diff --git a/BHPD.Keras3/02-DNN-Regression-Premium.ipynb b/BHPD.Keras3/02-DNN-Regression-Premium.ipynb
index 293486133f4c9463c5fcbd9f4805f0189ed44e01..d3a23c48895fe7ad95dea25c8dec4712a53877ce 100644
--- a/BHPD.Keras3/02-DNN-Regression-Premium.ipynb
+++ b/BHPD.Keras3/02-DNN-Regression-Premium.ipynb
@@ -7,7 +7,7 @@
"<img width=\"800px\" src=\"../fidle/img/header.svg\"></img>\n",
"\n",
"# <!-- TITLE --> [K3BHPD2] - Regression with a Dense Network (DNN) - Advanced code\n",
- " <!-- DESC --> A more advanced implementation of the precedent example\n",
+ " <!-- DESC --> A more advanced implementation of the precedent example, using Keras3\n",
" <!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
"\n",
"## Objectives :\n",
@@ -268,9 +268,7 @@
"source": [
"model=get_model_v1( (13,) )\n",
"\n",
- "model.summary()\n",
- "# img=keras.utils.plot_model( model, to_file='./run/model.png', show_shapes=True, show_layer_names=True, dpi=96)\n",
- "# display(img)"
+ "model.summary()"
]
},
{
@@ -289,10 +287,7 @@
"os.makedirs('./run/models', mode=0o750, exist_ok=True)\n",
"save_dir = \"./run/models/best_model.keras\"\n",
"\n",
- "# savemodel_callback = tf.keras.callbacks.ModelCheckpoint(filepath=save_dir, verbose=0, save_best_only=True)\n",
- "\n",
- "savemodel_callback = keras.callbacks.ModelCheckpoint( filepath=save_dir, monitor='val_mae', mode='max', save_best_only=True)\n",
- "\n"
+ "savemodel_callback = keras.callbacks.ModelCheckpoint( filepath=save_dir, monitor='val_mae', mode='max', save_best_only=True)"
]
},
{
@@ -310,7 +305,7 @@
"source": [
"history = model.fit(x_train,\n",
" y_train,\n",
- " epochs = 100,\n",
+ " epochs = 50,\n",
" batch_size = 10,\n",
" verbose = fit_verbosity,\n",
" validation_data = (x_test, y_test),\n",
diff --git a/README.ipynb b/README.ipynb
index b051119eed4685a0eae691d9d3ef5a5df270dc03..3b01dedb91291280fccca33c03bbd782e2899c50 100644
--- a/README.ipynb
+++ b/README.ipynb
@@ -3,13 +3,13 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "79c87fd3",
+ "id": "9fccea2b",
"metadata": {
"execution": {
- "iopub.execute_input": "2024-01-16T19:19:00.566206Z",
- "iopub.status.busy": "2024-01-16T19:19:00.565614Z",
- "iopub.status.idle": "2024-01-16T19:19:00.577256Z",
- "shell.execute_reply": "2024-01-16T19:19:00.576334Z"
+ "iopub.execute_input": "2024-01-16T21:04:27.072205Z",
+ "iopub.status.busy": "2024-01-16T21:04:27.071380Z",
+ "iopub.status.idle": "2024-01-16T21:04:27.081582Z",
+ "shell.execute_reply": "2024-01-16T21:04:27.080749Z"
},
"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 -->2.5.0<!-- VERSION_END -->\n",
+ "Current Version : <!-- VERSION_BEGIN -->2.5.1<!-- VERSION_END -->\n",
"\n",
"\n",
"## Course materials\n",
@@ -73,7 +73,7 @@
"The world of Deep Learning is changing very fast !\n",
"\n",
"<!-- TOC_BEGIN -->\n",
- "<!-- Automatically generated on : 16/01/24 20:18:59 -->\n",
+ "<!-- Automatically generated on : 16/01/24 22:04:25 -->\n",
"\n",
"### Linear and logistic regression\n",
"- **[LINR1](LinearReg/01-Linear-Regression.ipynb)** - [Linear regression with direct resolution](LinearReg/01-Linear-Regression.ipynb) \n",
@@ -89,21 +89,25 @@
"- **[PER57](Perceptron/01-Simple-Perceptron.ipynb)** - [Perceptron Model 1957](Perceptron/01-Simple-Perceptron.ipynb) \n",
"Example of use of a Perceptron, with sklearn and IRIS dataset of 1936 !\n",
"\n",
- "### BHPD regression (DNN), using Keras3\n",
+ "### BHPD regression (DNN), using Keras3/PyTorch\n",
"- **[K3BHPD1](BHPD.Keras3/01-DNN-Regression.ipynb)** - [Regression with a Dense Network (DNN)](BHPD.Keras3/01-DNN-Regression.ipynb) \n",
"Simple example of a regression with the dataset Boston Housing Prices Dataset (BHPD)\n",
"- **[K3BHPD2](BHPD.Keras3/02-DNN-Regression-Premium.ipynb)** - [Regression with a Dense Network (DNN) - Advanced code](BHPD.Keras3/02-DNN-Regression-Premium.ipynb) \n",
- "A more advanced implementation of the precedent example\n",
+ "A more advanced implementation of the precedent example, using Keras3\n",
"\n",
"### BHPD regression (DNN), using PyTorch\n",
"- **[PBHPD1](BHPD.PyTorch/01-DNN-Regression_PyTorch.ipynb)** - [Regression with a Dense Network (DNN)](BHPD.PyTorch/01-DNN-Regression_PyTorch.ipynb) \n",
"A Simple regression with a Dense Neural Network (DNN) using Pytorch - BHPD dataset\n",
"\n",
- "### Wine Quality prediction (DNN), using PyTorch Lightning\n",
+ "### Wine Quality prediction (DNN), using Keras3/PyTorch\n",
+ "- **[K3WINE1](Wine.Keras3/01-DNN-Wine-Regression.ipynb)** - [Wine quality prediction with a Dense Network (DNN)](Wine.Keras3/01-DNN-Wine-Regression.ipynb) \n",
+ "Another example of regression, with a wine quality prediction, using Keras 3 and PyTorch\n",
+ "\n",
+ "### Wine Quality prediction (DNN), using PyTorch/Lightning\n",
"- **[LWINE1](Wine.Lightning/01-DNN-Wine-Regression-lightning.ipynb)** - [Wine quality prediction with a Dense Network (DNN)](Wine.Lightning/01-DNN-Wine-Regression-lightning.ipynb) \n",
"Another example of regression, with a wine quality prediction, using PyTorch Lightning\n",
"\n",
- "### MNIST classification (DNN,CNN), using Keras3\n",
+ "### MNIST classification (DNN,CNN), using Keras3/PyTorch\n",
"- **[K3MNIST1](MNIST.Keras3/01-DNN-MNIST.ipynb)** - [Simple classification with DNN](MNIST.Keras3/01-DNN-MNIST.ipynb) \n",
"An example of classification using a dense neural network for the famous MNIST dataset\n",
"- **[K3MNIST2](MNIST.Keras3/02-CNN-MNIST.ipynb)** - [Simple classification with CNN](MNIST.Keras3/02-CNN-MNIST.ipynb) \n",
@@ -119,7 +123,7 @@
"- **[LMNIST2](MNIST.Lightning/02-CNN-MNIST_Lightning.ipynb)** - [Simple classification with CNN](MNIST.Lightning/02-CNN-MNIST_Lightning.ipynb) \n",
"An example of classification using a convolutional neural network for the famous MNIST dataset, using PyTorch Lightning\n",
"\n",
- "### Images classification with Convolutional Neural Networks (CNN), using Keras3\n",
+ "### Images classification GTSRB with Convolutional Neural Networks (CNN), using Keras3/PyTorch\n",
"- **[K3GTSRB1](GTSRB.Keras3/01-Preparation-of-data.ipynb)** - [Dataset analysis and preparation](GTSRB.Keras3/01-Preparation-of-data.ipynb) \n",
"Episode 1 : Analysis of the GTSRB dataset and creation of an enhanced dataset\n",
"- **[K3GTSRB2](GTSRB.Keras3/02-First-convolutions.ipynb)** - [First convolutions](GTSRB.Keras3/02-First-convolutions.ipynb) \n",
@@ -252,7 +256,7 @@
"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 : 16/01/24 20:18:59"
+ "# This README is visible under Jupiter Lab ;-)# Automatically generated on : 16/01/24 22:04:26"
]
}
],
diff --git a/README.md b/README.md
index f4d5867dce7f91bd3b178f6378a8fe3609686edc..5393036c2568974352d402c3189935c60562818e 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 -->2.5.0<!-- VERSION_END -->
+Current Version : <!-- VERSION_BEGIN -->2.5.1<!-- VERSION_END -->
## Course materials
@@ -52,7 +52,7 @@ For these reason, they are kept as examples, while we develop the Keras3/PyTorch
The world of Deep Learning is changing very fast !
<!-- TOC_BEGIN -->
-<!-- Automatically generated on : 16/01/24 20:18:59 -->
+<!-- Automatically generated on : 16/01/24 22:04:25 -->
### Linear and logistic regression
- **[LINR1](LinearReg/01-Linear-Regression.ipynb)** - [Linear regression with direct resolution](LinearReg/01-Linear-Regression.ipynb)
@@ -68,21 +68,25 @@ Simple example of logistic regression with a sklearn solution
- **[PER57](Perceptron/01-Simple-Perceptron.ipynb)** - [Perceptron Model 1957](Perceptron/01-Simple-Perceptron.ipynb)
Example of use of a Perceptron, with sklearn and IRIS dataset of 1936 !
-### BHPD regression (DNN), using Keras3
+### BHPD regression (DNN), using Keras3/PyTorch
- **[K3BHPD1](BHPD.Keras3/01-DNN-Regression.ipynb)** - [Regression with a Dense Network (DNN)](BHPD.Keras3/01-DNN-Regression.ipynb)
Simple example of a regression with the dataset Boston Housing Prices Dataset (BHPD)
- **[K3BHPD2](BHPD.Keras3/02-DNN-Regression-Premium.ipynb)** - [Regression with a Dense Network (DNN) - Advanced code](BHPD.Keras3/02-DNN-Regression-Premium.ipynb)
-A more advanced implementation of the precedent example
+A more advanced implementation of the precedent example, using Keras3
### BHPD regression (DNN), using PyTorch
- **[PBHPD1](BHPD.PyTorch/01-DNN-Regression_PyTorch.ipynb)** - [Regression with a Dense Network (DNN)](BHPD.PyTorch/01-DNN-Regression_PyTorch.ipynb)
A Simple regression with a Dense Neural Network (DNN) using Pytorch - BHPD dataset
-### Wine Quality prediction (DNN), using PyTorch Lightning
+### Wine Quality prediction (DNN), using Keras3/PyTorch
+- **[K3WINE1](Wine.Keras3/01-DNN-Wine-Regression.ipynb)** - [Wine quality prediction with a Dense Network (DNN)](Wine.Keras3/01-DNN-Wine-Regression.ipynb)
+Another example of regression, with a wine quality prediction, using Keras 3 and PyTorch
+
+### Wine Quality prediction (DNN), using PyTorch/Lightning
- **[LWINE1](Wine.Lightning/01-DNN-Wine-Regression-lightning.ipynb)** - [Wine quality prediction with a Dense Network (DNN)](Wine.Lightning/01-DNN-Wine-Regression-lightning.ipynb)
Another example of regression, with a wine quality prediction, using PyTorch Lightning
-### MNIST classification (DNN,CNN), using Keras3
+### MNIST classification (DNN,CNN), using Keras3/PyTorch
- **[K3MNIST1](MNIST.Keras3/01-DNN-MNIST.ipynb)** - [Simple classification with DNN](MNIST.Keras3/01-DNN-MNIST.ipynb)
An example of classification using a dense neural network for the famous MNIST dataset
- **[K3MNIST2](MNIST.Keras3/02-CNN-MNIST.ipynb)** - [Simple classification with CNN](MNIST.Keras3/02-CNN-MNIST.ipynb)
@@ -98,7 +102,7 @@ An example of classification using a dense neural network for the famous MNIST d
- **[LMNIST2](MNIST.Lightning/02-CNN-MNIST_Lightning.ipynb)** - [Simple classification with CNN](MNIST.Lightning/02-CNN-MNIST_Lightning.ipynb)
An example of classification using a convolutional neural network for the famous MNIST dataset, using PyTorch Lightning
-### Images classification with Convolutional Neural Networks (CNN), using Keras3
+### Images classification GTSRB with Convolutional Neural Networks (CNN), using Keras3/PyTorch
- **[K3GTSRB1](GTSRB.Keras3/01-Preparation-of-data.ipynb)** - [Dataset analysis and preparation](GTSRB.Keras3/01-Preparation-of-data.ipynb)
Episode 1 : Analysis of the GTSRB dataset and creation of an enhanced dataset
- **[K3GTSRB2](GTSRB.Keras3/02-First-convolutions.ipynb)** - [First convolutions](GTSRB.Keras3/02-First-convolutions.ipynb)
diff --git a/Wine.Keras2/01-DNN-Wine-Regression.ipynb b/Wine.Keras3/01-DNN-Wine-Regression.ipynb
similarity index 93%
rename from Wine.Keras2/01-DNN-Wine-Regression.ipynb
rename to Wine.Keras3/01-DNN-Wine-Regression.ipynb
index a443c845d13eecaca45e278a23b9c9aaea83a788..f3abe84f3f40c5f6cfecaecf2aa152971fa84740 100644
--- a/Wine.Keras2/01-DNN-Wine-Regression.ipynb
+++ b/Wine.Keras3/01-DNN-Wine-Regression.ipynb
@@ -6,8 +6,8 @@
"source": [
"<img width=\"800px\" src=\"../fidle/img/header.svg\"></img>\n",
"\n",
- "# <!-- TITLE --> [K2WINE1] - Wine quality prediction with a Dense Network (DNN)\n",
- " <!-- DESC --> Another example of regression, with a wine quality prediction, using Keras 2 and Tensorflow (obsolete)\n",
+ "# <!-- TITLE --> [K3WINE1] - Wine quality prediction with a Dense Network (DNN)\n",
+ " <!-- DESC --> Another example of regression, with a wine quality prediction, using Keras 3 and PyTorch\n",
" <!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
"\n",
"## Objectives :\n",
@@ -61,24 +61,18 @@
"metadata": {},
"outputs": [],
"source": [
- "# import os\n",
- "# os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'\n",
+ "import os\n",
+ "os.environ['KERAS_BACKEND'] = 'torch'\n",
"\n",
- "import tensorflow as tf\n",
- "from tensorflow import keras\n",
+ "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('K2WINE1')"
+ "run_id, run_dir, datasets_dir = fidle.init('K3WINE1')"
]
},
{
@@ -267,9 +261,9 @@
"outputs": [],
"source": [
"os.makedirs('./run/models', mode=0o750, exist_ok=True)\n",
- "save_dir = \"./run/models/best_model.h5\"\n",
+ "save_dir = \"./run/models/best_model.keras\"\n",
"\n",
- "savemodel_callback = tf.keras.callbacks.ModelCheckpoint(filepath=save_dir, verbose=0, save_best_only=True)"
+ "savemodel_callback = keras.callbacks.ModelCheckpoint( filepath=save_dir, monitor='val_mae', mode='max', save_best_only=True)"
]
},
{
@@ -365,7 +359,7 @@
"metadata": {},
"outputs": [],
"source": [
- "loaded_model = tf.keras.models.load_model('./run/models/best_model.h5')\n",
+ "loaded_model = keras.models.load_model('./run/models/best_model.keras')\n",
"loaded_model.summary()\n",
"print(\"Loaded.\")"
]
@@ -435,6 +429,16 @@
" print(f'{i:03d} {pred:.2f} {real} {delta:+.2f} ')"
]
},
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Few questions :\n",
+ "- Can this model be used for red wines from Bordeaux and/or Beaujolais?\n",
+ "- What are the limitations of this model?\n",
+ "- What are the limitations of this dataset?"
+ ]
+ },
{
"cell_type": "code",
"execution_count": null,
diff --git a/fidle/about.yml b/fidle/about.yml
index c3a168768f529c82c01867f9aae3cc03f5dd0a6b..ae56d2cb4b20b5551777093b06ba2af5e53ca19e 100644
--- a/fidle/about.yml
+++ b/fidle/about.yml
@@ -13,26 +13,27 @@
#
# This file describes the notebooks used by the Fidle training.
-version: 2.5.0
-content: notebooks
-name: Notebooks Fidle
-description: All notebooks used by the Fidle training
+version: 2.5.1
+content: notebooks
+name: Notebooks Fidle
+description: All notebooks used by the Fidle training
-readme_md: README.md
-readme_ipynb: README.ipynb
-default_ci: fidle/ci/default.yml
+readme_md: README.md
+readme_ipynb: README.ipynb
+default_ci: fidle/ci/default.yml
toc:
LinearReg: Linear and logistic regression
Perceptron: Perceptron Model 1957
- BHPD.Keras3: BHPD regression (DNN), using Keras3
+ BHPD.Keras3: BHPD regression (DNN), using Keras3/PyTorch
BHPD.PyTorch: BHPD regression (DNN), using PyTorch
- Wine.Lightning: Wine Quality prediction (DNN), using PyTorch Lightning
- MNIST.Keras3: MNIST classification (DNN,CNN), using Keras3
+ Wine.Keras3: Wine Quality prediction (DNN), using Keras3/PyTorch
+ Wine.Lightning: Wine Quality prediction (DNN), using PyTorch/Lightning
+ MNIST.Keras3: MNIST classification (DNN,CNN), using Keras3/PyTorch
MNIST.PyTorch: MNIST classification (DNN,CNN), using PyTorch
MNIST.Lightning: MNIST classification (DNN,CNN), using Lightning
- GTSRB.Keras3: Images classification with Convolutional Neural Networks (CNN), using Keras3
+ GTSRB.Keras3: Images classification GTSRB with Convolutional Neural Networks (CNN), using Keras3/PyTorch
Embedding.Keras2: Sentiment analysis with word embedding, using Keras2 (obsolete)
RNN.Keras2: Time series with Recurrent Neural Network (RNN), using Keras2 (obsolete)
Transformers.PyTorch: Sentiment analysis with transformer, using PyTorch
diff --git a/fidle/ci/default.yml b/fidle/ci/default.yml
index a22b264bd7894eeb3458a65687f3c16eda796736..46dc911ae36ad16f3a160ae8adc8942d162da648 100644
--- a/fidle/ci/default.yml
+++ b/fidle/ci/default.yml
@@ -1,6 +1,6 @@
campain:
version: '1.0'
- description: Automatically generated ci profile (16/01/24 20:18:59)
+ description: Automatically generated ci profile (16/01/24 22:04:25)
directory: ./campains/default
existing_notebook: 'remove # remove|skip'
report_template: 'fidle # fidle|default'
@@ -42,6 +42,15 @@ K3BHPD2:
PBHPD1:
notebook: BHPD.PyTorch/01-DNN-Regression_PyTorch.ipynb
+#
+# ------------ Wine.Keras3
+#
+K3WINE1:
+ notebook: Wine.Keras3/01-DNN-Wine-Regression.ipynb
+ overrides:
+ fit_verbosity: default
+ dataset_name: default
+
#
# ------------ Wine.Lightning
#