import torch, torchvision
from torch import nn
+from torch.nn import functional as F
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+print(f'device {device}')
+
######################################################################
def sample_gaussian_mixture(nb):
parser.add_argument('--ema_decay',
type = float, default = 0.9999,
- help = 'EMA decay, < 0 is no EMA')
+ help = 'EMA decay, <= 0 is no EMA')
data_list = ', '.join( [ str(k) for k in samplers ])
type = str, default = 'gaussian_mixture',
help = f'Toy data-set to use: {data_list}')
+parser.add_argument('--no_window',
+ action='store_true', default = False)
+
args = parser.parse_args()
if args.seed >= 0:
def __init__(self, model, decay):
self.model = model
self.decay = decay
- if self.decay < 0: return
- self.ema = { }
+ self.mem = { }
with torch.no_grad():
for p in model.parameters():
- self.ema[p] = p.clone()
+ self.mem[p] = p.clone()
def step(self):
- if self.decay < 0: return
with torch.no_grad():
for p in self.model.parameters():
- self.ema[p].copy_(self.decay * self.ema[p] + (1 - self.decay) * p)
+ self.mem[p].copy_(self.decay * self.mem[p] + (1 - self.decay) * p)
- def copy(self):
- if self.decay < 0: return
+ def copy_to_model(self):
with torch.no_grad():
for p in self.model.parameters():
- p.copy_(self.ema[p])
+ p.copy_(self.mem[p])
######################################################################
+# Gets a pair (x, t) and appends t (scalar or 1d tensor) to x as an
+# additional dimension / channel
+
+class TimeAppender(nn.Module):
+ def __init__(self):
+ super().__init__()
+
+ def forward(self, u):
+ x, t = u
+ if not torch.is_tensor(t):
+ t = x.new_full((x.size(0),), t)
+ t = t.view((-1,) + (1,) * (x.dim() - 1)).expand_as(x[:,:1])
+ return torch.cat((x, t), 1)
+
class ConvNet(nn.Module):
def __init__(self, in_channels, out_channels):
super().__init__()
ks, nc = 5, 64
self.core = nn.Sequential(
- nn.Conv2d(in_channels, nc, ks, padding = ks//2),
+ TimeAppender(),
+ nn.Conv2d(in_channels + 1, nc, ks, padding = ks//2),
nn.ReLU(),
nn.Conv2d(nc, nc, ks, padding = ks//2),
nn.ReLU(),
nn.Conv2d(nc, out_channels, ks, padding = ks//2),
)
- def forward(self, x):
- return self.core(x)
+ def forward(self, u):
+ return self.core(u)
######################################################################
# Data
nh = 256
model = nn.Sequential(
+ TimeAppender(),
nn.Linear(train_input.size(1) + 1, nh),
nn.ReLU(),
nn.Linear(nh, nh),
elif train_input.dim() == 4:
- model = ConvNet(train_input.size(1) + 1, train_input.size(1))
+ model = ConvNet(train_input.size(1), train_input.size(1))
model.to(device)
print(f'nb_parameters {sum([ p.numel() for p in model.parameters() ])}')
+######################################################################
+# Generate
+
+def generate(size, T, alpha, alpha_bar, sigma, model, train_mean, train_std):
+
+ with torch.no_grad():
+
+ x = torch.randn(size, device = device)
+
+ for t in range(T-1, -1, -1):
+ output = model((x, t / (T - 1) - 0.5))
+ z = torch.zeros_like(x) if t == 0 else torch.randn_like(x)
+ x = 1/torch.sqrt(alpha[t]) \
+ * (x - (1-alpha[t]) / torch.sqrt(1-alpha_bar[t]) * output) \
+ + sigma[t] * z
+
+ x = x * train_std + train_mean
+
+ return x
+
######################################################################
# Train
alpha_bar = alpha.log().cumsum(0).exp()
sigma = beta.sqrt()
-ema = EMA(model, decay = args.ema_decay)
+ema = EMA(model, decay = args.ema_decay) if args.ema_decay > 0 else None
for k in range(args.nb_epochs):
x0 = (x0 - train_mean) / train_std
t = torch.randint(T, (x0.size(0),) + (1,) * (x0.dim() - 1), device = x0.device)
eps = torch.randn_like(x0)
- input = torch.sqrt(alpha_bar[t]) * x0 + torch.sqrt(1 - alpha_bar[t]) * eps
- input = torch.cat((input, t.expand_as(x0[:,:1]) / (T - 1) - 0.5), 1)
- loss = (eps - model(input)).pow(2).mean()
+ xt = torch.sqrt(alpha_bar[t]) * x0 + torch.sqrt(1 - alpha_bar[t]) * eps
+ output = model((xt, t / (T - 1) - 0.5))
+ loss = (eps - output).pow(2).mean()
acc_loss += loss.item() * x0.size(0)
optimizer.zero_grad()
loss.backward()
optimizer.step()
- ema.step()
+ if ema is not None: ema.step()
print(f'{k} {acc_loss / train_input.size(0)}')
-ema.copy()
+if ema is not None: ema.copy_to_model()
######################################################################
-# Generate
+# Plot
-def generate(size, model):
- with torch.no_grad():
- x = torch.randn(size, device = device)
+model.eval()
- for t in range(T-1, -1, -1):
- z = torch.zeros_like(x) if t == 0 else torch.randn_like(x)
- input = torch.cat((x, torch.full_like(x[:,:1], t / (T - 1) - 0.5)), 1)
- x = 1/torch.sqrt(alpha[t]) \
- * (x - (1-alpha[t]) / torch.sqrt(1-alpha_bar[t]) * model(input)) \
- + sigma[t] * z
+########################################
+# Nx1 -> histogram
+if train_input.dim() == 2 and train_input.size(1) == 1:
- x = x * train_std + train_mean
+ fig = plt.figure()
+ fig.set_figheight(5)
+ fig.set_figwidth(8)
- return x
+ ax = fig.add_subplot(1, 1, 1)
-######################################################################
-# Plot
+ x = generate((10000, 1), T, alpha, alpha_bar, sigma,
+ model, train_mean, train_std)
-model.eval()
+ ax.set_xlim(-1.25, 1.25)
+ ax.spines.right.set_visible(False)
+ ax.spines.top.set_visible(False)
-if train_input.dim() == 2:
- fig = plt.figure()
- ax = fig.add_subplot(1, 1, 1)
+ d = train_input.flatten().detach().to('cpu').numpy()
+ ax.hist(d, 25, (-1, 1),
+ density = True,
+ histtype = 'bar', edgecolor = 'white', color = 'lightblue', label = 'Train')
- if train_input.size(1) == 1:
+ d = x.flatten().detach().to('cpu').numpy()
+ ax.hist(d, 25, (-1, 1),
+ density = True,
+ histtype = 'step', color = 'red', label = 'Synthesis')
- x = generate((10000, 1), model)
+ ax.legend(frameon = False, loc = 2)
- ax.set_xlim(-1.25, 1.25)
+ filename = f'minidiffusion_{args.data}.pdf'
+ print(f'saving {filename}')
+ fig.savefig(filename, bbox_inches='tight')
- d = train_input.flatten().detach().to('cpu').numpy()
- ax.hist(d, 25, (-1, 1),
- density = True,
- histtype = 'stepfilled', color = 'lightblue', label = 'Train')
+ if not args.no_window and hasattr(plt.get_current_fig_manager(), 'window'):
+ plt.get_current_fig_manager().window.setGeometry(2, 2, 1024, 768)
+ plt.show()
- d = x.flatten().detach().to('cpu').numpy()
- ax.hist(d, 25, (-1, 1),
- density = True,
- histtype = 'step', color = 'red', label = 'Synthesis')
+########################################
+# Nx2 -> scatter plot
+elif train_input.dim() == 2 and train_input.size(1) == 2:
- ax.legend(frameon = False, loc = 2)
+ fig = plt.figure()
+ fig.set_figheight(6)
+ fig.set_figwidth(6)
- elif train_input.size(1) == 2:
+ ax = fig.add_subplot(1, 1, 1)
- x = generate((1000, 2), model)
+ x = generate((1000, 2), T, alpha, alpha_bar, sigma,
+ model, train_mean, train_std)
- ax.set_xlim(-1.5, 1.5)
- ax.set_ylim(-1.5, 1.5)
- ax.set(aspect = 1)
- ax.spines.right.set_visible(False)
- ax.spines.top.set_visible(False)
+ ax.set_xlim(-1.5, 1.5)
+ ax.set_ylim(-1.5, 1.5)
+ ax.set(aspect = 1)
+ ax.spines.right.set_visible(False)
+ ax.spines.top.set_visible(False)
- d = x.detach().to('cpu').numpy()
- ax.scatter(d[:, 0], d[:, 1],
- facecolors = 'none', color = 'red', label = 'Synthesis')
+ d = train_input[:x.size(0)].detach().to('cpu').numpy()
+ ax.scatter(d[:, 0], d[:, 1],
+ s = 2.5, color = 'gray', label = 'Train')
- d = train_input[:x.size(0)].detach().to('cpu').numpy()
- ax.scatter(d[:, 0], d[:, 1],
- s = 1.0, color = 'blue', label = 'Train')
+ d = x.detach().to('cpu').numpy()
+ ax.scatter(d[:, 0], d[:, 1],
+ s = 2.0, color = 'red', label = 'Synthesis')
- ax.legend(frameon = False, loc = 2)
+ ax.legend(frameon = False, loc = 2)
- filename = f'diffusion_{args.data}.pdf'
+ filename = f'minidiffusion_{args.data}.pdf'
print(f'saving {filename}')
fig.savefig(filename, bbox_inches='tight')
- if hasattr(plt.get_current_fig_manager(), 'window'):
+ if not args.no_window and hasattr(plt.get_current_fig_manager(), 'window'):
plt.get_current_fig_manager().window.setGeometry(2, 2, 1024, 768)
plt.show()
+########################################
+# NxCxHxW -> image
elif train_input.dim() == 4:
- x = generate((128,) + train_input.size()[1:], model)
- x = 1 - x.clamp(min = 0, max = 255) / 255
- torchvision.utils.save_image(x, f'diffusion_{args.data}.png', nrow = 16, pad_value = 0.8)
+
+ x = generate((128,) + train_input.size()[1:], T, alpha, alpha_bar, sigma,
+ model, train_mean, train_std)
+
+ x = torchvision.utils.make_grid(x.clamp(min = 0, max = 255),
+ nrow = 16, padding = 1, pad_value = 64)
+ x = F.pad(x, pad = (2, 2, 2, 2), value = 64)[None]
+
+ t = torchvision.utils.make_grid(train_input[:128],
+ nrow = 16, padding = 1, pad_value = 64)
+ t = F.pad(t, pad = (2, 2, 2, 2), value = 64)[None]
+
+ result = 1 - torch.cat((t, x), 2) / 255
+
+ filename = f'minidiffusion_{args.data}.png'
+ print(f'saving {filename}')
+ torchvision.utils.save_image(result, filename)
+
+else:
+
+ print(f'cannot plot result of size {train_input.size()}')
######################################################################