425 lines
15 KiB
Plaintext
425 lines
15 KiB
Plaintext
{
|
|
"nbformat": 4,
|
|
"nbformat_minor": 0,
|
|
"metadata": {
|
|
"colab": {
|
|
"name": "03-basic-gan.ipynb",
|
|
"provenance": [],
|
|
"collapsed_sections": [],
|
|
"include_colab_link": true
|
|
},
|
|
"kernelspec": {
|
|
"name": "python3",
|
|
"display_name": "Python 3"
|
|
},
|
|
"accelerator": "GPU"
|
|
},
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "view-in-github",
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"<a href=\"https://colab.research.google.com/github/PytorchLightning/pytorch-lightning/blob/master/notebooks/03-basic-gan.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "J37PBnE_x7IW",
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"# PyTorch Lightning Basic GAN Tutorial ⚡\n",
|
|
"\n",
|
|
"How to train a GAN!\n",
|
|
"\n",
|
|
"Main takeaways:\n",
|
|
"1. Generator and discriminator are arbitraty PyTorch modules.\n",
|
|
"2. training_step does both the generator and discriminator training.\n",
|
|
"\n",
|
|
"---\n",
|
|
"\n",
|
|
" - Give us a ⭐ [on Github](https://www.github.com/PytorchLightning/pytorch-lightning/)\n",
|
|
" - Check out [the documentation](https://pytorch-lightning.readthedocs.io/en/latest/)\n",
|
|
" - Join us [on Slack](https://join.slack.com/t/pytorch-lightning/shared_invite/zt-f6bl2l0l-JYMK3tbAgAmGRrlNr00f1A)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "kg2MKpRmybht",
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"### Setup\n",
|
|
"Lightning is easy to install. Simply `pip install pytorch-lightning`"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "LfrJLKPFyhsK",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"! pip install pytorch-lightning --quiet"
|
|
],
|
|
"execution_count": null,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "BjEPuiVLyanw",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"import os\n",
|
|
"from argparse import ArgumentParser\n",
|
|
"from collections import OrderedDict\n",
|
|
"\n",
|
|
"import numpy as np\n",
|
|
"import torch\n",
|
|
"import torch.nn as nn\n",
|
|
"import torch.nn.functional as F\n",
|
|
"import torchvision\n",
|
|
"import torchvision.transforms as transforms\n",
|
|
"from torch.utils.data import DataLoader, random_split\n",
|
|
"from torchvision.datasets import MNIST\n",
|
|
"\n",
|
|
"import pytorch_lightning as pl"
|
|
],
|
|
"execution_count": 2,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "OuXJzr4G2uHV",
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"### MNIST DataModule\n",
|
|
"\n",
|
|
"Below, we define a DataModule for the MNIST Dataset. To learn more about DataModules, check out our tutorial on them or see the [latest docs](https://pytorch-lightning.readthedocs.io/en/latest/datamodules.html)."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "DOY_nHu328g7",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"class MNISTDataModule(pl.LightningDataModule):\n",
|
|
"\n",
|
|
" def __init__(self, data_dir: str = './', batch_size: int = 64, num_workers: int = 8):\n",
|
|
" super().__init__()\n",
|
|
" self.data_dir = data_dir\n",
|
|
" self.batch_size = batch_size\n",
|
|
" self.num_workers = num_workers\n",
|
|
"\n",
|
|
" self.transform = transforms.Compose([\n",
|
|
" transforms.ToTensor(),\n",
|
|
" transforms.Normalize((0.1307,), (0.3081,))\n",
|
|
" ])\n",
|
|
"\n",
|
|
" # self.dims is returned when you call dm.size()\n",
|
|
" # Setting default dims here because we know them.\n",
|
|
" # Could optionally be assigned dynamically in dm.setup()\n",
|
|
" self.dims = (1, 28, 28)\n",
|
|
" self.num_classes = 10\n",
|
|
"\n",
|
|
" def prepare_data(self):\n",
|
|
" # download\n",
|
|
" MNIST(self.data_dir, train=True, download=True)\n",
|
|
" MNIST(self.data_dir, train=False, download=True)\n",
|
|
"\n",
|
|
" def setup(self, stage=None):\n",
|
|
"\n",
|
|
" # Assign train/val datasets for use in dataloaders\n",
|
|
" if stage == 'fit' or stage is None:\n",
|
|
" mnist_full = MNIST(self.data_dir, train=True, transform=self.transform)\n",
|
|
" self.mnist_train, self.mnist_val = random_split(mnist_full, [55000, 5000])\n",
|
|
"\n",
|
|
" # Assign test dataset for use in dataloader(s)\n",
|
|
" if stage == 'test' or stage is None:\n",
|
|
" self.mnist_test = MNIST(self.data_dir, train=False, transform=self.transform)\n",
|
|
"\n",
|
|
" def train_dataloader(self):\n",
|
|
" return DataLoader(self.mnist_train, batch_size=self.batch_size, num_workers=self.num_workers)\n",
|
|
"\n",
|
|
" def val_dataloader(self):\n",
|
|
" return DataLoader(self.mnist_val, batch_size=self.batch_size, num_workers=self.num_workers)\n",
|
|
"\n",
|
|
" def test_dataloader(self):\n",
|
|
" return DataLoader(self.mnist_test, batch_size=self.batch_size, num_workers=self.num_workers)"
|
|
],
|
|
"execution_count": 3,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "tW3c0QrQyF9P",
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"### A. Generator"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "0E2QDjl5yWtz",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"class Generator(nn.Module):\n",
|
|
" def __init__(self, latent_dim, img_shape):\n",
|
|
" super().__init__()\n",
|
|
" self.img_shape = img_shape\n",
|
|
"\n",
|
|
" def block(in_feat, out_feat, normalize=True):\n",
|
|
" layers = [nn.Linear(in_feat, out_feat)]\n",
|
|
" if normalize:\n",
|
|
" layers.append(nn.BatchNorm1d(out_feat, 0.8))\n",
|
|
" layers.append(nn.LeakyReLU(0.2, inplace=True))\n",
|
|
" return layers\n",
|
|
"\n",
|
|
" self.model = nn.Sequential(\n",
|
|
" *block(latent_dim, 128, normalize=False),\n",
|
|
" *block(128, 256),\n",
|
|
" *block(256, 512),\n",
|
|
" *block(512, 1024),\n",
|
|
" nn.Linear(1024, int(np.prod(img_shape))),\n",
|
|
" nn.Tanh()\n",
|
|
" )\n",
|
|
"\n",
|
|
" def forward(self, z):\n",
|
|
" img = self.model(z)\n",
|
|
" img = img.view(img.size(0), *self.img_shape)\n",
|
|
" return img"
|
|
],
|
|
"execution_count": 4,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "uyrltsGvyaI3",
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"### B. Discriminator"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "Ed3MR3vnyxyW",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"class Discriminator(nn.Module):\n",
|
|
" def __init__(self, img_shape):\n",
|
|
" super().__init__()\n",
|
|
"\n",
|
|
" self.model = nn.Sequential(\n",
|
|
" nn.Linear(int(np.prod(img_shape)), 512),\n",
|
|
" nn.LeakyReLU(0.2, inplace=True),\n",
|
|
" nn.Linear(512, 256),\n",
|
|
" nn.LeakyReLU(0.2, inplace=True),\n",
|
|
" nn.Linear(256, 1),\n",
|
|
" nn.Sigmoid(),\n",
|
|
" )\n",
|
|
"\n",
|
|
" def forward(self, img):\n",
|
|
" img_flat = img.view(img.size(0), -1)\n",
|
|
" validity = self.model(img_flat)\n",
|
|
"\n",
|
|
" return validity"
|
|
],
|
|
"execution_count": 5,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {
|
|
"id": "BwUMom3ryySK",
|
|
"colab_type": "text"
|
|
},
|
|
"source": [
|
|
"### C. GAN\n",
|
|
"\n",
|
|
"#### A couple of cool features to check out in this example...\n",
|
|
"\n",
|
|
" - We use `some_tensor.type_as(another_tensor)` to make sure we initialize new tensors on the right device (i.e. GPU, CPU).\n",
|
|
" - Lightning will put your dataloader data on the right device automatically\n",
|
|
" - In this example, we pull from latent dim on the fly, so we need to dynamically add tensors to the right device.\n",
|
|
" - `type_as` is the way we recommend to do this.\n",
|
|
" - This example shows how to use multiple dataloaders in your `LightningModule`."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "3vKszYf6y1Vv",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
" class GAN(pl.LightningModule):\n",
|
|
"\n",
|
|
" def __init__(\n",
|
|
" self,\n",
|
|
" channels,\n",
|
|
" width,\n",
|
|
" height,\n",
|
|
" latent_dim: int = 100,\n",
|
|
" lr: float = 0.0002,\n",
|
|
" b1: float = 0.5,\n",
|
|
" b2: float = 0.999,\n",
|
|
" batch_size: int = 64,\n",
|
|
" **kwargs\n",
|
|
" ):\n",
|
|
" super().__init__()\n",
|
|
" self.save_hyperparameters()\n",
|
|
"\n",
|
|
" # networks\n",
|
|
" data_shape = (channels, width, height)\n",
|
|
" self.generator = Generator(latent_dim=self.hparams.latent_dim, img_shape=data_shape)\n",
|
|
" self.discriminator = Discriminator(img_shape=data_shape)\n",
|
|
"\n",
|
|
" self.validation_z = torch.randn(8, self.hparams.latent_dim)\n",
|
|
"\n",
|
|
" self.example_input_array = torch.zeros(2, self.hparams.latent_dim)\n",
|
|
"\n",
|
|
" def forward(self, z):\n",
|
|
" return self.generator(z)\n",
|
|
"\n",
|
|
" def adversarial_loss(self, y_hat, y):\n",
|
|
" return F.binary_cross_entropy(y_hat, y)\n",
|
|
"\n",
|
|
" def training_step(self, batch, batch_idx, optimizer_idx):\n",
|
|
" imgs, _ = batch\n",
|
|
"\n",
|
|
" # sample noise\n",
|
|
" z = torch.randn(imgs.shape[0], self.hparams.latent_dim)\n",
|
|
" z = z.type_as(imgs)\n",
|
|
"\n",
|
|
" # train generator\n",
|
|
" if optimizer_idx == 0:\n",
|
|
"\n",
|
|
" # generate images\n",
|
|
" self.generated_imgs = self(z)\n",
|
|
"\n",
|
|
" # log sampled images\n",
|
|
" sample_imgs = self.generated_imgs[:6]\n",
|
|
" grid = torchvision.utils.make_grid(sample_imgs)\n",
|
|
" self.logger.experiment.add_image('generated_images', grid, 0)\n",
|
|
"\n",
|
|
" # ground truth result (ie: all fake)\n",
|
|
" # put on GPU because we created this tensor inside training_loop\n",
|
|
" valid = torch.ones(imgs.size(0), 1)\n",
|
|
" valid = valid.type_as(imgs)\n",
|
|
"\n",
|
|
" # adversarial loss is binary cross-entropy\n",
|
|
" g_loss = self.adversarial_loss(self.discriminator(self(z)), valid)\n",
|
|
" tqdm_dict = {'g_loss': g_loss}\n",
|
|
" output = OrderedDict({\n",
|
|
" 'loss': g_loss,\n",
|
|
" 'progress_bar': tqdm_dict,\n",
|
|
" 'log': tqdm_dict\n",
|
|
" })\n",
|
|
" return output\n",
|
|
"\n",
|
|
" # train discriminator\n",
|
|
" if optimizer_idx == 1:\n",
|
|
" # Measure discriminator's ability to classify real from generated samples\n",
|
|
"\n",
|
|
" # how well can it label as real?\n",
|
|
" valid = torch.ones(imgs.size(0), 1)\n",
|
|
" valid = valid.type_as(imgs)\n",
|
|
"\n",
|
|
" real_loss = self.adversarial_loss(self.discriminator(imgs), valid)\n",
|
|
"\n",
|
|
" # how well can it label as fake?\n",
|
|
" fake = torch.zeros(imgs.size(0), 1)\n",
|
|
" fake = fake.type_as(imgs)\n",
|
|
"\n",
|
|
" fake_loss = self.adversarial_loss(\n",
|
|
" self.discriminator(self(z).detach()), fake)\n",
|
|
"\n",
|
|
" # discriminator loss is the average of these\n",
|
|
" d_loss = (real_loss + fake_loss) / 2\n",
|
|
" tqdm_dict = {'d_loss': d_loss}\n",
|
|
" output = OrderedDict({\n",
|
|
" 'loss': d_loss,\n",
|
|
" 'progress_bar': tqdm_dict,\n",
|
|
" 'log': tqdm_dict\n",
|
|
" })\n",
|
|
" return output\n",
|
|
"\n",
|
|
" def configure_optimizers(self):\n",
|
|
" lr = self.hparams.lr\n",
|
|
" b1 = self.hparams.b1\n",
|
|
" b2 = self.hparams.b2\n",
|
|
"\n",
|
|
" opt_g = torch.optim.Adam(self.generator.parameters(), lr=lr, betas=(b1, b2))\n",
|
|
" opt_d = torch.optim.Adam(self.discriminator.parameters(), lr=lr, betas=(b1, b2))\n",
|
|
" return [opt_g, opt_d], []\n",
|
|
"\n",
|
|
" def on_epoch_end(self):\n",
|
|
" z = self.validation_z.type_as(self.generator.model[0].weight)\n",
|
|
"\n",
|
|
" # log sampled images\n",
|
|
" sample_imgs = self(z)\n",
|
|
" grid = torchvision.utils.make_grid(sample_imgs)\n",
|
|
" self.logger.experiment.add_image('generated_images', grid, self.current_epoch)"
|
|
],
|
|
"execution_count": 6,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "Ey5FmJPnzm_E",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"dm = MNISTDataModule()\n",
|
|
"model = GAN(*dm.size())\n",
|
|
"trainer = pl.Trainer(gpus=1, max_epochs=5, progress_bar_refresh_rate=20)\n",
|
|
"trainer.fit(model, dm)"
|
|
],
|
|
"execution_count": null,
|
|
"outputs": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"metadata": {
|
|
"id": "MlECc7cHzolp",
|
|
"colab_type": "code",
|
|
"colab": {}
|
|
},
|
|
"source": [
|
|
"# Start tensorboard.\n",
|
|
"%load_ext tensorboard\n",
|
|
"%tensorboard --logdir lightning_logs/"
|
|
],
|
|
"execution_count": null,
|
|
"outputs": []
|
|
}
|
|
]
|
|
}
|