Real Delta')\n",
+ "for i in range(n):\n",
+ " pred = y_pred[i][0]\n",
+ " real = y_sample[i]\n",
+ " delta = real-pred\n",
+ " print(f'{i:03d} {pred:.2f} {real} {delta:+.2f} ')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "fidle.end()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "---\n",
+ "<img width=\"80px\" src=\"../fidle/img/00-Fidle-logo-01.svg\"></img>"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3.9.2 ('fidle-env')",
+ "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": "3.9.2"
+ },
+ "vscode": {
+ "interpreter": {
+ "hash": "b3929042cc22c1274d74e3e946c52b845b57cb6d84f2d591ffe0519b38e4896d"
+ }
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/Misc/Using-pandas.ipynb b/Misc/Using-pandas.ipynb
new file mode 100644
index 0000000000000000000000000000000000000000..bc314cfeb5c7cc9595a8e37770898d496a3ac3fd
--- /dev/null
+++ b/Misc/Using-pandas.ipynb
@@ -0,0 +1,148 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "slideshow": {
+ "slide_type": "slide"
+ }
+ },
+ "source": [
+ "<img width=\"800px\" src=\"../fidle/img/00-Fidle-header-01.svg\"></img>\n",
+ "\n",
+ "# <!-- TITLE --> [PANDAS1] - Quelques exemples avec Pandas\n",
+ "<!-- DESC --> pandas is another essential tool for the Scientific Python.\n",
+ "<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
+ "\n",
+ "## Objectives :\n",
+ " - Understand how to slice a dataset"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Step 1 - A little cooking with datasets"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import numpy as np"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Get some data\n",
+ "a = np.arange(50).reshape(10,5)\n",
+ "print('Starting data: \\n',a)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Create a DataFrame\n",
+ "df_all = pd.DataFrame(a, columns=['A','B','C','D','E'])\n",
+ "print('\\nDataFrame :')\n",
+ "display(df_all)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Shuffle data\n",
+ "df_all = df_all.sample(frac=1, axis=0)\n",
+ "print('\\nDataFrame randomly shuffled :')\n",
+ "display(df_all)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Get a train part\n",
+ "df_train = df_all.sample(frac=0.8, axis=0)\n",
+ "print('\\nTrain set (80%) :')\n",
+ "display(df_train)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "\n",
+ "# Get test set as all - train\n",
+ "df_test = df_all.drop(df_train.index)\n",
+ "print('\\nTest set (all - train) :')\n",
+ "display(df_test)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "x_train = df_train.drop('E', axis=1)\n",
+ "y_train = df_train['E']\n",
+ "x_test = df_test.drop('E', axis=1)\n",
+ "y_test = df_test['E']\n",
+ "display(x_train)\n",
+ "display(y_train)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "---\n",
+ "<img width=\"80px\" src=\"../fidle/img/00-Fidle-logo-01.svg\"></img>"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3.9.2 ('fidle-env')",
+ "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": "3.9.2"
+ },
+ "orig_nbformat": 4,
+ "vscode": {
+ "interpreter": {
+ "hash": "b3929042cc22c1274d74e3e946c52b845b57cb6d84f2d591ffe0519b38e4896d"
+ }
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/README.ipynb b/README.ipynb
index 72f868497d7e11e6be7b35b08d815a491f14ffd3..e1a120b941c601a9f4db69a7805d4712948726f5 100644
--- a/README.ipynb
+++ b/README.ipynb
@@ -3,13 +3,13 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "a097c5d3",
+ "id": "c0502242",
"metadata": {
"execution": {
- "iopub.execute_input": "2022-10-13T16:40:09.834885Z",
- "iopub.status.busy": "2022-10-13T16:40:09.834097Z",
- "iopub.status.idle": "2022-10-13T16:40:09.845618Z",
- "shell.execute_reply": "2022-10-13T16:40:09.844753Z"
+ "iopub.execute_input": "2022-10-16T19:33:52.178836Z",
+ "iopub.status.busy": "2022-10-16T19:33:52.178369Z",
+ "iopub.status.idle": "2022-10-16T19:33:52.190555Z",
+ "shell.execute_reply": "2022-10-16T19:33:52.189704Z"
},
"jupyter": {
"source_hidden": true
@@ -52,7 +52,7 @@
"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",
"\n",
- "Current Version : <!-- VERSION_BEGIN -->2.2.0<!-- VERSION_END -->\n",
+ "Current Version : <!-- VERSION_BEGIN -->2.2.1<!-- VERSION_END -->\n",
"\n",
"\n",
"## Course materials\n",
@@ -67,7 +67,7 @@
"## Jupyter notebooks\n",
"\n",
"<!-- TOC_BEGIN -->\n",
- "<!-- Automatically generated on : 13/10/22 18:40:08 -->\n",
+ "<!-- Automatically generated on : 16/10/22 21:33:51 -->\n",
"\n",
"### Linear and logistic regression\n",
"- **[LINR1](LinearReg/01-Linear-Regression.ipynb)** - [Linear regression with direct resolution](LinearReg/01-Linear-Regression.ipynb) \n",
@@ -88,6 +88,8 @@
"Simple example of a regression with the dataset Boston Housing Prices Dataset (BHPD)\n",
"- **[BHPD2](BHPD/02-DNN-Regression-Premium.ipynb)** - [Regression with a Dense Network (DNN) - Advanced code](BHPD/02-DNN-Regression-Premium.ipynb) \n",
"A more advanced implementation of the precedent example\n",
+ "- **[WINE1](BHPD/03-DNN-Wine-Regression.ipynb)** - [Wine quality prediction with a Dense Network (DNN)](BHPD/03-DNN-Wine-Regression.ipynb) \n",
+ "Another example of regression, with a wine quality prediction!\n",
"\n",
"### Basic classification using a DN\n",
"- **[MNIST1](MNIST/01-DNN-MNIST.ipynb)** - [Simple classification with DNN](MNIST/01-DNN-MNIST.ipynb) \n",
@@ -198,6 +200,8 @@
"A scratchbook for small examples\n",
"- **[TSB1](Misc/Using-Tensorboard.ipynb)** - [Tensorboard with/from Jupyter ](Misc/Using-Tensorboard.ipynb) \n",
"4 ways to use Tensorboard from the Jupyter environment\n",
+ "- **[PANDAS1](Misc/Using-pandas.ipynb)** - [Quelques exemples avec Pandas](Misc/Using-pandas.ipynb) \n",
+ "pandas is another essential tool for the Scientific Python.\n",
"<!-- TOC_END -->\n",
"\n",
"\n",
@@ -229,7 +233,7 @@
"from IPython.display import display,Markdown\n",
"display(Markdown(open('README.md', 'r').read()))\n",
"#\n",
- "# This README is visible under Jupiter Lab ;-)# Automatically generated on : 13/10/22 18:40:09"
+ "# This README is visible under Jupiter Lab ;-)# Automatically generated on : 16/10/22 21:33:51"
]
}
],
diff --git a/README.md b/README.md
index 9b225e6772b4d4e9fc7e3784775ae086c7ceaa63..db8aee27205397bf8f8803cde00fcdab284eb191 100644
--- a/README.md
+++ b/README.md
@@ -31,7 +31,7 @@ For more information, see **https://fidle.cnrs.fr** :
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 -->2.2.0<!-- VERSION_END -->
+Current Version : <!-- VERSION_BEGIN -->2.2.1<!-- VERSION_END -->
## Course materials
@@ -46,7 +46,7 @@ Have a look about **[How to get and install](https://fidle.cnrs.fr/installation)
## Jupyter notebooks
<!-- TOC_BEGIN -->
-<!-- Automatically generated on : 13/10/22 18:40:08 -->
+<!-- Automatically generated on : 16/10/22 21:33:51 -->
### Linear and logistic regression
- **[LINR1](LinearReg/01-Linear-Regression.ipynb)** - [Linear regression with direct resolution](LinearReg/01-Linear-Regression.ipynb)
@@ -67,6 +67,8 @@ Example of use of a Perceptron, with sklearn and IRIS dataset of 1936 !
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
+- **[WINE1](BHPD/03-DNN-Wine-Regression.ipynb)** - [Wine quality prediction with a Dense Network (DNN)](BHPD/03-DNN-Wine-Regression.ipynb)
+Another example of regression, with a wine quality prediction!
### Basic classification using a DN
- **[MNIST1](MNIST/01-DNN-MNIST.ipynb)** - [Simple classification with DNN](MNIST/01-DNN-MNIST.ipynb)
@@ -177,6 +179,8 @@ Numpy is an essential tool for the Scientific Python.
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
+- **[PANDAS1](Misc/Using-pandas.ipynb)** - [Quelques exemples avec Pandas](Misc/Using-pandas.ipynb)
+pandas is another essential tool for the Scientific Python.
<!-- TOC_END -->
diff --git a/fidle/about.yml b/fidle/about.yml
index b806e6b0e5490bd4f378bf4555823da9ec75eeb9..707666d66982d6fe80555c763d18401d8f827811 100644
--- a/fidle/about.yml
+++ b/fidle/about.yml
@@ -13,7 +13,7 @@
#
# This file describes the notebooks used by the Fidle training.
-version: 2.2.0
+version: 2.2.1
content: notebooks
name: Notebooks Fidle
description: All notebooks used by the Fidle training
diff --git a/fidle/ci/OLD-full_ci.yml b/fidle/ci/OLD-full_ci.yml
deleted file mode 100644
index 8dd473385643d4c3bac526ccf49c9e20824b9042..0000000000000000000000000000000000000000
--- a/fidle/ci/OLD-full_ci.yml
+++ /dev/null
@@ -1,292 +0,0 @@
-_metadata_:
- version: '1.0'
- output_tag: ==ci==
- save_figs: true
- description: Full profile for CI
-#
-# ------ LinearReg -------------------------------------------------
-#
-LINR1:
- notebook_id: LINR1
- notebook_dir: LinearReg
- notebook_src: 01-Linear-Regression.ipynb
- notebook_tag: default
-GRAD1:
- notebook_id: GRAD1
- notebook_dir: LinearReg
- notebook_src: 02-Gradient-descent.ipynb
- notebook_tag: default
-POLR1:
- notebook_id: POLR1
- notebook_dir: LinearReg
- notebook_src: 03-Polynomial-Regression.ipynb
- notebook_tag: default
-LOGR1:
- notebook_id: LOGR1
- notebook_dir: LinearReg
- notebook_src: 04-Logistic-Regression.ipynb
- notebook_tag: default
-PER57:
- notebook_id: PER57
- notebook_dir: IRIS
- notebook_src: 01-Simple-Perceptron.ipynb
- notebook_tag: default
-#
-# ------ BHPD ------------------------------------------------------
-#
-BHPD1:
- notebook_id: BHPD1
- notebook_dir: BHPD
- notebook_src: 01-DNN-Regression.ipynb
- notebook_tag: default
-BHPD2:
- notebook_id: BHPD2
- notebook_dir: BHPD
- notebook_src: 02-DNN-Regression-Premium.ipynb
- notebook_tag: default
-#
-# ------ MNIST -----------------------------------------------------
-#
-MNIST1:
- notebook_id: MNIST1
- notebook_dir: MNIST
- notebook_src: 01-DNN-MNIST.ipynb
- notebook_tag: default
-#
-# ------ GTSRB -----------------------------------------------------
-#
-GTSRB1:
- notebook_id: GTSRB1
- notebook_dir: GTSRB
- notebook_src: 01-Preparation-of-data.ipynb
- notebook_tag: default
- overrides:
- scale: 0.01
- output_dir: './data'
-GTSRB2:
- notebook_id: GTSRB2
- notebook_dir: GTSRB
- notebook_src: 02-First-convolutions.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/GTSRB2_ci
- enhanced_dir: './data'
- dataset_name: set-24x24-L
- batch_size: 64
- epochs: 5
- scale: 1
-GTSRB3:
- notebook_id: GTSRB3
- notebook_dir: GTSRB
- notebook_src: 03-Tracking-and-visualizing.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/GTSRB3_ci
- enhanced_dir: './data'
- dataset_name: set-24x24-L
- batch_size: 64
- epochs: 5
- scale: 1
-GTSRB4:
- notebook_id: GTSRB4
- notebook_dir: GTSRB
- notebook_src: 04-Data-augmentation.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/GTSRB4_ci
- enhanced_dir: './data'
- dataset_name: set-24x24-L
- batch_size: 64
- epochs: 5
- scale: 1
-GTSRB5_r1:
- notebook_id: GTSRB5
- notebook_dir: GTSRB
- notebook_src: 05-Full-convolutions.ipynb
- notebook_tag: =1==ci==
- overrides:
- run_dir: ./run/GTSRB5_ci
- enhanced_dir: './data'
- datasets: "['set-24x24-L', 'set-24x24-RGB', 'set-48x48-L', 'set-48x48-RGB', 'set-24x24-L-LHE', 'set-24x24-RGB-HE', 'set-48x48-L-LHE', 'set-48x48-RGB-HE']"
- models: "{'v1':'get_model_v1', 'v2':'get_model_v2', 'v3':'get_model_v3'}"
- batch_size: 64
- epochs: 16
- scale: 1
- with_datagen: False
- verbose: 0
-GTSRB5_r2:
- notebook_id: GTSRB5
- notebook_dir: GTSRB
- notebook_src: 05-Full-convolutions.ipynb
- notebook_tag: =2==ci==
- overrides:
- run_dir: ./run/GTSRB5_ci
- enhanced_dir: './data'
- datasets: "['set-48x48-L', 'set-48x48-RGB']"
- models: "{'v2':'get_model_v2', 'v3':'get_model_v3'}"
- batch_size: 64
- epochs: 16
- scale: 1
- with_datagen: False
- verbose: 0
-GTSRB6:
- notebook_id: GTSRB6
- notebook_dir: GTSRB
- notebook_src: 06-Notebook-as-a-batch.ipynb
- notebook_tag: default
-GTSRB7:
- notebook_id: GTSRB7
- notebook_dir: GTSRB
- notebook_src: 07-Show-report.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/GTSRB7_ci
- report_dir: ./run/GTSRB5_ci
-#
-# ------ IMDB ------------------------------------------------------
-#
-IMDB1:
- notebook_id: IMDB1
- notebook_dir: IMDB
- notebook_src: 01-Embedding-Keras.ipynb
- notebook_tag: default
-IMDB2:
- notebook_id: IMDB1
- notebook_dir: IMDB
- notebook_src: 02-Prediction.ipynb
- notebook_tag: default
-IMDB3:
- notebook_id: IMDB1
- notebook_dir: IMDB
- notebook_src: 03-LSTM-Keras.ipynb
- notebook_tag: default
-#
-# ------ SYNOP -----------------------------------------------------
-#
-SYNOP1:
- notebook_id: SYNOP1
- notebook_dir: SYNOP
- notebook_src: 01-Preparation-of-data.ipynb
- notebook_tag: default
-SYNOP2:
- notebook_id: SYNOP2
- notebook_dir: SYNOP
- notebook_src: 02-First-predictions.ipynb
- notebook_tag: default
- overrides:
- scale: 0.5
- train_prop: 0.8
- sequence_len: 16
- batch_size: 32
- epochs: 10
-SYNOP3:
- notebook_id: SYNOP3
- notebook_dir: SYNOP
- notebook_src: 03-12h-predictions.ipynb
- notebook_tag: default
- overrides:
- iterations: 4
- scale: 1
- train_prop: 0.8
- sequence_len: 16
- batch_size: 32
- epochs: 10
-#
-# ------ AE --------------------------------------------------------
-#
-AE1:
- notebook_id: AE1
- notebook_dir: AE
- notebook_src: 01-AE-with-MNIST.ipynb
- notebook_tag: default
-AE2:
- notebook_id: AE2
- notebook_dir: AE
- notebook_src: 02-AE-with-MNIST-post.ipynb
- notebook_tag: default
-#
-# ------ VAE -------------------------------------------------------
-#
-VAE1:
- notebook_id: VAE1
- notebook_dir: VAE
- notebook_src: 01-VAE-with-MNIST.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/VAE1_ci
- scale: 1
- latent_dim: 2
- r_loss_factor: 0.994
- batch_size: 64
- epochs: 10
-VAE2:
- notebook_id: VAE2
- notebook_dir: VAE
- notebook_src: 02-VAE-with-MNIST-post.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/VAE1_ci
-VAE5:
- notebook_id: VAE5
- notebook_dir: VAE
- notebook_src: 05-About-CelebA.ipynb
- notebook_tag: default
-VAE6:
- notebook_id: VAE6
- notebook_dir: VAE
- notebook_src: 06-Prepare-CelebA-datasets.ipynb
- notebook_tag: default
- overrides:
- scale: 0.02
- image_size: '(192,160)'
- output_dir: ./data
- exit_if_exist: False
-VAE7:
- notebook_id: VAE7
- notebook_dir: VAE
- notebook_src: 07-Check-CelebA.ipynb
- notebook_tag: default
- overrides:
- image_size: '(192,160)'
- enhanced_dir: './data'
-VAE8:
- notebook_id: VAE8
- notebook_dir: VAE
- notebook_src: 08-VAE-with-CelebA.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/VAE8_ci
- scale: 1
- image_size: '(192,160)'
- enhanced_dir: './data'
- latent_dim: 300
- r_loss_factor: 0.6
- batch_size: 64
- epochs: 15
-VAE9:
- notebook_id: VAE9
- notebook_dir: VAE
- notebook_src: 09-VAE-with-CelebA-post.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/VAE8_ci
- image_size: '(192,160)'
- enhanced_dir: './data'
-#
-# ------ Misc ------------------------------------------------------
-#
-ACTF1:
- notebook_id: ACTF1
- notebook_dir: Misc
- notebook_src: Activation-Functions.ipynb
- notebook_tag: default
-NP1:
- notebook_id: NP1
- notebook_dir: Misc
- notebook_src: Numpy.ipynb
- notebook_tag: default
-TSB1:
- notebook_id: TSB1
- notebook_dir: Misc
- notebook_src: Using-Tensorboard.ipynb
- notebook_tag: default
diff --git a/fidle/ci/OLD-full_gpu.yml b/fidle/ci/OLD-full_gpu.yml
deleted file mode 100644
index 511dba89d0c288894c29682d8f22dac1f47d912c..0000000000000000000000000000000000000000
--- a/fidle/ci/OLD-full_gpu.yml
+++ /dev/null
@@ -1,362 +0,0 @@
-_metadata_:
- version: '1.0'
- output_tag: ==done==
- save_figs: true
- description: Full profile for GPU
-#
-# ------ LinearReg -------------------------------------------------
-#
-Nb_LINR1:
- notebook_id: LINR1
- notebook_dir: LinearReg
- notebook_src: 01-Linear-Regression.ipynb
- notebook_tag: default
-Nb_GRAD1:
- notebook_id: GRAD1
- notebook_dir: LinearReg
- notebook_src: 02-Gradient-descent.ipynb
- notebook_tag: default
-Nb_POLR1:
- notebook_id: POLR1
- notebook_dir: LinearReg
- notebook_src: 03-Polynomial-Regression.ipynb
- notebook_tag: default
-Nb_LOGR1:
- notebook_id: LOGR1
- notebook_dir: LinearReg
- notebook_src: 04-Logistic-Regression.ipynb
- notebook_tag: default
-Nb_PER57:
- notebook_id: PER57
- notebook_dir: IRIS
- notebook_src: 01-Simple-Perceptron.ipynb
- notebook_tag: default
-#
-# ------ BHPD ------------------------------------------------------
-#
-Nb_BHPD1:
- notebook_id: BHPD1
- notebook_dir: BHPD
- notebook_src: 01-DNN-Regression.ipynb
- notebook_tag: default
-Nb_BHPD2:
- notebook_id: BHPD2
- notebook_dir: BHPD
- notebook_src: 02-DNN-Regression-Premium.ipynb
- notebook_tag: default
-#
-# ------ MNIST -----------------------------------------------------
-#
-Nb_MNIST1:
- notebook_id: MNIST1
- notebook_dir: MNIST
- notebook_src: 01-DNN-MNIST.ipynb
- notebook_tag: default
-Nb_MNIST2:
- notebook_id: MNIST2
- notebook_dir: MNIST
- notebook_src: 02-CNN-MNIST.ipynb
- notebook_tag: default
-#
-# ------ GTSRB -----------------------------------------------------
-#
-Nb_GTSRB1:
- notebook_id: GTSRB1
- notebook_dir: GTSRB
- notebook_src: 01-Preparation-of-data.ipynb
- notebook_tag: default
- overrides:
- scale: 0.05
- output_dir: ./data
-Nb_GTSRB2:
- notebook_id: GTSRB2
- notebook_dir: GTSRB
- notebook_src: 02-First-convolutions.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/GTSRB2_done
- enhanced_dir: '{datasets_dir}/GTSRB/enhanced'
- dataset_name: set-24x24-L
- batch_size: 64
- epochs: 5
- scale: 1
-Nb_GTSRB3:
- notebook_id: GTSRB3
- notebook_dir: GTSRB
- notebook_src: 03-Tracking-and-visualizing.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/GTSRB3_done
- enhanced_dir: '{datasets_dir}/GTSRB/enhanced'
- dataset_name: set-24x24-L
- batch_size: 64
- epochs: 5
- scale: 1
-Nb_GTSRB4:
- notebook_id: GTSRB4
- notebook_dir: GTSRB
- notebook_src: 04-Data-augmentation.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/GTSRB4_done
- enhanced_dir: '{datasets_dir}/GTSRB/enhanced'
- dataset_name: set-24x24-L
- batch_size: 64
- epochs: 5
- scale: 1
-Nb_GTSRB5_r1:
- notebook_id: GTSRB5
- notebook_dir: GTSRB
- notebook_src: 05-Full-convolutions.ipynb
- notebook_tag: =1==done==
- overrides:
- run_dir: ./run/GTSRB5_done
- enhanced_dir: '{datasets_dir}/GTSRB/enhanced'
- datasets: "['set-24x24-L', 'set-24x24-RGB', 'set-48x48-L', 'set-48x48-RGB', 'set-24x24-L-LHE', 'set-24x24-RGB-HE', 'set-48x48-L-LHE', 'set-48x48-RGB-HE']"
- models: "{'v1':'get_model_v1', 'v2':'get_model_v2', 'v3':'get_model_v3'}"
- batch_size: 64
- epochs: 16
- scale: 1
- with_datagen: False
- verbose: 0
-Nb_GTSRB5_r2:
- notebook_id: GTSRB5
- notebook_dir: GTSRB
- notebook_src: 05-Full-convolutions.ipynb
- notebook_tag: =2==done==
- overrides:
- run_dir: ./run/GTSRB5_done
- enhanced_dir: '{datasets_dir}/GTSRB/enhanced'
- datasets: "['set-24x24-L', 'set-24x24-RGB', 'set-48x48-L', 'set-48x48-RGB', 'set-24x24-L-LHE', 'set-24x24-RGB-HE', 'set-48x48-L-LHE', 'set-48x48-RGB-HE']"
- models: "{'v1':'get_model_v1', 'v2':'get_model_v2', 'v3':'get_model_v3'}"
- batch_size: 64
- epochs: 16
- scale: 1
- with_datagen: False
- verbose: 0
-Nb_GTSRB5_r3:
- notebook_id: GTSRB5
- notebook_dir: GTSRB
- notebook_src: 05-Full-convolutions.ipynb
- notebook_tag: =3==done==
- overrides:
- run_dir: ./run/GTSRB5_done
- enhanced_dir: '{datasets_dir}/GTSRB/enhanced'
- datasets: "['set-48x48-L', 'set-48x48-RGB']"
- models: "{'v2':'get_model_v2', 'v3':'get_model_v3'}"
- batch_size: 64
- epochs: 16
- scale: 1
- with_datagen: True
- verbose: 0
-Nb_GTSRB6:
- notebook_id: GTSRB6
- notebook_dir: GTSRB
- notebook_src: 06-Notebook-as-a-batch.ipynb
- notebook_tag: default
-Nb_GTSRB7:
- notebook_id: GTSRB7
- notebook_dir: GTSRB
- notebook_src: 07-Show-report.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/GTSRB7_done
- report_dir: ./run/GTSRB5_done
-#
-# ------ IMDB ------------------------------------------------------
-#
-Nb_IMDB1:
- notebook_id: IMDB1
- notebook_dir: IMDB
- notebook_src: 01-One-hot-encoding.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- vocab_size: default
- hide_most_frequently: default
- batch_size: default
- epochs: default
-Nb_IMDB2:
- notebook_id: IMDB2
- notebook_dir: IMDB
- notebook_src: 02-Keras-embedding.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- vocab_size: default
- hide_most_frequently: default
- review_len: default
- dense_vector_size: default
- batch_size: default
- epochs: default
- output_dir: default
-Nb_IMDB3:
- notebook_id: IMDB3
- notebook_dir: IMDB
- notebook_src: 03-Prediction.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- vocab_size: default
- review_len: default
- dictionaries_dir: default
-Nb_IMDB4:
- notebook_id: IMDB4
- notebook_dir: IMDB
- notebook_src: 04-Show-vectors.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- vocab_size: default
- review_len: default
- dictionaries_dir: default
-Nb_IMDB5:
- notebook_id: IMDB5
- notebook_dir: IMDB
- notebook_src: 05-LSTM-Keras.ipynb
- notebook_tag: default
-#
-# ------ SYNOP -----------------------------------------------------
-#
-Nb_LADYB1:
- notebook_id: LADYB1
- notebook_dir: SYNOP
- notebook_src: LADYB1-Ladybug.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- scale: default
- train_prop: default
- sequence_len: default
- predict_len: default
- batch_size: default
- epochs: default
-Nb_SYNOP1:
- notebook_id: SYNOP1
- notebook_dir: SYNOP
- notebook_src: SYNOP1-Preparation-of-data.ipynb
- notebook_tag: default
- overrides:
- output_dir: default
-Nb_SYNOP2:
- notebook_id: SYNOP2
- notebook_dir: SYNOP
- notebook_src: SYNOP2-First-predictions.ipynb
- notebook_tag: default
- overrides:
- scale: default
- train_prop: default
- sequence_len: default
- batch_size: default
- epochs: default
-Nb_SYNOP3:
- notebook_id: SYNOP3
- notebook_dir: SYNOP
- notebook_src: SYNOP3-12h-predictions.ipynb
- notebook_tag: default
- overrides:
- iterations: default
- scale: default
- train_prop: default
- sequence_len: default
- batch_size: default
- epochs: default
-#
-# ------ AE --------------------------------------------------------
-#
-Nb_AE1:
- notebook_id: AE1
- notebook_dir: AE
- notebook_src: 01-AE-with-MNIST.ipynb
- notebook_tag: default
-Nb_AE2:
- notebook_id: AE2
- notebook_dir: AE
- notebook_src: 02-AE-with-MNIST-post.ipynb
- notebook_tag: default
-#
-# ------ VAE -------------------------------------------------------
-#
-Nb_VAE1:
- notebook_id: VAE1
- notebook_dir: VAE
- notebook_src: 01-VAE-with-MNIST.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/VAE1_done
- scale: 1
- latent_dim: 2
- r_loss_factor: 0.994
- batch_size: 64
- epochs: 10
-Nb_VAE2:
- notebook_id: VAE2
- notebook_dir: VAE
- notebook_src: 02-VAE-with-MNIST-post.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/VAE1_done
-Nb_VAE5:
- notebook_id: VAE5
- notebook_dir: VAE
- notebook_src: 05-About-CelebA.ipynb
- notebook_tag: default
-Nb_VAE6:
- notebook_id: VAE6
- notebook_dir: VAE
- notebook_src: 06-Prepare-CelebA-datasets.ipynb
- notebook_tag: default
- overrides:
- scale: 0.01
- image_size: '(192,160)'
- output_dir: ./data
- exit_if_exist: False
-Nb_VAE7:
- notebook_id: VAE7
- notebook_dir: VAE
- notebook_src: 07-Check-CelebA.ipynb
- notebook_tag: default
- overrides:
- image_size: '(192,160)'
- enhanced_dir: '{datasets_dir}/celeba/enhanced'
-Nb_VAE8:
- notebook_id: VAE8
- notebook_dir: VAE
- notebook_src: 08-VAE-with-CelebA.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/VAE8_done
- scale: 1
- image_size: '(192,160)'
- enhanced_dir: '{datasets_dir}/celeba/enhanced'
- latent_dim: 300
- r_loss_factor: 0.6
- batch_size: 64
- epochs: 15
-Nb_VAE9:
- notebook_id: VAE9
- notebook_dir: VAE
- notebook_src: 09-VAE-with-CelebA-post.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/VAE8_done
- image_size: '(192,160)'
- enhanced_dir: '{datasets_dir}/celeba/enhanced'
-#
-# ------ Misc ------------------------------------------------------
-#
-Nb_ACTF1:
- notebook_id: ACTF1
- notebook_dir: Misc
- notebook_src: Activation-Functions.ipynb
- notebook_tag: default
-Nb_NP1:
- notebook_id: NP1
- notebook_dir: Misc
- notebook_src: Numpy.ipynb
- notebook_tag: default
-Nb_TSB1:
- notebook_id: TSB1
- notebook_dir: Misc
- notebook_src: Using-Tensorboard.ipynb
- notebook_tag: default
diff --git a/fidle/ci/OLD-small_cpu.yml b/fidle/ci/OLD-small_cpu.yml
deleted file mode 100644
index 135c785cca62e4fe2b34d208aad6ef7db45615aa..0000000000000000000000000000000000000000
--- a/fidle/ci/OLD-small_cpu.yml
+++ /dev/null
@@ -1,477 +0,0 @@
-_metadata_:
- version: '1.0'
- description: Full run on a small cpu
- output_tag: ==ci==
- output_ipynb: ./fidle/run/ci/ipynb
- output_html: ./fidle/run/ci/html
- report_json: ./fidle/run/ci/report.json
- report_error: ./fidle/run/ci/error.txt
- environment_vars:
- FIDLE_SAVE_FIGS: true
- TF_CPP_MIN_LOG_LEVEL: 2
-#
-# ------ LinearReg -------------------------------------------------
-#
-Nb_LINR1:
- notebook_id: LINR1
- notebook_dir: LinearReg
- notebook_src: 01-Linear-Regression.ipynb
- notebook_tag: default
-Nb_GRAD1:
- notebook_id: GRAD1
- notebook_dir: LinearReg
- notebook_src: 02-Gradient-descent.ipynb
- notebook_tag: default
-Nb_POLR1:
- notebook_id: POLR1
- notebook_dir: LinearReg
- notebook_src: 03-Polynomial-Regression.ipynb
- notebook_tag: default
-Nb_LOGR1:
- notebook_id: LOGR1
- notebook_dir: LinearReg
- notebook_src: 04-Logistic-Regression.ipynb
- notebook_tag: default
-Nb_PER57:
- notebook_id: PER57
- notebook_dir: IRIS
- notebook_src: 01-Simple-Perceptron.ipynb
- notebook_tag: default
-#
-# ------ BHPD ------------------------------------------------------
-#
-Nb_BHPD1:
- notebook_id: BHPD1
- notebook_dir: BHPD
- notebook_src: 01-DNN-Regression.ipynb
- notebook_tag: default
- overrides:
- fit_verbosity: 2
-Nb_BHPD2:
- notebook_id: BHPD2
- notebook_dir: BHPD
- notebook_src: 02-DNN-Regression-Premium.ipynb
- notebook_tag: default
- overrides:
- fit_verbosity: 2
-#
-# ------ MNIST -----------------------------------------------------
-#
-Nb_MNIST1:
- notebook_id: MNIST1
- notebook_dir: MNIST
- notebook_src: 01-DNN-MNIST.ipynb
- notebook_tag: default
- overrides:
- fit_verbosity: 2
-Nb_MNIST2:
- notebook_id: MNIST2
- notebook_dir: MNIST
- notebook_src: 02-CNN-MNIST.ipynb
- notebook_tag: default
- overrides:
- fit_verbosity: 2
-#
-# ------ GTSRB -----------------------------------------------------
-#
-Nb_GTSRB1:
- notebook_id: GTSRB1
- notebook_dir: GTSRB
- notebook_src: 01-Preparation-of-data.ipynb
- notebook_tag: default
- overrides:
- scale: 0.01
- output_dir: ./data
- progress_verbosity: 2
-
-Nb_GTSRB2:
- notebook_id: GTSRB2
- notebook_dir: GTSRB
- notebook_src: 02-First-convolutions.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/GTSRB2_done
- enhanced_dir: './data'
- dataset_name: set-24x24-L
- batch_size: 64
- epochs: 5
- scale: 1
- fit_verbosity: 2
-
-Nb_GTSRB3:
- notebook_id: GTSRB3
- notebook_dir: GTSRB
- notebook_src: 03-Tracking-and-visualizing.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/GTSRB3_done
- enhanced_dir: './data'
- dataset_name: set-24x24-L
- batch_size: 64
- epochs: 5
- scale: 1
- fit_verbosity: 2
-
-Nb_GTSRB4:
- notebook_id: GTSRB4
- notebook_dir: GTSRB
- notebook_src: 04-Data-augmentation.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/GTSRB4_done
- enhanced_dir: './data'
- dataset_name: set-24x24-L
- batch_size: 64
- epochs: 5
- scale: 1
- fit_verbosity: 2
-
-Nb_GTSRB5_r1:
- notebook_id: GTSRB5
- notebook_dir: GTSRB
- notebook_src: 05-Full-convolutions.ipynb
- notebook_tag: =1==ci==
- overrides:
- run_dir: ./run/GTSRB5_done
- enhanced_dir: './data'
- datasets: "['set-24x24-L', 'set-24x24-RGB']"
- models: "{'v1':'get_model_v1', 'v2':'get_model_v2'}"
- batch_size: 64
- epochs: 5
- scale: 1
- with_datagen: False
- fit_verbosity: 0
-
-Nb_GTSRB6:
- notebook_id: GTSRB6
- notebook_dir: GTSRB
- notebook_src: 06-Notebook-as-a-batch.ipynb
- notebook_tag: default
-
-Nb_GTSRB7:
- notebook_id: GTSRB7
- notebook_dir: GTSRB
- notebook_src: 07-Show-report.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/GTSRB7_done
- report_dir: ./run/GTSRB5_done
-#
-# ------ IMDB ------------------------------------------------------
-#
-Nb_IMDB1:
- notebook_id: IMDB1
- notebook_dir: IMDB
- notebook_src: 01-One-hot-encoding.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- vocab_size: default
- hide_most_frequently: default
- batch_size: default
- epochs: default
- fit_verbosity: 2
-
-Nb_IMDB2:
- notebook_id: IMDB2
- notebook_dir: IMDB
- notebook_src: 02-Keras-embedding.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- vocab_size: default
- hide_most_frequently: default
- review_len: default
- dense_vector_size: default
- batch_size: default
- epochs: default
- output_dir: default
-
-Nb_IMDB3:
- notebook_id: IMDB3
- notebook_dir: IMDB
- notebook_src: 03-Prediction.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- vocab_size: default
- review_len: default
- dictionaries_dir: default
-
-Nb_IMDB4:
- notebook_id: IMDB4
- notebook_dir: IMDB
- notebook_src: 04-Show-vectors.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- vocab_size: default
- review_len: default
- dictionaries_dir: default
-
-Nb_IMDB5:
- notebook_id: IMDB5
- notebook_dir: IMDB
- notebook_src: 05-LSTM-Keras.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- vocab_size: default
- hide_most_frequently: default
- review_len: default
- dense_vector_size: default
- batch_size: default
- epochs: default
- fit_verbosity: 2
- scale: .1
-#
-# ------ SYNOP -----------------------------------------------------
-#
-Nb_LADYB1:
- notebook_id: LADYB1
- notebook_dir: SYNOP
- notebook_src: LADYB1-Ladybug.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- scale: 0.1
- train_prop: default
- sequence_len: default
- predict_len: default
- batch_size: default
- epochs: default
- fit_verbosity: 2
-
-Nb_SYNOP1:
- notebook_id: SYNOP1
- notebook_dir: SYNOP
- notebook_src: SYNOP1-Preparation-of-data.ipynb
- notebook_tag: default
- overrides:
- output_dir: default
-
-Nb_SYNOP2:
- notebook_id: SYNOP2
- notebook_dir: SYNOP
- notebook_src: SYNOP2-First-predictions.ipynb
- notebook_tag: default
- overrides:
- scale: 0.1
- train_prop: default
- sequence_len: default
- batch_size: default
- epochs: default
-
-Nb_SYNOP3:
- notebook_id: SYNOP3
- notebook_dir: SYNOP
- notebook_src: SYNOP3-12h-predictions.ipynb
- notebook_tag: default
- overrides:
- iterations: default
- scale: default
- train_prop: default
- sequence_len: default
-#
-# ------ AE --------------------------------------------------------
-#
-Nb_AE1:
- notebook_id: AE1
- notebook_dir: AE
- notebook_src: 01-Prepare-MNIST-dataset.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- scale: 0.02
- prepared_dataset: default
- progress_verbosity: 2
-
-Nb_AE2:
- notebook_id: AE2
- notebook_dir: AE
- notebook_src: 02-AE-with-MNIST.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- prepared_dataset: default
- dataset_seed: default
- scale: default
- latent_dim: default
- train_prop: default
- batch_size: default
- epochs: default
-
-Nb_AE3:
- notebook_id: AE3
- notebook_dir: AE
- notebook_src: 03-AE-with-MNIST-post.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- prepared_dataset: default
- dataset_seed: default
- scale: default
- train_prop: default
-
-Nb_AE4:
- notebook_id: AE4
- notebook_dir: AE
- notebook_src: 04-ExtAE-with-MNIST.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- prepared_dataset: default
- dataset_seed: default
- scale: default
- latent_dim: default
- train_prop: default
- batch_size: default
- epochs: default
-
-Nb_AE5:
- notebook_id: AE5
- notebook_dir: AE
- notebook_src: 05-ExtAE-with-MNIST.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- prepared_dataset: default
- dataset_seed: default
- scale: default
- latent_dim: default
- train_prop: default
- batch_size: default
- epochs: default
-#
-# ------ VAE -------------------------------------------------------
-#
-Nb_VAE1:
- notebook_id: VAE1
- notebook_dir: VAE
- notebook_src: 01-VAE-with-MNIST.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- latent_dim: default
- loss_weights: default
- scale: 0.01
- seed: default
- batch_size: default
- epochs: default
- fit_verbosity: 2
-
-Nb_VAE2:
- notebook_id: VAE2
- notebook_dir: VAE
- notebook_src: 02-VAE-with-MNIST.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/VAE2.000
- latent_dim: default
- loss_weights: default
- scale: 0.01
- seed: default
- batch_size: default
- epochs: default
- fit_verbosity: 2
-
-Nb_VAE3:
- notebook_id: VAE3
- notebook_dir: VAE
- notebook_src: 03-VAE-with-MNIST-post.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/VAE2.000
- scale: default
- seed: default
-
-Nb_VAE5:
- notebook_id: VAE5
- notebook_dir: VAE
- notebook_src: 05-About-CelebA.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- progress_verbosity: 2
-
-Nb_VAE6:
- notebook_id: VAE6
- notebook_dir: VAE
- notebook_src: 06-Prepare-CelebA-datasets.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- scale: 0.01
- seed: default
- cluster_size: default
- image_size: default
- output_dir: ./data
- exit_if_exist: False
- progress_verbosity: 2
-
-Nb_VAE7:
- notebook_id: VAE7
- notebook_dir: VAE
- notebook_src: 07-Check-CelebA.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- image_size: default
- enhanced_dir: ./data
- progress_verbosity: 2
-
-Nb_VAE8:
- notebook_id: VAE8
- notebook_dir: VAE
- notebook_src: 08-VAE-with-CelebA.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- scale: 0.1
- image_size: default
- enhanced_dir: ./data
- latent_dim: default
- loss_weights: default
- batch_size: default
- epochs: default
- progress_verbosity: 2
-
-Nb_VAE9:
- notebook_id: VAE9
- notebook_dir: VAE
- notebook_src: 09-VAE-with-CelebA-post.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- image_size: default
- enhanced_dir: ./data
-
-# ------ DCGAN -----------------------------------------------------
-#
-Nb_SHEEP1:
- notebook_id: SHEEP1
- notebook_dir: DCGAN
- notebook_src: 01-DCGAN-Draw-me-a-sheep.ipynb
- notebook_tag: default
- overrides:
- scale: 0.005
- run_dir: default
- latent_dim: default
- epochs: 5
- batch_size: default
- num_img: default
- fit_verbosity: 2
-#
-# ------ Misc ------------------------------------------------------
-#
-Nb_ACTF1:
- notebook_id: ACTF1
- notebook_dir: Misc
- notebook_src: Activation-Functions.ipynb
- notebook_tag: default
-
-Nb_NP1:
- notebook_id: NP1
- notebook_dir: Misc
- notebook_src: Numpy.ipynb
- notebook_tag: default
diff --git a/fidle/ci/OLD-smart_gpu.yml b/fidle/ci/OLD-smart_gpu.yml
deleted file mode 100644
index fc8cd714bbe86c84d585ad568042713c12e97ae7..0000000000000000000000000000000000000000
--- a/fidle/ci/OLD-smart_gpu.yml
+++ /dev/null
@@ -1,571 +0,0 @@
-_metadata_:
- version: '1.0'
- description: Full run on a smart gpu
- output_tag: ==done==
- output_ipynb: ./fidle/run/done/ipynb
- output_html: ./fidle/run/done/html
- report_json: ./fidle/run/done/report.json
- report_error: ./fidle/run/done/error.txt
- environment_vars:
- FIDLE_SAVE_FIGS: true
- TF_CPP_MIN_LOG_LEVEL: 2
-#
-# ------ LinearReg -------------------------------------------------
-#
-Nb_LINR1:
- notebook_id: LINR1
- notebook_dir: LinearReg
- notebook_src: 01-Linear-Regression.ipynb
- notebook_tag: default
-Nb_GRAD1:
- notebook_id: GRAD1
- notebook_dir: LinearReg
- notebook_src: 02-Gradient-descent.ipynb
- notebook_tag: default
-Nb_POLR1:
- notebook_id: POLR1
- notebook_dir: LinearReg
- notebook_src: 03-Polynomial-Regression.ipynb
- notebook_tag: default
-Nb_LOGR1:
- notebook_id: LOGR1
- notebook_dir: LinearReg
- notebook_src: 04-Logistic-Regression.ipynb
- notebook_tag: default
-Nb_PER57:
- notebook_id: PER57
- notebook_dir: IRIS
- notebook_src: 01-Simple-Perceptron.ipynb
- notebook_tag: default
-#
-# ------ BHPD ------------------------------------------------------
-#
-Nb_BHPD1:
- notebook_id: BHPD1
- notebook_dir: BHPD
- notebook_src: 01-DNN-Regression.ipynb
- notebook_tag: default
- overrides:
- fit_verbosity: 2
-Nb_BHPD2:
- notebook_id: BHPD2
- notebook_dir: BHPD
- notebook_src: 02-DNN-Regression-Premium.ipynb
- notebook_tag: default
- overrides:
- fit_verbosity: 2
-#
-# ------ MNIST -----------------------------------------------------
-#
-Nb_MNIST1:
- notebook_id: MNIST1
- notebook_dir: MNIST
- notebook_src: 01-DNN-MNIST.ipynb
- notebook_tag: default
- overrides:
- fit_verbosity: 2
-Nb_MNIST2:
- notebook_id: MNIST2
- notebook_dir: MNIST
- notebook_src: 02-CNN-MNIST.ipynb
- notebook_tag: default
- overrides:
- fit_verbosity: 2
-#
-# ------ GTSRB -----------------------------------------------------
-#
-Nb_GTSRB1:
- notebook_id: GTSRB1
- notebook_dir: GTSRB
- notebook_src: 01-Preparation-of-data.ipynb
- notebook_tag: default
- overrides:
- scale: 0.01
- output_dir: ./data
- progress_verbosity: 2
-
-Nb_GTSRB2:
- notebook_id: GTSRB2
- notebook_dir: GTSRB
- notebook_src: 02-First-convolutions.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- enhanced_dir: '{datasets_dir}/GTSRB/enhanced'
- dataset_name: set-24x24-L
- batch_size: 64
- epochs: 5
- scale: 1
- fit_verbosity: 2
-
-Nb_GTSRB3:
- notebook_id: GTSRB3
- notebook_dir: GTSRB
- notebook_src: 03-Tracking-and-visualizing.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- enhanced_dir: '{datasets_dir}/GTSRB/enhanced'
- dataset_name: set-24x24-L
- batch_size: 64
- epochs: 5
- scale: 1
- fit_verbosity: 2
-
-Nb_GTSRB4:
- notebook_id: GTSRB4
- notebook_dir: GTSRB
- notebook_src: 04-Data-augmentation.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- enhanced_dir: '{datasets_dir}/GTSRB/enhanced'
- dataset_name: set-24x24-L
- batch_size: 64
- epochs: 5
- scale: 1
- fit_verbosity: 2
-
-Nb_GTSRB5_r1:
- notebook_id: GTSRB5
- notebook_dir: GTSRB
- notebook_src: 05-Full-convolutions.ipynb
- notebook_tag: =1==done==
- overrides:
- run_dir: default
- enhanced_dir: '{datasets_dir}/GTSRB/enhanced'
- datasets: "['set-24x24-L', 'set-24x24-RGB', 'set-48x48-L', 'set-48x48-RGB', 'set-24x24-L-LHE', 'set-24x24-RGB-HE', 'set-48x48-L-LHE', 'set-48x48-RGB-HE']"
- models: "{'v1':'get_model_v1', 'v2':'get_model_v2', 'v3':'get_model_v3'}"
- batch_size: 64
- epochs: 16
- scale: 1
- with_datagen: False
- fit_verbosity: 0
-
-Nb_GTSRB5_r2:
- notebook_id: GTSRB5
- notebook_dir: GTSRB
- notebook_src: 05-Full-convolutions.ipynb
- notebook_tag: =2==done==
- overrides:
- run_dir: default
- enhanced_dir: '{datasets_dir}/GTSRB/enhanced'
- datasets: "['set-24x24-L', 'set-24x24-RGB', 'set-48x48-L', 'set-48x48-RGB', 'set-24x24-L-LHE', 'set-24x24-RGB-HE', 'set-48x48-L-LHE', 'set-48x48-RGB-HE']"
- models: "{'v1':'get_model_v1', 'v2':'get_model_v2', 'v3':'get_model_v3'}"
- batch_size: 64
- epochs: 16
- scale: 1
- with_datagen: False
- fit_verbosity: 0
-
-Nb_GTSRB5_r3:
- notebook_id: GTSRB5
- notebook_dir: GTSRB
- notebook_src: 05-Full-convolutions.ipynb
- notebook_tag: =3==done==
- overrides:
- run_dir: default
- enhanced_dir: '{datasets_dir}/GTSRB/enhanced'
- datasets: "['set-48x48-L', 'set-48x48-RGB']"
- models: "{'v2':'get_model_v2', 'v3':'get_model_v3'}"
- batch_size: 64
- epochs: 16
- scale: 1
- with_datagen: True
- fit_verbosity: 0
-
-Nb_GTSRB6:
- notebook_id: GTSRB6
- notebook_dir: GTSRB
- notebook_src: 06-Notebook-as-a-batch.ipynb
- notebook_tag: default
-
-Nb_GTSRB7:
- notebook_id: GTSRB7
- notebook_dir: GTSRB
- notebook_src: 07-Show-report.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- report_dir: ./run/GTSRB5
-#
-# ------ IMDB ------------------------------------------------------
-#
-Nb_IMDB1:
- notebook_id: IMDB1
- notebook_dir: IMDB
- notebook_src: 01-One-hot-encoding.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- vocab_size: default
- hide_most_frequently: default
- batch_size: default
- epochs: default
- fit_verbosity: 2
-
-Nb_IMDB2:
- notebook_id: IMDB2
- notebook_dir: IMDB
- notebook_src: 02-Keras-embedding.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- vocab_size: default
- hide_most_frequently: default
- review_len: default
- dense_vector_size: default
- batch_size: default
- epochs: default
- output_dir: default
-
-Nb_IMDB3:
- notebook_id: IMDB3
- notebook_dir: IMDB
- notebook_src: 03-Prediction.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- vocab_size: default
- review_len: default
- dictionaries_dir: default
-
-Nb_IMDB4:
- notebook_id: IMDB4
- notebook_dir: IMDB
- notebook_src: 04-Show-vectors.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- vocab_size: default
- review_len: default
- dictionaries_dir: default
-
-Nb_IMDB5:
- notebook_id: IMDB5
- notebook_dir: IMDB
- notebook_src: 05-LSTM-Keras.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- vocab_size: default
- hide_most_frequently: default
- review_len: default
- dense_vector_size: default
- batch_size: default
- epochs: default
- fit_verbosity: 2
- scale: .5
-#
-# ------ SYNOP -----------------------------------------------------
-#
-Nb_LADYB1:
- notebook_id: LADYB1
- notebook_dir: SYNOP
- notebook_src: LADYB1-Ladybug.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- scale: 1
- train_prop: default
- sequence_len: default
- predict_len: default
- batch_size: default
- epochs: default
- fit_verbosity: 2
-
-Nb_SYNOP1:
- notebook_id: SYNOP1
- notebook_dir: SYNOP
- notebook_src: SYNOP1-Preparation-of-data.ipynb
- notebook_tag: default
- overrides:
- output_dir: default
-
-Nb_SYNOP2:
- notebook_id: SYNOP2
- notebook_dir: SYNOP
- notebook_src: SYNOP2-First-predictions.ipynb
- notebook_tag: default
- overrides:
- scale: 1
- train_prop: default
- sequence_len: default
- batch_size: default
- epochs: default
-
-Nb_SYNOP3:
- notebook_id: SYNOP3
- notebook_dir: SYNOP
- notebook_src: SYNOP3-12h-predictions.ipynb
- notebook_tag: default
- overrides:
- iterations: default
- scale: default
- train_prop: default
- sequence_len: default
-#
-# ------ AE --------------------------------------------------------
-#
-Nb_AE1:
- notebook_id: AE1
- notebook_dir: AE
- notebook_src: 01-Prepare-MNIST-dataset.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- scale: 1
- prepared_dataset: default
- progress_verbosity: 2
-
-Nb_AE2:
- notebook_id: AE2
- notebook_dir: AE
- notebook_src: 02-AE-with-MNIST.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- prepared_dataset: default
- dataset_seed: default
- scale: 1
- latent_dim: default
- train_prop: default
- batch_size: default
- epochs: default
-
-Nb_AE3:
- notebook_id: AE3
- notebook_dir: AE
- notebook_src: 03-AE-with-MNIST-post.ipynb
- notebook_tag: default
- overrides:
- run_dir: ./run/AE2
- prepared_dataset: default
- dataset_seed: default
- scale: 1
- train_prop: default
-
-Nb_AE4:
- notebook_id: AE4
- notebook_dir: AE
- notebook_src: 04-ExtAE-with-MNIST.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- prepared_dataset: default
- dataset_seed: default
- scale: 1
- latent_dim: default
- train_prop: default
- batch_size: default
- epochs: default
-
-Nb_AE5:
- notebook_id: AE5
- notebook_dir: AE
- notebook_src: 05-ExtAE-with-MNIST.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- prepared_dataset: default
- dataset_seed: default
- scale: 1
- latent_dim: default
- train_prop: default
- batch_size: default
- epochs: default
-#
-# ------ VAE -------------------------------------------------------
-#
-Nb_VAE1:
- notebook_id: VAE1
- notebook_dir: VAE
- notebook_src: 01-VAE-with-MNIST.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- latent_dim: 2
- loss_weights: default
- scale: 1
- seed: default
- batch_size: default
- epochs: default
- fit_verbosity: 2
-
-Nb_VAE2:
- notebook_id: VAE2
- notebook_dir: VAE
- notebook_src: 02-VAE-with-MNIST.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- latent_dim: 2
- loss_weights: default
- scale: 1
- seed: default
- batch_size: default
- epochs: default
- fit_verbosity: 2
-
-Nb_VAE3:
- notebook_id: VAE3
- notebook_dir: VAE
- notebook_src: 03-VAE-with-MNIST-post.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- scale: 1
- seed: default
-
-Nb_VAE5:
- notebook_id: VAE5
- notebook_dir: VAE
- notebook_src: 05-About-CelebA.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- progress_verbosity: 2
-
-Nb_VAE6:
- notebook_id: VAE6
- notebook_dir: VAE
- notebook_src: 06-Prepare-CelebA-datasets.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- scale: 0.05
- seed: default
- cluster_size: default
- image_size: default
- output_dir: ./data
- exit_if_exist: False
- progress_verbosity: 2
-
-Nb_VAE7:
- notebook_id: VAE7
- notebook_dir: VAE
- notebook_src: 07-Check-CelebA.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- image_size: default
- enhanced_dir: ./data
- progress_verbosity: 2
-
-Nb_VAE8:
- notebook_id: VAE8
- notebook_dir: VAE
- notebook_src: 08-VAE-with-CelebA.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- scale: 1
- image_size: '(192,160)'
- enhanced_dir: '{datasets_dir}/celeba/enhanced'
- latent_dim: 300
- loss_weights: default
- batch_size: 64
- epochs: 15
- progress_verbosity: 2
-
-Nb_VAE9_r1:
- notebook_id: VAE9
- notebook_dir: VAE
- notebook_src: 09-VAE-with-CelebA-192x160.ipynb
- notebook_tag: =1==done==
- overrides:
- run_dir: ./run/VAE9_r1
- scale: 1
- image_size: '(192,160)'
- enhanced_dir: '{datasets_dir}/celeba/enhanced'
- latent_dim: 100
- loss_weights: '[.7,.3]'
- batch_size: 64
- epochs: 5
- progress_verbosity: 2
-
-Nb_VAE9_r2:
- notebook_id: VAE9
- notebook_dir: VAE
- notebook_src: 09-VAE-with-CelebA-192x160.ipynb
- notebook_tag: =2==done==
- overrides:
- run_dir: ./run/VAE9_r2
- scale: 1
- image_size: '(192,160)'
- enhanced_dir: '{datasets_dir}/celeba/enhanced'
- latent_dim: 100
- loss_weights: '[.5,.5]'
- batch_size: 64
- epochs: 5
- progress_verbosity: 2
-
-Nb_VAE9_r3:
- notebook_id: VAE9
- notebook_dir: VAE
- notebook_src: 09-VAE-with-CelebA-192x160.ipynb
- notebook_tag: =3==done==
- overrides:
- run_dir: ./run/VAE9_r3
- scale: 1
- image_size: '(192,160)'
- enhanced_dir: '{datasets_dir}/celeba/enhanced'
- latent_dim: 100
- loss_weights: '[.3,.7]'
- batch_size: 64
- epochs: 5
- progress_verbosity: 2
-
-Nb_VAE10:
- notebook_id: VAE10
- notebook_dir: VAE
- notebook_src: 10-VAE-with-CelebA-post.ipynb
- notebook_tag: default
- overrides:
- run_dir: default
- image_size: '(192,160)'
- enhanced_dir: '{datasets_dir}/celeba/enhanced'
-
-# ------ DCGAN -----------------------------------------------------
-#
-Nb_SHEEP1:
- notebook_id: SHEEP1
- notebook_dir: DCGAN
- notebook_src: 01-DCGAN-Draw-me-a-sheep.ipynb
- notebook_tag: default
- overrides:
- scale: 1
- run_dir: ./run/SHEEP1
- latent_dim: default
- epochs: 10
- batch_size: 32
- num_img: 12
- fit_verbosity: 2
-
-Nb_SHEEP2:
- notebook_id: SHEEP2
- notebook_dir: DCGAN
- notebook_src: 02-WGANGP-Draw-me-a-sheep.ipynb
- notebook_tag: default
- overrides:
- scale: 1
- run_dir: ./run/SHEEP2
- latent_dim: 80
- epochs: 3
- batch_size: 64
- num_img: 12
- fit_verbosity: 2
-#
-# ------ Misc ------------------------------------------------------
-#
-Nb_ACTF1:
- notebook_id: ACTF1
- notebook_dir: Misc
- notebook_src: Activation-Functions.ipynb
- notebook_tag: default
-
-Nb_NP1:
- notebook_id: NP1
- notebook_dir: Misc
- notebook_src: Numpy.ipynb
- notebook_tag: default
diff --git a/fidle/ci/default.yml b/fidle/ci/default.yml
index c222b601aba5c27f960b3e39bb4a69c4794ab14c..4eb039b12729aa96e4f7fb8f8ccae7cc5783018a 100644
--- a/fidle/ci/default.yml
+++ b/fidle/ci/default.yml
@@ -1,6 +1,6 @@
campain:
version: '1.0'
- description: Automatically generated ci profile (13/10/22 18:40:08)
+ description: Automatically generated ci profile (16/10/22 21:33:51)
directory: ./campains/default
existing_notebook: 'remove # remove|skip'
report_template: 'fidle # fidle|default'
@@ -35,6 +35,11 @@ BHPD2:
notebook: BHPD/02-DNN-Regression-Premium.ipynb
overrides:
fit_verbosity: default
+WINE1:
+ notebook: BHPD/03-DNN-Wine-Regression.ipynb
+ overrides:
+ fit_verbosity: default
+ dataset_name: default
#
# ------------ MNIST
@@ -361,3 +366,5 @@ SCRATCH1:
TSB1:
notebook: Misc/Using-Tensorboard.ipynb
overrides: ??
+PANDAS1:
+ notebook: Misc/Using-pandas.ipynb
diff --git a/fidle/ci/default_settings.yml b/fidle/ci/default_settings.yml
index 69df1d9e20bb1d027ad3a921b12e2b16a0c17de4..7ab4f53d8058d00f5ebcb2827bbdb1a84ecc6d7f 100644
--- a/fidle/ci/default_settings.yml
+++ b/fidle/ci/default_settings.yml
@@ -15,10 +15,13 @@ campain:
#
LINR1:
notebook: LinearReg/01-Linear-Regression.ipynb
+
GRAD1:
notebook: LinearReg/02-Gradient-descent.ipynb
+
POLR1:
notebook: LinearReg/03-Polynomial-Regression.ipynb
+
LOGR1:
notebook: LinearReg/04-Logistic-Regression.ipynb
@@ -35,11 +38,17 @@ BHPD1:
notebook: BHPD/01-DNN-Regression.ipynb
overrides:
fit_verbosity: 2
+
BHPD2:
notebook: BHPD/02-DNN-Regression-Premium.ipynb
overrides:
fit_verbosity: 2
+WINE1:
+ notebook: BHPD/03-DNN-Wine-Regression.ipynb
+ overrides:
+ fit_verbosity: 2
+ dataset_name: default
#
# ------------ MNIST
#
diff --git a/fidle/ci/scale1_settings.yml b/fidle/ci/scale1_settings.yml
index 87c3630faac96f685e1a120f12bc522c34ca6b93..ad1cac6063c0073dbcf39f981f71f294c3f05baf 100644
--- a/fidle/ci/scale1_settings.yml
+++ b/fidle/ci/scale1_settings.yml
@@ -15,10 +15,13 @@ campain:
#
LINR1:
notebook: LinearReg/01-Linear-Regression.ipynb
+
GRAD1:
notebook: LinearReg/02-Gradient-descent.ipynb
+
POLR1:
notebook: LinearReg/03-Polynomial-Regression.ipynb
+
LOGR1:
notebook: LinearReg/04-Logistic-Regression.ipynb
@@ -35,11 +38,24 @@ BHPD1:
notebook: BHPD/01-DNN-Regression.ipynb
overrides:
fit_verbosity: 2
+
BHPD2:
notebook: BHPD/02-DNN-Regression-Premium.ipynb
overrides:
fit_verbosity: 2
+WINE1.1:
+ notebook: BHPD/03-DNN-Wine-Regression.ipynb
+ overrides:
+ fit_verbosity: 2
+ dataset_name: winequality-red.csv
+
+WINE1.2:
+ notebook: BHPD/03-DNN-Wine-Regression.ipynb
+ overrides:
+ fit_verbosity: 2
+ dataset_name: winequality-red.csv
+
#
# ------------ MNIST
#