难点:转置卷积
import torch
import torch.nn as nn
from torch.utils.data import Dataset
import h5py
import pandas, numpy, random
import matplotlib.pyplot as plt
def generate_random_image(size):
random_data = torch.rand(size)
return random_data
def generate_random_seed(size):
random_data = torch.randn(size)
return random_data
class View(nn.Module):
def __init__(self, shape):
super().__init__()
self.shape = shape,
def forward(self, x):
return x.view(*self.shape)
def crop_centre(img, new_width, new_height):
height, width, _ = img.shape
startx = width//2 - new_width//2
starty = height//2 - new_height//2
return img[ starty:starty + new_height, startx:startx + new_width, :]
class CelebADataset(Dataset):
def __init__(self, file):
self.file_object = h5py.File(file, 'r')
self.dataset = self.file_object['img_align_celeba']
pass
def __len__(self):
return len(self.dataset)
def __getitem__(self, index):
if (index >= len(self.dataset)):
raise IndexError()
img = numpy.array(self.dataset[str(index)+'.jpg'])
# crop to 128x128 square
img = crop_centre(img, 128, 128)
return torch.cuda.FloatTensor(img).permute(2,0,1).view(1,3,128,128) / 255.0
def plot_image(self, index):
img = numpy.array(self.dataset[str(index)+'.jpg'])
# crop to 128x128 square
img = crop_centre(img, 128, 128)
plt.imshow(img, interpolation='nearest')
pass
pass
celeba_dataset = CelebADataset('mount/My Drive/Colab Notebooks/myo_gan/celeba_dataset/celeba_aligned_small.h5py')
celeba_dataset.plot_image(43)
class Discriminator(nn.Module):
def __init__(self):
# initialise parent pytorch class
super().__init__()
# define neural network layers
self.model = nn.Sequential(
# expect input of shape (1,3,128,128)
nn.Conv2d(3, 256, kernel_size=8, stride=2),
nn.BatchNorm2d(256),
nn.LeakyReLU(0.2),
nn.Conv2d(256, 256, kernel_size=8, stride=2),
nn.BatchNorm2d(256),
nn.LeakyReLU(0.2),
nn.Conv2d(256, 3, kernel_size=8, stride=2),
nn.LeakyReLU(0.2),
View(3*10*10),
nn.Linear(3*10*10, 1),
nn.Sigmoid()
)
# create loss function
self.loss_function = nn.BCELoss()
# create optimiser, simple stochastic gradient descent
self.optimiser = torch.optim.Adam(self.parameters(), lr=0.0001)
# counter and accumulator for progress
self.counter = 0;
self.progress = []
def forward(self, inputs):
# simply run model
return self.model(inputs)
def train(self, inputs, targets):
# calculate the output of the network
outputs = self.forward(inputs)
# calculate loss
loss = self.loss_function(outputs, targets)
# increase counter and accumulate error every 10
self.counter += 1;
if (self.counter % 10 == 0):
self.progress.append(loss.item())
pass
if (self.counter % 1000 == 0):
print("counter = ", self.counter)
pass
# zero gradients, perform a backward pass, update weights
self.optimiser.zero_grad()
loss.backward()
self.optimiser.step()
def plot_progress(self):
df = pandas.DataFrame(self.progress, columns=['loss'])
df.plot(ylim=(0), figsize=(16,8), alpha=0.1, marker='.', grid=True, yticks=(0, 0.25, 0.5, 1.0, 5.0))
D = Discriminator()
D.to(device)
for image_data_tensor in celeba_dataset:
# real data
D.train(image_data_tensor, torch.cuda.FloatTensor([1.0]))
# fake data
D.train(generate_random_image((1,3,128,128)), torch.cuda.FloatTensor([0.0]))
pass
# manually run discriminator to check it can tell real data from fake
for i in range(4):
image_data_tensor = celeba_dataset[random.randint(0,20000)]
print( D.forward( image_data_tensor ).item() )
pass
for i in range(4):
print( D.forward( generate_random_image((1,3,128,128))).item() )
pass
class Generator(nn.Module):
def __init__(self):
# initialise parent pytorch class
super().__init__()
# define neural network layers
self.model = nn.Sequential(
# input is a 1d array
nn.Linear(100, 3*11*11),
nn.LeakyReLU(0.2),
# reshape to 4d
View((1, 3, 11, 11)),
nn.ConvTranspose2d(3, 256, kernel_size=8, stride=2),
nn.BatchNorm2d(256),
nn.LeakyReLU(0.2),
nn.ConvTranspose2d(256, 256, kernel_size=8, stride=2),
nn.BatchNorm2d(256),
nn.LeakyReLU(0.2),
nn.ConvTranspose2d(256, 3, kernel_size=8, stride=2, padding=1),
nn.BatchNorm2d(3),
# output should be (1,3,128,128)
nn.Sigmoid()
)
# create optimiser, simple stochastic gradient descent
self.optimiser = torch.optim.Adam(self.parameters(), lr=0.0001)
# counter and accumulator for progress
self.counter = 0;
self.progress = []
pass
def forward(self, inputs):
# simply run model
return self.model(inputs)
def train(self, D, inputs, targets):
# calculate the output of the network
g_output = self.forward(inputs)
# pass onto Discriminator
d_output = D.forward(g_output)
# calculate error
loss = D.loss_function(d_output, targets)
# increase counter and accumulate error every 10
self.counter += 1;
if (self.counter % 10 == 0):
self.progress.append(loss.item())
pass
# zero gradients, perform a backward pass, update weights
self.optimiser.zero_grad()
loss.backward()
self.optimiser.step()
pass
def plot_progress(self):
df = pandas.DataFrame(self.progress, columns=['loss'])
df.plot(ylim=(0), figsize=(16,8), alpha=0.1, marker='.', grid=True, yticks=(0, 0.25, 0.5, 1.0, 5.0))
pass
pass
# check the generator output is of the right type and shape
G = Generator()
# move model to cuda device
G.to(device)
output = G.forward(generate_random_seed(100))
img = output.detach().permute(0,2,3,1).view(128,128,3).cpu().numpy()
plt.imshow(img, interpolation='none', cmap='Blues')
D = Discriminator()
G = Generator()
D.to(device)
G.to(device)
epochs = 1
for epoch in range(epochs):
print ("epoch = ", epoch + 1)
for image_data_tensor in celeba_dataset:
D.train(image_data_tensor, torch.cuda.FloatTensor([1.0]))
D.train(G.forward(generate_random_seed(100)).detach(), torch.cuda.FloatTensor([0.0]))
G.train(D, generate_random_seed(100), torch.cuda.FloatTensor([1.0]))
# plot several outputs from the trained generator
# plot a 3 column, 2 row array of generated images
f, axarr = plt.subplots(2,3, figsize=(16,8))
for i in range(2):
for j in range(3):
output = G.forward(generate_random_seed(100))
img = output.detach().permute(0,2,3,1).view(128,128,3).cpu().numpy()
axarr[i,j].imshow(img, interpolation='none', cmap='Blues')
pass
pass