lightning/tests/helpers/advanced_models.py

229 lines
7.0 KiB
Python

# Copyright The PyTorch Lightning team.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
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 pytorch_lightning.core.lightning import LightningModule
from tests.helpers.datasets import AverageDataset, MNIST, TrialMNIST
class Generator(nn.Module):
def __init__(self, latent_dim: int, 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 BasicGAN(LightningModule):
"""Implements a basic GAN for the purpose of illustrating multiple optimizers."""
def __init__(
self, hidden_dim: int = 128, learning_rate: float = 0.001, b1: float = 0.5, b2: float = 0.999, **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
self.example_input_array = torch.rand(2, self.hidden_dim)
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)
class ParityModuleRNN(LightningModule):
def __init__(self):
super().__init__()
self.rnn = nn.LSTM(10, 20, batch_first=True)
self.linear_out = nn.Linear(in_features=20, out_features=5)
self.example_input_array = torch.rand(2, 3, 10)
def forward(self, x):
seq, last = self.rnn(x)
return self.linear_out(seq)
def training_step(self, batch, batch_nb):
x, y = batch
y_hat = self(x)
loss = F.mse_loss(y_hat, y)
return {'loss': loss}
def configure_optimizers(self):
return torch.optim.Adam(self.parameters(), lr=0.02)
def train_dataloader(self):
return DataLoader(AverageDataset(), batch_size=30)
class ParityModuleMNIST(LightningModule):
def __init__(self):
super().__init__()
self.c_d1 = nn.Linear(in_features=28 * 28, out_features=128)
self.c_d1_bn = nn.BatchNorm1d(128)
self.c_d1_drop = nn.Dropout(0.3)
self.c_d2 = nn.Linear(in_features=128, out_features=10)
self.example_input_array = torch.rand(2, 1, 28, 28)
def forward(self, x):
x = x.view(x.size(0), -1)
x = self.c_d1(x)
x = torch.tanh(x)
x = self.c_d1_bn(x)
x = self.c_d1_drop(x)
x = self.c_d2(x)
return x
def training_step(self, batch, batch_nb):
x, y = batch
y_hat = self(x)
loss = F.cross_entropy(y_hat, y)
return {'loss': loss}
def configure_optimizers(self):
return torch.optim.Adam(self.parameters(), lr=0.02)
def train_dataloader(self):
return DataLoader(MNIST(
train=True,
download=True,
), batch_size=128, num_workers=1)