From cb776ade458f773cb537d9ee4ae449a1ac8bfe39 Mon Sep 17 00:00:00 2001
From: Jean-Luc Parouty <Jean-Luc.Parouty@simap.grenoble-inp.fr>
Date: Sun, 3 Mar 2024 20:56:31 +0100
Subject: [PATCH] Update notebook names, toc and ci (3.0.9)
---
AE.Keras3/01-Prepare-MNIST-dataset.ipynb | 4 +-
AE.Keras3/02-AE-with-MNIST.ipynb | 4 +-
AE.Keras3/03-AE-with-MNIST-post.ipynb | 6 +-
AE.Keras3/04-ExtAE-with-MNIST.ipynb | 4 +-
AE.Keras3/05-ExtAE-with-MNIST.ipynb | 4 +-
DCGAN.Lightning/01-DCGAN-PL.ipynb | 12 +-
README.ipynb | 34 ++---
README.md | 22 ++--
VAE.Keras3/01-VAE-with-MNIST-LossLayer.ipynb | 15 +--
VAE.Keras3/02-VAE-with-MNIST.ipynb | 4 +-
VAE.Keras3/03-VAE-with-MNIST-post.ipynb | 6 +-
fidle/about.yml | 2 +-
fidle/ci/default.yml | 21 +--
fidle/ci/gpu-scale1.yml | 130 +++++++++++++++++++
14 files changed, 197 insertions(+), 71 deletions(-)
diff --git a/AE.Keras3/01-Prepare-MNIST-dataset.ipynb b/AE.Keras3/01-Prepare-MNIST-dataset.ipynb
index be56312..8886e25 100644
--- a/AE.Keras3/01-Prepare-MNIST-dataset.ipynb
+++ b/AE.Keras3/01-Prepare-MNIST-dataset.ipynb
@@ -6,7 +6,7 @@
"source": [
"<img width=\"800px\" src=\"../fidle/img/header.svg\"></img>\n",
"\n",
- "# <!-- TITLE --> [AE1] - Prepare a noisy MNIST dataset\n",
+ "# <!-- TITLE --> [K3AE1] - Prepare a noisy MNIST dataset\n",
"<!-- DESC --> Episode 1: Preparation of a noisy MNIST dataset\n",
"\n",
"<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
@@ -52,7 +52,7 @@
"import fidle\n",
"\n",
"# Init Fidle environment\n",
- "run_id, run_dir, datasets_dir = fidle.init('AE1')"
+ "run_id, run_dir, datasets_dir = fidle.init('K3AE1')"
]
},
{
diff --git a/AE.Keras3/02-AE-with-MNIST.ipynb b/AE.Keras3/02-AE-with-MNIST.ipynb
index e593173..be3b4ff 100644
--- a/AE.Keras3/02-AE-with-MNIST.ipynb
+++ b/AE.Keras3/02-AE-with-MNIST.ipynb
@@ -6,7 +6,7 @@
"source": [
"<img width=\"800px\" src=\"../fidle/img/header.svg\"></img>\n",
"\n",
- "# <!-- TITLE --> [AE2] - Building and training an AE denoiser model\n",
+ "# <!-- TITLE --> [K3AE2] - Building and training an AE denoiser model\n",
"<!-- DESC --> Episode 1 : Construction of a denoising autoencoder and training of it with a noisy MNIST dataset.\n",
"\n",
"<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
@@ -66,7 +66,7 @@
"import fidle\n",
"\n",
"# Init Fidle environment\n",
- "run_id, run_dir, datasets_dir = fidle.init('AE2')"
+ "run_id, run_dir, datasets_dir = fidle.init('K3AE2')"
]
},
{
diff --git a/AE.Keras3/03-AE-with-MNIST-post.ipynb b/AE.Keras3/03-AE-with-MNIST-post.ipynb
index e9b3f78..3ecc33f 100644
--- a/AE.Keras3/03-AE-with-MNIST-post.ipynb
+++ b/AE.Keras3/03-AE-with-MNIST-post.ipynb
@@ -6,7 +6,7 @@
"source": [
"<img width=\"800px\" src=\"../fidle/img/header.svg\"></img>\n",
"\n",
- "# <!-- TITLE --> [AE3] - Playing with our denoiser model\n",
+ "# <!-- TITLE --> [K3AE3] - Playing with our denoiser model\n",
"<!-- DESC --> Episode 2 : Using the previously trained autoencoder to denoise data\n",
"<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
"\n",
@@ -53,7 +53,7 @@
"import fidle\n",
"\n",
"# Init Fidle environment\n",
- "run_id, run_dir, datasets_dir = fidle.init('AE3')"
+ "run_id, run_dir, datasets_dir = fidle.init('K3AE3')"
]
},
{
@@ -75,7 +75,7 @@
"outputs": [],
"source": [
"prepared_dataset = './data/mnist-noisy.h5'\n",
- "saved_models = './run/AE2/models'\n",
+ "saved_models = './run/K3AE2/models'\n",
"dataset_seed = 123\n",
"scale = 1\n",
"train_prop = .8"
diff --git a/AE.Keras3/04-ExtAE-with-MNIST.ipynb b/AE.Keras3/04-ExtAE-with-MNIST.ipynb
index 2e74e09..2a26788 100644
--- a/AE.Keras3/04-ExtAE-with-MNIST.ipynb
+++ b/AE.Keras3/04-ExtAE-with-MNIST.ipynb
@@ -6,7 +6,7 @@
"source": [
"<img width=\"800px\" src=\"../fidle/img/header.svg\"></img>\n",
"\n",
- "# <!-- TITLE --> [AE4] - Denoiser and classifier model\n",
+ "# <!-- TITLE --> [K3AE4] - Denoiser and classifier model\n",
"<!-- DESC --> Episode 4 : Construction of a denoiser and classifier model\n",
"\n",
"<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
@@ -64,7 +64,7 @@
"import fidle\n",
"\n",
"# Init Fidle environment\n",
- "run_id, run_dir, datasets_dir = fidle.init('AE4')"
+ "run_id, run_dir, datasets_dir = fidle.init('K3AE4')"
]
},
{
diff --git a/AE.Keras3/05-ExtAE-with-MNIST.ipynb b/AE.Keras3/05-ExtAE-with-MNIST.ipynb
index aa5cc5b..589ace8 100644
--- a/AE.Keras3/05-ExtAE-with-MNIST.ipynb
+++ b/AE.Keras3/05-ExtAE-with-MNIST.ipynb
@@ -6,7 +6,7 @@
"source": [
"<img width=\"800px\" src=\"../fidle/img/header.svg\"></img>\n",
"\n",
- "# <!-- TITLE --> [AE5] - Advanced denoiser and classifier model\n",
+ "# <!-- TITLE --> [K3AE5] - Advanced denoiser and classifier model\n",
"<!-- DESC --> Episode 5 : Construction of an advanced denoiser and classifier model\n",
"\n",
"<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
@@ -65,7 +65,7 @@
"\n",
"\n",
"# Init Fidle environment\n",
- "run_id, run_dir, datasets_dir = fidle.init('AE5')"
+ "run_id, run_dir, datasets_dir = fidle.init('K3AE5')"
]
},
{
diff --git a/DCGAN.Lightning/01-DCGAN-PL.ipynb b/DCGAN.Lightning/01-DCGAN-PL.ipynb
index 99e9ab5..cfb550e 100644
--- a/DCGAN.Lightning/01-DCGAN-PL.ipynb
+++ b/DCGAN.Lightning/01-DCGAN-PL.ipynb
@@ -6,7 +6,7 @@
"source": [
"<img width=\"800px\" src=\"../fidle/img/header.svg\"></img>\n",
"\n",
- "# <!-- TITLE --> [SHEEP3] - A DCGAN to Draw a Sheep, using Pytorch Lightning\n",
+ "# <!-- TITLE --> [PLSHEEP3] - A DCGAN to Draw a Sheep, using Pytorch Lightning\n",
"<!-- DESC --> \"Draw me a sheep\", revisited with a DCGAN, using Pytorch Lightning\n",
"<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
"\n",
@@ -66,7 +66,7 @@
"from modules.Discriminators import *\n",
"\n",
"# Init Fidle environment\n",
- "run_id, run_dir, datasets_dir = fidle.init('SHEEP3')"
+ "run_id, run_dir, datasets_dir = fidle.init('PLSHEEP3')"
]
},
{
@@ -390,7 +390,7 @@
"metadata": {},
"outputs": [],
"source": [
- "gan = GAN.load_from_checkpoint('./run/SHEEP3/models/bestModel.ckpt')"
+ "gan = GAN.load_from_checkpoint(f'{run_dir}/models/bestModel.ckpt')"
]
},
{
@@ -445,9 +445,9 @@
],
"metadata": {
"kernelspec": {
- "display_name": "Fidle-keras 3",
+ "display_name": "fidle-env",
"language": "python",
- "name": "fidle-k3"
+ "name": "python3"
},
"language_info": {
"codemirror_mode": {
@@ -459,7 +459,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.11.6"
+ "version": "3.9.2"
}
},
"nbformat": 4,
diff --git a/README.ipynb b/README.ipynb
index 311cc15..8b92b21 100644
--- a/README.ipynb
+++ b/README.ipynb
@@ -3,13 +3,13 @@
{
"cell_type": "code",
"execution_count": 1,
- "id": "42b2ce5d",
+ "id": "60a4d6df",
"metadata": {
"execution": {
- "iopub.execute_input": "2024-03-03T13:46:52.756661Z",
- "iopub.status.busy": "2024-03-03T13:46:52.756452Z",
- "iopub.status.idle": "2024-03-03T13:46:52.770894Z",
- "shell.execute_reply": "2024-03-03T13:46:52.769696Z"
+ "iopub.execute_input": "2024-03-03T19:38:38.844681Z",
+ "iopub.status.busy": "2024-03-03T19:38:38.844023Z",
+ "iopub.status.idle": "2024-03-03T19:38:38.854300Z",
+ "shell.execute_reply": "2024-03-03T19:38:38.853434Z"
},
"jupyter": {
"source_hidden": true
@@ -53,7 +53,7 @@
"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 -->3.0.8<!-- VERSION_END -->\n",
+ "Current Version : <!-- VERSION_BEGIN -->3.0.9<!-- VERSION_END -->\n",
"\n",
"\n",
"## Course materials\n",
@@ -68,7 +68,7 @@
"## Jupyter notebooks\n",
"\n",
"<!-- TOC_BEGIN -->\n",
- "<!-- Automatically generated on : 03/03/24 14:46:51 -->\n",
+ "<!-- Automatically generated on : 03/03/24 20:38:37 -->\n",
"\n",
"### Linear and logistic regression\n",
"- **[LINR1](LinearReg/01-Linear-Regression.ipynb)** - [Linear regression with direct resolution](LinearReg/01-Linear-Regression.ipynb) \n",
@@ -155,27 +155,27 @@
"Using a Tranformer to perform a sentiment analysis (IMDB) - Colab version\n",
"\n",
"### Unsupervised learning with an autoencoder neural network (AE), using Keras3\n",
- "- **[AE1](AE.Keras3/01-Prepare-MNIST-dataset.ipynb)** - [Prepare a noisy MNIST dataset](AE.Keras3/01-Prepare-MNIST-dataset.ipynb) \n",
+ "- **[K3AE1](AE.Keras3/01-Prepare-MNIST-dataset.ipynb)** - [Prepare a noisy MNIST dataset](AE.Keras3/01-Prepare-MNIST-dataset.ipynb) \n",
"Episode 1: Preparation of a noisy MNIST dataset\n",
- "- **[AE2](AE.Keras3/02-AE-with-MNIST.ipynb)** - [Building and training an AE denoiser model](AE.Keras3/02-AE-with-MNIST.ipynb) \n",
+ "- **[K3AE2](AE.Keras3/02-AE-with-MNIST.ipynb)** - [Building and training an AE denoiser model](AE.Keras3/02-AE-with-MNIST.ipynb) \n",
"Episode 1 : Construction of a denoising autoencoder and training of it with a noisy MNIST dataset.\n",
- "- **[AE3](AE.Keras3/03-AE-with-MNIST-post.ipynb)** - [Playing with our denoiser model](AE.Keras3/03-AE-with-MNIST-post.ipynb) \n",
+ "- **[K3AE3](AE.Keras3/03-AE-with-MNIST-post.ipynb)** - [Playing with our denoiser model](AE.Keras3/03-AE-with-MNIST-post.ipynb) \n",
"Episode 2 : Using the previously trained autoencoder to denoise data\n",
- "- **[AE4](AE.Keras3/04-ExtAE-with-MNIST.ipynb)** - [Denoiser and classifier model](AE.Keras3/04-ExtAE-with-MNIST.ipynb) \n",
+ "- **[K3AE4](AE.Keras3/04-ExtAE-with-MNIST.ipynb)** - [Denoiser and classifier model](AE.Keras3/04-ExtAE-with-MNIST.ipynb) \n",
"Episode 4 : Construction of a denoiser and classifier model\n",
- "- **[AE5](AE.Keras3/05-ExtAE-with-MNIST.ipynb)** - [Advanced denoiser and classifier model](AE.Keras3/05-ExtAE-with-MNIST.ipynb) \n",
+ "- **[K3AE5](AE.Keras3/05-ExtAE-with-MNIST.ipynb)** - [Advanced denoiser and classifier model](AE.Keras3/05-ExtAE-with-MNIST.ipynb) \n",
"Episode 5 : Construction of an advanced denoiser and classifier model\n",
"\n",
"### Generative network with Variational Autoencoder (VAE), using Keras3\n",
- "- **[VAE1](VAE.Keras3/01-VAE-with-MNIST-LossLayer.ipynb)** - [First VAE, using functional API (MNIST dataset)](VAE.Keras3/01-VAE-with-MNIST-LossLayer.ipynb) \n",
+ "- **[K3VAE1](VAE.Keras3/01-VAE-with-MNIST-LossLayer.ipynb)** - [First VAE, using functional API (MNIST dataset)](VAE.Keras3/01-VAE-with-MNIST-LossLayer.ipynb) \n",
"Construction and training of a VAE, using functional APPI, with a latent space of small dimension.\n",
- "- **[VAE2](VAE.Keras3/02-VAE-with-MNIST.ipynb)** - [VAE, using a custom model class (MNIST dataset)](VAE.Keras3/02-VAE-with-MNIST.ipynb) \n",
+ "- **[K3VAE2](VAE.Keras3/02-VAE-with-MNIST.ipynb)** - [VAE, using a custom model class (MNIST dataset)](VAE.Keras3/02-VAE-with-MNIST.ipynb) \n",
"Construction and training of a VAE, using model subclass, with a latent space of small dimension.\n",
- "- **[VAE3](VAE.Keras3/03-VAE-with-MNIST-post.ipynb)** - [Analysis of the VAE's latent space of MNIST dataset](VAE.Keras3/03-VAE-with-MNIST-post.ipynb) \n",
+ "- **[K3VAE3](VAE.Keras3/03-VAE-with-MNIST-post.ipynb)** - [Analysis of the VAE's latent space of MNIST dataset](VAE.Keras3/03-VAE-with-MNIST-post.ipynb) \n",
"Visualization and analysis of the VAE's latent space of the dataset MNIST\n",
"\n",
"### Generative Adversarial Networks (GANs), using Lightning\n",
- "- **[SHEEP3](DCGAN.Lightning/01-DCGAN-PL.ipynb)** - [A DCGAN to Draw a Sheep, using Pytorch Lightning](DCGAN.Lightning/01-DCGAN-PL.ipynb) \n",
+ "- **[PLSHEEP3](DCGAN.Lightning/01-DCGAN-PL.ipynb)** - [A DCGAN to Draw a Sheep, using Pytorch Lightning](DCGAN.Lightning/01-DCGAN-PL.ipynb) \n",
"\"Draw me a sheep\", revisited with a DCGAN, using Pytorch Lightning\n",
"\n",
"### Diffusion Model (DDPM) using PyTorch\n",
@@ -237,7 +237,7 @@
"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 : 03/03/24 14:46:51"
+ "# This README is visible under Jupiter Lab ;-)# Automatically generated on : 03/03/24 20:38:37"
]
}
],
diff --git a/README.md b/README.md
index cbcd47c..320b9d2 100644
--- a/README.md
+++ b/README.md
@@ -32,7 +32,7 @@ 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 -->3.0.8<!-- VERSION_END -->
+Current Version : <!-- VERSION_BEGIN -->3.0.9<!-- VERSION_END -->
## Course materials
@@ -47,7 +47,7 @@ Have a look about **[How to get and install](https://fidle.cnrs.fr/installation)
## Jupyter notebooks
<!-- TOC_BEGIN -->
-<!-- Automatically generated on : 03/03/24 14:46:51 -->
+<!-- Automatically generated on : 03/03/24 20:38:37 -->
### Linear and logistic regression
- **[LINR1](LinearReg/01-Linear-Regression.ipynb)** - [Linear regression with direct resolution](LinearReg/01-Linear-Regression.ipynb)
@@ -134,27 +134,27 @@ Using a Tranformer to perform a sentiment analysis (IMDB) - Jean Zay version
Using a Tranformer to perform a sentiment analysis (IMDB) - Colab version
### Unsupervised learning with an autoencoder neural network (AE), using Keras3
-- **[AE1](AE.Keras3/01-Prepare-MNIST-dataset.ipynb)** - [Prepare a noisy MNIST dataset](AE.Keras3/01-Prepare-MNIST-dataset.ipynb)
+- **[K3AE1](AE.Keras3/01-Prepare-MNIST-dataset.ipynb)** - [Prepare a noisy MNIST dataset](AE.Keras3/01-Prepare-MNIST-dataset.ipynb)
Episode 1: Preparation of a noisy MNIST dataset
-- **[AE2](AE.Keras3/02-AE-with-MNIST.ipynb)** - [Building and training an AE denoiser model](AE.Keras3/02-AE-with-MNIST.ipynb)
+- **[K3AE2](AE.Keras3/02-AE-with-MNIST.ipynb)** - [Building and training an AE denoiser model](AE.Keras3/02-AE-with-MNIST.ipynb)
Episode 1 : Construction of a denoising autoencoder and training of it with a noisy MNIST dataset.
-- **[AE3](AE.Keras3/03-AE-with-MNIST-post.ipynb)** - [Playing with our denoiser model](AE.Keras3/03-AE-with-MNIST-post.ipynb)
+- **[K3AE3](AE.Keras3/03-AE-with-MNIST-post.ipynb)** - [Playing with our denoiser model](AE.Keras3/03-AE-with-MNIST-post.ipynb)
Episode 2 : Using the previously trained autoencoder to denoise data
-- **[AE4](AE.Keras3/04-ExtAE-with-MNIST.ipynb)** - [Denoiser and classifier model](AE.Keras3/04-ExtAE-with-MNIST.ipynb)
+- **[K3AE4](AE.Keras3/04-ExtAE-with-MNIST.ipynb)** - [Denoiser and classifier model](AE.Keras3/04-ExtAE-with-MNIST.ipynb)
Episode 4 : Construction of a denoiser and classifier model
-- **[AE5](AE.Keras3/05-ExtAE-with-MNIST.ipynb)** - [Advanced denoiser and classifier model](AE.Keras3/05-ExtAE-with-MNIST.ipynb)
+- **[K3AE5](AE.Keras3/05-ExtAE-with-MNIST.ipynb)** - [Advanced denoiser and classifier model](AE.Keras3/05-ExtAE-with-MNIST.ipynb)
Episode 5 : Construction of an advanced denoiser and classifier model
### Generative network with Variational Autoencoder (VAE), using Keras3
-- **[VAE1](VAE.Keras3/01-VAE-with-MNIST-LossLayer.ipynb)** - [First VAE, using functional API (MNIST dataset)](VAE.Keras3/01-VAE-with-MNIST-LossLayer.ipynb)
+- **[K3VAE1](VAE.Keras3/01-VAE-with-MNIST-LossLayer.ipynb)** - [First VAE, using functional API (MNIST dataset)](VAE.Keras3/01-VAE-with-MNIST-LossLayer.ipynb)
Construction and training of a VAE, using functional APPI, with a latent space of small dimension.
-- **[VAE2](VAE.Keras3/02-VAE-with-MNIST.ipynb)** - [VAE, using a custom model class (MNIST dataset)](VAE.Keras3/02-VAE-with-MNIST.ipynb)
+- **[K3VAE2](VAE.Keras3/02-VAE-with-MNIST.ipynb)** - [VAE, using a custom model class (MNIST dataset)](VAE.Keras3/02-VAE-with-MNIST.ipynb)
Construction and training of a VAE, using model subclass, with a latent space of small dimension.
-- **[VAE3](VAE.Keras3/03-VAE-with-MNIST-post.ipynb)** - [Analysis of the VAE's latent space of MNIST dataset](VAE.Keras3/03-VAE-with-MNIST-post.ipynb)
+- **[K3VAE3](VAE.Keras3/03-VAE-with-MNIST-post.ipynb)** - [Analysis of the VAE's latent space of MNIST dataset](VAE.Keras3/03-VAE-with-MNIST-post.ipynb)
Visualization and analysis of the VAE's latent space of the dataset MNIST
### Generative Adversarial Networks (GANs), using Lightning
-- **[SHEEP3](DCGAN.Lightning/01-DCGAN-PL.ipynb)** - [A DCGAN to Draw a Sheep, using Pytorch Lightning](DCGAN.Lightning/01-DCGAN-PL.ipynb)
+- **[PLSHEEP3](DCGAN.Lightning/01-DCGAN-PL.ipynb)** - [A DCGAN to Draw a Sheep, using Pytorch Lightning](DCGAN.Lightning/01-DCGAN-PL.ipynb)
"Draw me a sheep", revisited with a DCGAN, using Pytorch Lightning
### Diffusion Model (DDPM) using PyTorch
diff --git a/VAE.Keras3/01-VAE-with-MNIST-LossLayer.ipynb b/VAE.Keras3/01-VAE-with-MNIST-LossLayer.ipynb
index d0206c4..104c0b4 100644
--- a/VAE.Keras3/01-VAE-with-MNIST-LossLayer.ipynb
+++ b/VAE.Keras3/01-VAE-with-MNIST-LossLayer.ipynb
@@ -6,7 +6,7 @@
"source": [
"<img width=\"800px\" src=\"../fidle/img/header.svg\"></img>\n",
"\n",
- "# <!-- TITLE --> [VAE1] - First VAE, using functional API (MNIST dataset)\n",
+ "# <!-- TITLE --> [K3VAE1] - First VAE, using functional API (MNIST dataset)\n",
"<!-- DESC --> Construction and training of a VAE, using functional APPI, with a latent space of small dimension.\n",
"\n",
"<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
@@ -59,7 +59,7 @@
"import fidle\n",
"\n",
"# Init Fidle environment\n",
- "run_id, run_dir, datasets_dir = fidle.init('VAE1')\n"
+ "run_id, run_dir, datasets_dir = fidle.init('K3VAE1')\n"
]
},
{
@@ -413,9 +413,9 @@
],
"metadata": {
"kernelspec": {
- "display_name": "Fidle-keras 3",
+ "display_name": "fidle-env",
"language": "python",
- "name": "fidle-k3"
+ "name": "python3"
},
"language_info": {
"codemirror_mode": {
@@ -427,12 +427,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
- "version": "3.11.6"
- },
- "vscode": {
- "interpreter": {
- "hash": "b3929042cc22c1274d74e3e946c52b845b57cb6d84f2d591ffe0519b38e4896d"
- }
+ "version": "3.9.2"
}
},
"nbformat": 4,
diff --git a/VAE.Keras3/02-VAE-with-MNIST.ipynb b/VAE.Keras3/02-VAE-with-MNIST.ipynb
index 2c1b740..0cc8c11 100644
--- a/VAE.Keras3/02-VAE-with-MNIST.ipynb
+++ b/VAE.Keras3/02-VAE-with-MNIST.ipynb
@@ -6,7 +6,7 @@
"source": [
"<img width=\"800px\" src=\"../fidle/img/header.svg\"></img>\n",
"\n",
- "# <!-- TITLE --> [VAE2] - VAE, using a custom model class (MNIST dataset)\n",
+ "# <!-- TITLE --> [K3VAE2] - VAE, using a custom model class (MNIST dataset)\n",
"<!-- DESC --> Construction and training of a VAE, using model subclass, with a latent space of small dimension.\n",
"\n",
"<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
@@ -64,7 +64,7 @@
"import fidle\n",
"\n",
"# Init Fidle environment\n",
- "run_id, run_dir, datasets_dir = fidle.init('VAE2')\n",
+ "run_id, run_dir, datasets_dir = fidle.init('K3VAE2')\n",
"\n",
"VAE.about()"
]
diff --git a/VAE.Keras3/03-VAE-with-MNIST-post.ipynb b/VAE.Keras3/03-VAE-with-MNIST-post.ipynb
index 8833ca1..1db7d95 100644
--- a/VAE.Keras3/03-VAE-with-MNIST-post.ipynb
+++ b/VAE.Keras3/03-VAE-with-MNIST-post.ipynb
@@ -6,7 +6,7 @@
"source": [
"<img width=\"800px\" src=\"../fidle/img/header.svg\"></img>\n",
"\n",
- "# <!-- TITLE --> [VAE3] - Analysis of the VAE's latent space of MNIST dataset\n",
+ "# <!-- TITLE --> [K3VAE3] - Analysis of the VAE's latent space of MNIST dataset\n",
"<!-- DESC --> Visualization and analysis of the VAE's latent space of the dataset MNIST\n",
"<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
"\n",
@@ -65,7 +65,7 @@
"import fidle\n",
"\n",
"# Init Fidle environment\n",
- "run_id, run_dir, datasets_dir = fidle.init('VAE3')"
+ "run_id, run_dir, datasets_dir = fidle.init('K3VAE3')"
]
},
{
@@ -83,7 +83,7 @@
"source": [
"scale = 1\n",
"seed = 123\n",
- "models_dir = './run/VAE2'"
+ "models_dir = './run/K3VAE2'"
]
},
{
diff --git a/fidle/about.yml b/fidle/about.yml
index 39c16fa..74bff6a 100644
--- a/fidle/about.yml
+++ b/fidle/about.yml
@@ -13,7 +13,7 @@
#
# This file describes the notebooks used by the Fidle training.
-version: 3.0.8
+version: 3.0.9
content: notebooks
name: Notebooks Fidle
description: All notebooks used by the Fidle training
diff --git a/fidle/ci/default.yml b/fidle/ci/default.yml
index f84337a..31d363e 100644
--- a/fidle/ci/default.yml
+++ b/fidle/ci/default.yml
@@ -1,6 +1,6 @@
campain:
version: '1.0'
- description: Automatically generated ci profile (03/03/24 14:46:51)
+ description: Automatically generated ci profile (03/03/24 20:38:37)
directory: ./campains/default
existing_notebook: 'remove # remove|skip'
report_template: 'fidle # fidle|default'
@@ -189,13 +189,13 @@ TRANS2:
#
# ------------ AE.Keras3
#
-AE1:
+K3AE1:
notebook: AE.Keras3/01-Prepare-MNIST-dataset.ipynb
overrides:
prepared_dataset: default
scale: default
progress_verbosity: default
-AE2:
+K3AE2:
notebook: AE.Keras3/02-AE-with-MNIST.ipynb
overrides:
prepared_dataset: default
@@ -206,14 +206,14 @@ AE2:
batch_size: default
epochs: default
fit_verbosity: default
-AE3:
+K3AE3:
notebook: AE.Keras3/03-AE-with-MNIST-post.ipynb
overrides:
prepared_dataset: default
dataset_seed: default
scale: default
train_prop: default
-AE4:
+K3AE4:
notebook: AE.Keras3/04-ExtAE-with-MNIST.ipynb
overrides:
prepared_dataset: default
@@ -223,7 +223,7 @@ AE4:
batch_size: default
epochs: default
fit_verbosity: default
-AE5:
+K3AE5:
notebook: AE.Keras3/05-ExtAE-with-MNIST.ipynb
overrides:
prepared_dataset: default
@@ -237,7 +237,7 @@ AE5:
#
# ------------ VAE.Keras3
#
-VAE1:
+K3VAE1:
notebook: VAE.Keras3/01-VAE-with-MNIST-LossLayer.ipynb
overrides:
latent_dim: default
@@ -247,7 +247,7 @@ VAE1:
batch_size: default
epochs: default
fit_verbosity: default
-VAE2:
+K3VAE2:
notebook: VAE.Keras3/02-VAE-with-MNIST.ipynb
overrides:
latent_dim: default
@@ -257,7 +257,7 @@ VAE2:
batch_size: default
epochs: default
fit_verbosity: default
-VAE3:
+K3VAE3:
notebook: VAE.Keras3/03-VAE-with-MNIST-post.ipynb
overrides:
scale: default
@@ -267,7 +267,7 @@ VAE3:
#
# ------------ DCGAN.Lightning
#
-SHEEP3:
+PLSHEEP3:
notebook: DCGAN.Lightning/01-DCGAN-PL.ipynb
overrides:
latent_dim: default
@@ -284,6 +284,7 @@ SHEEP3:
dataset_file: default
data_shape: default
scale: default
+ num_workers: default
#
# ------------ DDPM.PyTorch
diff --git a/fidle/ci/gpu-scale1.yml b/fidle/ci/gpu-scale1.yml
index 090c84a..254f875 100644
--- a/fidle/ci/gpu-scale1.yml
+++ b/fidle/ci/gpu-scale1.yml
@@ -205,6 +205,136 @@ K3LADYB1:
batch_size: 32
epochs: 10
+#
+# ------------ AE.Keras3
+#
+K3AE1:
+ notebook: AE.Keras3/01-Prepare-MNIST-dataset.ipynb
+ overrides:
+ prepared_dataset: default
+ scale: 1
+ progress_verbosity: 2
+
+K3AE2:
+ notebook: AE.Keras3/02-AE-with-MNIST.ipynb
+ after: K3AE1
+ overrides:
+ prepared_dataset: default
+ dataset_seed: default
+ scale: 1
+ latent_dim: 10
+ train_prop: default
+ batch_size: default
+ epochs: 20
+ fit_verbosity: default
+
+K3AE3:
+ notebook: AE.Keras3/03-AE-with-MNIST-post.ipynb
+ after: K3AE2
+ overrides:
+ prepared_dataset: default
+ dataset_seed: default
+ scale: default
+ train_prop: default
+
+K3AE4:
+ notebook: AE.Keras3/04-ExtAE-with-MNIST.ipynb
+ after: K3AE1
+ overrides:
+ prepared_dataset: default
+ dataset_seed: default
+ scale: 1
+ train_prop: default
+ batch_size: default
+ epochs: 20
+ fit_verbosity: default
+
+K3AE5:
+ notebook: AE.Keras3/05-ExtAE-with-MNIST.ipynb
+ after: K3AE1
+ overrides:
+ prepared_dataset: default
+ dataset_seed: default
+ scale: 1
+ train_prop: default
+ batch_size: default
+ epochs: 30
+ fit_verbosity: default
+
+#
+# ------------ VAE.Keras3
+#
+K3VAE1:
+ notebook: VAE.Keras3/01-VAE-with-MNIST-LossLayer.ipynb
+ overrides:
+ latent_dim: default
+ loss_weights: default
+ scale: 1
+ seed: default
+ batch_size: default
+ epochs: 20
+ fit_verbosity: default
+
+K3VAE2:
+ notebook: VAE.Keras3/02-VAE-with-MNIST.ipynb
+ overrides:
+ latent_dim: default
+ loss_weights: default
+ scale: 1
+ seed: default
+ batch_size: default
+ epochs: 20
+ fit_verbosity: default
+
+K3VAE3:
+ notebook: VAE.Keras3/03-VAE-with-MNIST-post.ipynb
+ after: K3VAE2
+ overrides:
+ scale: 1
+ seed: default
+ models_dir: default
+
+#
+# ------------ DCGAN.Lightning
+#
+PLSHEEP3_1:
+ notebook: DCGAN.Lightning/01-DCGAN-PL.ipynb
+ overrides:
+ latent_dim: default
+ gan_name: GAN
+ generator_name: Generator_2
+ discriminator_name: Discriminator_3
+ epochs: 30
+ lr: default
+ b1: default
+ b2: default
+ batch_size: 64
+ num_img: default
+ fit_verbosity: default
+ dataset_file: default
+ data_shape: default
+ scale: 1
+ num_workers: 2
+
+PLSHEEP3_2:
+ notebook: DCGAN.Lightning/01-DCGAN-PL.ipynb
+ overrides:
+ latent_dim: default
+ gan_name: WGANGP
+ generator_name: Generator_2
+ discriminator_name: Discriminator_3
+ epochs: 30
+ lr: default
+ b1: default
+ b2: default
+ batch_size: 64
+ num_img: default
+ fit_verbosity: default
+ dataset_file: default
+ data_shape: default
+ scale: 1
+ num_workers: 2
+
#
# ------------ Misc
#
--
GitLab