Skip to content
Snippets Groups Projects
01-DCGAN-PL.ipynb 13.1 KiB
Newer Older
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<img width=\"800px\" src=\"../fidle/img/header.svg\"></img>\n",
    "\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",
    "## Objectives :\n",
    " - Build and train a DCGAN model with the Quick Draw dataset\n",
    " - Understanding DCGAN\n",
    "\n",
    "The [Quick draw dataset](https://quickdraw.withgoogle.com/data) contains about 50.000.000 drawings, made by real people...  \n",
    "We are using a subset of 117.555 of Sheep drawings  \n",
    "To get the dataset : [https://github.com/googlecreativelab/quickdraw-dataset](https://github.com/googlecreativelab/quickdraw-dataset)  \n",
    "Datasets in numpy bitmap file : [https://console.cloud.google.com/storage/quickdraw_dataset/full/numpy_bitmap](https://console.cloud.google.com/storage/quickdraw_dataset/full/numpy_bitmap)   \n",
    "Sheep dataset : [https://storage.googleapis.com/quickdraw_dataset/full/numpy_bitmap/sheep.npy](https://storage.googleapis.com/quickdraw_dataset/full/numpy_bitmap/sheep.npy) (94.3 Mo)\n",
    "\n",
    "\n",
    "## What we're going to do :\n",
    "\n",
    " - Have a look to the dataset\n",
    " - Defining a GAN model\n",
    " - Build the model\n",
    " - Train it\n",
    " - Have a look of the results"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 1 - Init and parameters\n",
    "#### Python init"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc's avatar
Jean-Luc committed
   "execution_count": null,
Jean-Luc's avatar
Jean-Luc committed
   "outputs": [],
   "source": [
    "import os\n",
    "import sys\n",
    "import shutil\n",
    "\n",
    "import numpy as np\n",
    "import torch\n",
    "from lightning import Trainer\n",
    "from lightning.pytorch.callbacks                        import ModelCheckpoint\n",
    "from lightning.pytorch.loggers.tensorboard              import TensorBoardLogger\n",
    "\n",
    "import fidle\n",
    "\n",
    "from modules.QuickDrawDataModule import QuickDrawDataModule\n",
    "\n",
    "from modules.GAN                 import GAN\n",
    "from modules.WGANGP              import WGANGP\n",
    "from modules.Generators          import *\n",
    "from modules.Discriminators      import *\n",
    "\n",
    "# Init Fidle environment\n",
    "run_id, run_dir, datasets_dir = fidle.init('PLSHEEP3')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
Jean-Luc's avatar
Jean-Luc committed
    "#### Few parameters\n",
    "scale=1, epochs=20 : Need 22' on a V100"
Jean-Luc's avatar
Jean-Luc committed
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "latent_dim          = 128\n",
    "\n",
    "gan_name            = 'WGANGP'\n",
    "generator_name      = 'Generator_2'\n",
    "discriminator_name  = 'Discriminator_3'\n",
    "    \n",
Jean-Luc's avatar
Jean-Luc committed
    "scale               = 0.001\n",
Jean-Luc's avatar
Jean-Luc committed
    "num_workers         = 2\n",
    "lr                  = 0.0001\n",
    "b1                  = 0.5\n",
    "b2                  = 0.999\n",
    "lambda_gp           = 10\n",
    "batch_size          = 64\n",
    "num_img             = 48\n",
    "fit_verbosity       = 2\n",
    "    \n",
    "dataset_file        = datasets_dir+'/QuickDraw/origine/sheep.npy' \n",
    "data_shape          = (28,28,1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Override parameters (batch mode) - Just forget this cell"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc's avatar
Jean-Luc committed
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "fidle.override('latent_dim', 'gan_name', 'generator_name', 'discriminator_name')  \n",
    "fidle.override('epochs', 'lr', 'b1', 'b2', 'batch_size', 'num_img', 'fit_verbosity')\n",
Jean-Luc's avatar
Jean-Luc committed
    "fidle.override('dataset_file', 'data_shape', 'scale', 'num_workers' )"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Cleaning"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc's avatar
Jean-Luc committed
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# You can comment these lines to keep each run...\n",
    "shutil.rmtree(f'{run_dir}/figs', ignore_errors=True)\n",
    "shutil.rmtree(f'{run_dir}/models', ignore_errors=True)\n",
    "shutil.rmtree(f'{run_dir}/tb_logs', ignore_errors=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 2 - Get some nice data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Get a Nice DataModule\n",
    "Our DataModule is defined in [./modules/QuickDrawDataModule.py](./modules/QuickDrawDataModule.py)   \n",
    "This is a [LightningDataModule](https://pytorch-lightning.readthedocs.io/en/stable/data/datamodule.html)"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc's avatar
Jean-Luc committed
   "execution_count": null,
Jean-Luc's avatar
Jean-Luc committed
   "outputs": [],
Jean-Luc's avatar
Jean-Luc committed
    "dm = QuickDrawDataModule(dataset_file, scale, batch_size, num_workers=num_workers)\n",
    "dm.setup()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Have a look"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc's avatar
Jean-Luc committed
   "execution_count": null,
Jean-Luc's avatar
Jean-Luc committed
   "outputs": [],
   "source": [
    "dl         = dm.train_dataloader()\n",
    "batch_data = next(iter(dl))\n",
    "\n",
    "fidle.scrawler.images( batch_data.reshape(-1,28,28), indices=range(batch_size), columns=12, x_size=1, y_size=1, \n",
    "                       y_padding=0,spines_alpha=0, save_as='01-Sheeps')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 3 - Get a nice GAN model\n",
    "\n",
    "Our Generators are defined in [./modules/Generators.py](./modules/Generators.py)  \n",
    "Our Discriminators are defined in [./modules/Discriminators.py](./modules/Discriminators.py)  \n",
    "\n",
    "\n",
    "Our GANs are defined in :\n",
    " - [./modules/GAN.py](./modules/GAN.py)  \n",
    " - [./modules/WGANGP.py](./modules/WGANGP.py)  \n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Retrieve class by name\n",
    "To be very flexible, we just specify class names as parameters.  \n",
    "The code below retrieves classes from their names."
   ]
  },
  {
   "cell_type": "code",
Jean-Luc's avatar
Jean-Luc committed
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "module=sys.modules['__main__']\n",
    "Generator_     = getattr(module, generator_name)\n",
    "Discriminator_ = getattr(module, discriminator_name)\n",
    "GAN_           = getattr(module, gan_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Basic test - Just to be sure it (could) works... ;-)"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc's avatar
Jean-Luc committed
   "execution_count": null,
Jean-Luc's avatar
Jean-Luc committed
   "outputs": [],
   "source": [
    "generator     = Generator_(     latent_dim=latent_dim, data_shape=data_shape )\n",
    "discriminator = Discriminator_( latent_dim=latent_dim, data_shape=data_shape )\n",
    "\n",
    "print('\\nFew tests :\\n')\n",
    "z = torch.randn(batch_size, latent_dim)\n",
    "print('z size        : ',z.size())\n",
    "\n",
    "fake_img = generator.forward(z)\n",
    "print('fake_img      : ', fake_img.size())\n",
    "\n",
    "p = discriminator.forward(fake_img)\n",
    "print('pred fake     : ', p.size())\n",
    "\n",
    "print('batch_data    : ',batch_data.size())\n",
    "\n",
    "p = discriminator.forward(batch_data)\n",
    "print('pred real     : ', p.size())\n",
    "\n",
    "print('\\nShow fake images :')\n",
    "nimg = fake_img.detach().numpy()\n",
    "fidle.scrawler.images( nimg.reshape(-1,28,28), indices=range(batch_size), columns=12, x_size=1, y_size=1, \n",
    "                       y_padding=0,spines_alpha=0, save_as='01-Sheeps')"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc's avatar
Jean-Luc committed
   "execution_count": null,
Jean-Luc's avatar
Jean-Luc committed
   "outputs": [],
   "source": [
    "print('Fake images : ', fake_img.size())\n",
    "print('Batch size  : ', batch_data.size())\n",
    "e = torch.distributions.uniform.Uniform(0, 1).sample([batch_size,1])\n",
    "e = e[:None,None,None]\n",
    "i = fake_img * e + (1-e)*batch_data\n",
    "\n",
    "print('\\ninterpolate images :')\n",
    "nimg = i.detach().numpy()\n",
    "fidle.scrawler.images( nimg.reshape(-1,28,28), indices=range(batch_size), columns=12, x_size=1, y_size=1, \n",
    "                       y_padding=0,spines_alpha=0, save_as='01-Sheeps')\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### GAN model\n",
    "To simplify our code, the GAN class is defined separately in the module [./modules/GAN.py](./modules/GAN.py)  \n",
    "Passing the classe names for generator/discriminator by parameter allows to stay modular and to use the PL checkpoints."
   ]
  },
  {
   "cell_type": "code",
Jean-Luc's avatar
Jean-Luc committed
   "execution_count": null,
Jean-Luc's avatar
Jean-Luc committed
   "outputs": [],
   "source": [
    "gan = GAN_( data_shape          = data_shape,\n",
    "            lr                  = lr,\n",
    "            b1                  = b1,\n",
    "            b2                  = b2,\n",
    "            lambda_gp           = lambda_gp,\n",
    "            batch_size          = batch_size, \n",
    "            latent_dim          = latent_dim, \n",
    "            generator_name      = generator_name, \n",
    "            discriminator_name  = discriminator_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 5 - Train it !\n",
    "#### Instantiate Callbacks, Logger & co.\n",
    "More about :\n",
    "- [Checkpoints](https://pytorch-lightning.readthedocs.io/en/stable/common/checkpointing_basic.html)\n",
    "- [modelCheckpoint](https://pytorch-lightning.readthedocs.io/en/stable/api/pytorch_lightning.callbacks.ModelCheckpoint.html#pytorch_lightning.callbacks.ModelCheckpoint)"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc's avatar
Jean-Luc committed
   "execution_count": null,
Jean-Luc's avatar
Jean-Luc committed
   "outputs": [],
   "source": [
    "\n",
    "# ---- for tensorboard logs\n",
    "#\n",
    "logger       = TensorBoardLogger(       save_dir       = f'{run_dir}',\n",
    "                                        name           = 'tb_logs'  )\n",
    "\n",
    "log_dir = os.path.abspath(f'{run_dir}/tb_logs')\n",
    "print('To access the logs with tensorboard, use this command line :')\n",
    "print(f'tensorboard --logdir {log_dir}')\n",
    "\n",
    "# ---- To save checkpoints\n",
    "#\n",
    "callback_checkpoints = ModelCheckpoint( dirpath        = f'{run_dir}/models', \n",
    "                                        filename       = 'bestModel', \n",
    "                                        save_top_k     = 1, \n",
    "                                        save_last      = True,\n",
    "                                        every_n_epochs = 1, \n",
    "                                        monitor        = \"g_loss\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Train it"
   ]
  },
  {
   "cell_type": "code",
Jean-Luc's avatar
Jean-Luc committed
   "execution_count": null,
Jean-Luc's avatar
Jean-Luc committed
   "outputs": [],
   "source": [
    "\n",
    "trainer = Trainer(\n",
    "    accelerator        = \"auto\",\n",
    "    max_epochs         = epochs,\n",
    "    callbacks          = [callback_checkpoints],\n",
    "    log_every_n_steps  = batch_size,\n",
    "    logger             = logger\n",
    ")\n",
    "\n",
    "trainer.fit(gan, dm)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Step 6 - Reload our best model\n",
    "Note : "
   ]
  },
  {
   "cell_type": "code",
Jean-Luc's avatar
Jean-Luc committed
   "execution_count": null,
Jean-Luc's avatar
Jean-Luc committed
   "outputs": [],
    "gan = GAN.load_from_checkpoint(f'{run_dir}/models/bestModel.ckpt')"
Jean-Luc's avatar
Jean-Luc committed
  {
   "cell_type": "code",
   "execution_count": null,
Jean-Luc's avatar
Jean-Luc committed
   "outputs": [],
   "source": [
    "nb_images = 96\n",
    "\n",
    "z = torch.randn(nb_images, latent_dim)\n",
    "print('z size        : ',z.size())\n",
    "\n",
Jean-Luc's avatar
Jean-Luc committed
    "if torch.cuda.is_available(): z=z.cuda()\n",
    "\n",
    "fake_img = gan.generator.forward(z)\n",
    "print('fake_img      : ', fake_img.size())\n",
    "\n",
    "nimg = fake_img.cpu().detach().numpy()\n",
    "fidle.scrawler.images( nimg.reshape(-1,28,28), indices=range(nb_images), columns=12, x_size=1, y_size=1, \n",
    "                       y_padding=0,spines_alpha=0, save_as='01-Sheeps')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "fidle.end()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "<img width=\"80px\" src=\"../fidle/img/logo-paysage.svg\"></img>"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "fidle-env",
  },
  "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"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}