lightning/tests/base/models.py

157 lines
4.8 KiB
Python

from collections import OrderedDict
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.utils.data import DataLoader
from tests.base.datasets import TrialMNIST
try:
from test_tube import HyperOptArgumentParser
except ImportError:
# TODO: this should be discussed and moved out of this package
raise ImportError('Missing test-tube package.')
from pytorch_lightning.core.lightning import LightningModule
class Generator(nn.Module):
def __init__(self, latent_dim: tuple, img_shape: tuple):
super().__init__()
self.img_shape = img_shape
def block(in_feat, out_feat, normalize=True):
layers = [nn.Linear(in_feat, out_feat)]
if normalize:
layers.append(nn.BatchNorm1d(out_feat, 0.8))
layers.append(nn.LeakyReLU(0.2, inplace=True))
return layers
self.model = nn.Sequential(
*block(latent_dim, 128, normalize=False),
*block(128, 256),
*block(256, 512),
*block(512, 1024),
nn.Linear(1024, int(np.prod(img_shape))),
nn.Tanh()
)
def forward(self, z):
img = self.model(z)
img = img.view(img.size(0), *self.img_shape)
return img
class Discriminator(nn.Module):
def __init__(self, img_shape: tuple):
super().__init__()
self.model = nn.Sequential(
nn.Linear(int(np.prod(img_shape)), 512),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(512, 256),
nn.LeakyReLU(0.2, inplace=True),
nn.Linear(256, 1),
nn.Sigmoid(),
)
def forward(self, img):
img_flat = img.view(img.size(0), -1)
validity = self.model(img_flat)
return validity
class TestGAN(LightningModule):
"""Implements a basic GAN for the purpose of illustrating multiple optimizers."""
def __init__(self, hidden_dim, learning_rate, b1, b2, **kwargs):
super().__init__()
self.hidden_dim = hidden_dim
self.learning_rate = learning_rate
self.b1 = b1
self.b2 = b2
# networks
mnist_shape = (1, 28, 28)
self.generator = Generator(latent_dim=self.hidden_dim, img_shape=mnist_shape)
self.discriminator = Discriminator(img_shape=mnist_shape)
# cache for generated images
self.generated_imgs = None
self.last_imgs = None
def forward(self, z):
return self.generator(z)
def adversarial_loss(self, y_hat, y):
return F.binary_cross_entropy(y_hat, y)
def training_step(self, batch, batch_idx, optimizer_idx=None):
imgs, _ = batch
self.last_imgs = imgs
# train generator
if optimizer_idx == 0:
# sample noise
z = torch.randn(imgs.shape[0], self.hidden_dim)
z = z.type_as(imgs)
# generate images
self.generated_imgs = self(z)
# ground truth result (ie: all fake)
# put on GPU because we created this tensor inside training_loop
valid = torch.ones(imgs.size(0), 1)
valid = valid.type_as(imgs)
# adversarial loss is binary cross-entropy
g_loss = self.adversarial_loss(self.discriminator(self.generated_imgs), valid)
tqdm_dict = {'g_loss': g_loss}
output = OrderedDict({
'loss': g_loss,
'progress_bar': tqdm_dict,
'log': tqdm_dict
})
return output
# train discriminator
if optimizer_idx == 1:
# Measure discriminator's ability to classify real from generated samples
# how well can it label as real?
valid = torch.ones(imgs.size(0), 1)
valid = valid.type_as(imgs)
real_loss = self.adversarial_loss(self.discriminator(imgs), valid)
# how well can it label as fake?
fake = torch.zeros(imgs.size(0), 1)
fake = fake.type_as(fake)
fake_loss = self.adversarial_loss(self.discriminator(self.generated_imgs.detach()), fake)
# discriminator loss is the average of these
d_loss = (real_loss + fake_loss) / 2
tqdm_dict = {'d_loss': d_loss}
output = OrderedDict({
'loss': d_loss,
'progress_bar': tqdm_dict,
'log': tqdm_dict
})
return output
def configure_optimizers(self):
lr = self.learning_rate
b1 = self.b1
b2 = self.b2
opt_g = torch.optim.Adam(self.generator.parameters(), lr=lr, betas=(b1, b2))
opt_d = torch.optim.Adam(self.discriminator.parameters(), lr=lr, betas=(b1, b2))
return [opt_g, opt_d], []
def train_dataloader(self):
return DataLoader(TrialMNIST(train=True, download=True), batch_size=16)