Skip to content
Snippets Groups Projects
02-AE-with-MNIST.ipynb 12.8 KiB
Newer Older
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<img width=\"800px\" src=\"../fidle/img/header.svg\"></img>\n",
    "# <!-- TITLE --> [K2AE2] - 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, using Keras 2 and Tensorflow (obsolete)\n",
    "\n",
    "<!-- AUTHOR : Jean-Luc Parouty (CNRS/SIMaP) -->\n",
    "\n",
    "## Objectives :\n",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    " - Understanding and implementing a denoizing **autoencoder** neurals network (AE)\n",
    " - First overview or example of Keras procedural syntax\n",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    "The calculation needs being important, it is preferable to use a very simple dataset such as MNIST.  \n",
    "The use of a GPU is often indispensable.\n",
    "\n",
    "## What we're going to do :\n",
    "\n",
    " - Defining a VAE model\n",
    " - Build the model\n",
    " - Train it\n",
    " - Follow the learning process with Tensorboard\n",
    " \n",
    "## Data Terminology :\n",
    "- `clean_train`, `clean_test` for noiseless images \n",
    "- `noisy_train`, `noisy_test` for noisy images\n",
    "- `denoised_test` for denoised images at the output of the model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    "## Step 1 - Init python stuff\n",
    "### 1.1 - Init"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "execution_count": null,
   "metadata": {},
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from skimage import io\n",
    "import random\n",
    "\n",
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "from tensorflow.keras import layers\n",
    "from tensorflow.keras.callbacks import ModelCheckpoint, TensorBoard\n",
    "\n",
    "import os,sys\n",
    "from importlib import reload\n",
    "import h5py\n",
    "\n",
    "from modules.MNIST          import MNIST\n",
    "from modules.ImagesCallback import ImagesCallback\n",
    "import fidle\n",
    "# Init Fidle environment\n",
    "run_id, run_dir, datasets_dir = fidle.init('K2AE2')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 1.2 - Parameters\n",
    "`prepared_dataset` : Filename of the prepared dataset (Need 400 Mo, but can be in ./data)  \n",
    "`dataset_seed` : Random seed for shuffling dataset  \n",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    "`scale` : % of the dataset to use (1. for 100%)  \n",
    "`latent_dim` : Dimension of the latent space  \n",
    "`train_prop` : Percentage for train (the rest being for the test)\n",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    "`batch_size` : Batch size  \n",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    "`epochs` : Nb of epochs for training\\\n",
    "`fit_verbosity` is the verbosity during training : 0 = silent, 1 = progress bar, 2 = one line per epoch\n"
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "prepared_dataset = './data/mnist-noisy.h5'\n",
    "dataset_seed     = 123\n",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    "\n",
    "scale            = .1\n",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    "\n",
    "latent_dim       = 10\n",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    "\n",
    "train_prop       = .8\n",
    "batch_size       = 128\n",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    "epochs           = 30\n",
    "fit_verbosity    = 1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Override parameters (batch mode) - Just forget this cell"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "execution_count": null,
   "metadata": {},
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "outputs": [],
   "source": [
    "fidle.override('prepared_dataset', 'dataset_seed', 'scale', 'latent_dim')\n",
    "fidle.override('train_prop', 'batch_size', 'epochs', 'fit_verbosity')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 2 - Retrieve dataset\n",
    "With our MNIST class, in one call, we can reload, rescale, shuffle and split our previously saved dataset :-)"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "execution_count": null,
   "metadata": {},
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "outputs": [],
   "source": [
    "clean_train,clean_test, noisy_train,noisy_test, _,_ = MNIST.reload_prepared_dataset(scale      = scale, \n",
    "                                                                                    train_prop = train_prop,\n",
    "                                                                                    seed       = dataset_seed,\n",
    "                                                                                    shuffle    = True,\n",
    "                                                                                    filename=prepared_dataset )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 3 - Build models"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Encoder"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "inputs    = keras.Input(shape=(28, 28, 1))\n",
    "x         = layers.Conv2D(32, 3, activation=\"relu\", strides=2, padding=\"same\")(inputs)\n",
    "x         = layers.Conv2D(64, 3, activation=\"relu\", strides=2, padding=\"same\")(x)\n",
    "x         = layers.Flatten()(x)\n",
    "x         = layers.Dense(16, activation=\"relu\")(x)\n",
    "z         = layers.Dense(latent_dim)(x)\n",
    "\n",
    "encoder = keras.Model(inputs, z, name=\"encoder\")\n",
    "# encoder.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Decoder"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "inputs  = keras.Input(shape=(latent_dim,))\n",
    "x       = layers.Dense(7 * 7 * 64, activation=\"relu\")(inputs)\n",
    "x       = layers.Reshape((7, 7, 64))(x)\n",
    "x       = layers.Conv2DTranspose(64, 3, activation=\"relu\", strides=2, padding=\"same\")(x)\n",
    "x       = layers.Conv2DTranspose(32, 3, activation=\"relu\", strides=2, padding=\"same\")(x)\n",
    "outputs = layers.Conv2DTranspose(1, 3, activation=\"sigmoid\", padding=\"same\")(x)\n",
    "\n",
    "decoder = keras.Model(inputs, outputs, name=\"decoder\")\n",
    "# decoder.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### AE\n"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "inputs    = keras.Input(shape=(28, 28, 1))\n",
    "\n",
    "latents   = encoder(inputs)\n",
    "outputs   = decoder(latents)\n",
    "\n",
    "ae = keras.Model(inputs,outputs, name=\"ae\")\n",
    "\n",
    "ae.compile(optimizer=keras.optimizers.Adam(), loss='binary_crossentropy')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 4 - Train\n",
    "20' on a CPU  \n",
    "1'12 on a GPU (V100, IDRIS)"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# ---- Callback : Images\n",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    "#\n",
    "fidle.utils.mkdir( run_dir + '/images')\n",
    "filename = run_dir + '/images/image-{epoch:03d}-{i:02d}.jpg'\n",
    "callback_images = ImagesCallback(filename, x=clean_test[:5], encoder=encoder,decoder=decoder)\n",
    "\n",
    "# ---- Callback : Best model\n",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    "#\n",
    "fidle.utils.mkdir( run_dir + '/models')\n",
    "filename = run_dir + '/models/best_model.h5'\n",
    "callback_bestmodel = tf.keras.callbacks.ModelCheckpoint(filepath=filename, verbose=0, save_best_only=True)\n",
    "\n",
    "# ---- Callback tensorboard\n",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    "#\n",
    "logdir = run_dir + '/logs'\n",
    "callback_tensorboard = TensorBoard(log_dir=logdir, histogram_freq=1)\n",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    "# callbacks_list = [callback_images, callback_bestmodel, callback_tensorboard]\n",
    "callbacks_list = [callback_images, callback_bestmodel]"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "execution_count": null,
   "metadata": {},
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "outputs": [],
   "source": [
    "chrono = fidle.Chrono()\n",
    "chrono.start()\n",
    "history = ae.fit(noisy_train, clean_train,\n",
    "                 batch_size      = batch_size,\n",
    "                 epochs          = epochs,\n",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    "                 verbose         = fit_verbosity,\n",
    "                 validation_data = (noisy_test, clean_test),\n",
    "                 callbacks       = callbacks_list  )\n",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
    "\n",
    "chrono.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 5 - History"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "execution_count": null,
   "metadata": {},
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "outputs": [],
   "source": [
    "fidle.scrawler.history(history,  plot={'loss':['loss','val_loss']}, save_as='01-history')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 6 - Denoising progress"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "execution_count": null,
   "metadata": {},
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "outputs": [],
   "source": [
    "imgs=[]\n",
    "for epoch in range(0,epochs,2):\n",
    "    for i in range(5):\n",
    "        filename = run_dir + '/images/image-{epoch:03d}-{i:02d}.jpg'.format(epoch=epoch, i=i)\n",
    "        img      = io.imread(filename)\n",
    "        imgs.append(img)      \n",
    "fidle.utils.subtitle('Real images (clean_test) :')\n",
    "fidle.scrawler.images(clean_test[:5], None, indices='all', columns=5, x_size=2,y_size=2, interpolation=None, save_as='02-original-real')\n",
    "fidle.utils.subtitle('Noisy images (noisy_test) :')\n",
    "fidle.scrawler.images(noisy_test[:5], None, indices='all', columns=5, x_size=2,y_size=2, interpolation=None, save_as='03-original-noisy')\n",
    "fidle.utils.subtitle('Evolution during the training period (denoised_test) :')\n",
    "fidle.scrawler.images(imgs, None, indices='all', columns=5, x_size=2,y_size=2, interpolation=None, y_padding=0.1, save_as='04-learning')\n",
    "fidle.utils.subtitle('Noisy images (noisy_test) :')\n",
    "fidle.scrawler.images(noisy_test[:5], None, indices='all', columns=5, x_size=2,y_size=2, interpolation=None, save_as=None)\n",
    "fidle.utils.subtitle('Real images (clean_test) :')\n",
    "fidle.scrawler.images(clean_test[:5], None, indices='all', columns=5, x_size=2,y_size=2, interpolation=None, save_as=None)\n"
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 7 - Evaluation\n",
    "**Note :** We will use the following data:\\\n",
    "`clean_train`, `clean_test` for noiseless images \\\n",
    "`noisy_train`, `noisy_test` for noisy images\\\n",
    "`denoised_test` for denoised images at the output of the model\n",
    " \n",
    "### 7.1 - Reload our best model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = keras.models.load_model(f'{run_dir}/models/best_model.h5')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 7.2 - Let's make a prediction"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "denoised_test = model.predict(noisy_test)\n",
    "\n",
    "print('Denoised images   (denoised_test) shape : ',denoised_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### 7.3 - Denoised images "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "i=random.randint(0,len(denoised_test)-8)\n",
    "j=i+8\n",
    "\n",
    "fidle.utils.subtitle('Noisy test images (input):')\n",
    "fidle.scrawler.images(noisy_test[i:j], None, indices='all', columns=8, x_size=2,y_size=2, interpolation=None, save_as='05-test-noisy')\n",
    "fidle.utils.subtitle('Denoised images (output):')\n",
    "fidle.scrawler.images(denoised_test[i:j], None, indices='all', columns=8, x_size=2,y_size=2, interpolation=None, save_as='06-test-predict')\n",
    "fidle.utils.subtitle('Real test images :')\n",
    "fidle.scrawler.images(clean_test[i:j], None, indices='all', columns=8, x_size=2,y_size=2, interpolation=None, save_as='07-test-real')"
  {
   "cell_type": "code",
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "execution_count": null,
   "metadata": {},
Jean-Luc Parouty's avatar
Jean-Luc Parouty committed
   "outputs": [],
   "source": [
    "fidle.end()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "<img width=\"80px\" src=\"../fidle/img/logo-paysage.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
}