projects
/
pytorch.git
/ commitdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
| commitdiff |
tree
raw
|
patch
|
inline
| side by side (parent:
a810bbe
)
Tried to make the source clearer, added the TimeAppender Module.
author
Francois Fleuret
<francois@fleuret.org>
Mon, 15 Aug 2022 07:27:47 +0000
(09:27 +0200)
committer
Francois Fleuret
<francois@fleuret.org>
Mon, 15 Aug 2022 07:27:47 +0000
(09:27 +0200)
minidiffusion.py
patch
|
blob
|
history
diff --git
a/minidiffusion.py
b/minidiffusion.py
index
65ca947
..
27842d9
100755
(executable)
--- a/
minidiffusion.py
+++ b/
minidiffusion.py
@@
-146,6
+146,20
@@
class EMA:
######################################################################
######################################################################
+# 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__()
class ConvNet(nn.Module):
def __init__(self, in_channels, out_channels):
super().__init__()
@@
-153,7
+167,8
@@
class ConvNet(nn.Module):
ks, nc = 5, 64
self.core = nn.Sequential(
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.ReLU(),
nn.Conv2d(nc, nc, ks, padding = ks//2),
nn.ReLU(),
@@
-166,8
+181,8
@@
class ConvNet(nn.Module):
nn.Conv2d(nc, out_channels, ks, padding = ks//2),
)
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
######################################################################
# Data
@@
-187,6
+202,7
@@
if train_input.dim() == 2:
nh = 256
model = nn.Sequential(
nh = 256
model = nn.Sequential(
+ TimeAppender(),
nn.Linear(train_input.size(1) + 1, nh),
nn.ReLU(),
nn.Linear(nh, nh),
nn.Linear(train_input.size(1) + 1, nh),
nn.ReLU(),
nn.Linear(nh, nh),
@@
-198,7
+214,7
@@
if train_input.dim() == 2:
elif train_input.dim() == 4:
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)
model.to(device)
@@
-214,10
+230,10
@@
def generate(size, alpha, alpha_bar, sigma, model, train_mean, train_std):
x = torch.randn(size, device = device)
for t in range(T-1, -1, -1):
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)
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/torch.sqrt(alpha[t]) \
- * (x - (1-alpha[t]) / torch.sqrt(1-alpha_bar[t]) *
model(input)
) \
+ * (x - (1-alpha[t]) / torch.sqrt(1-alpha_bar[t]) *
output
) \
+ sigma[t] * z
x = x * train_std + train_mean
+ sigma[t] * z
x = x * train_std + train_mean
@@
-245,8
+261,8
@@
for k in range(args.nb_epochs):
t = torch.randint(T, (x0.size(0),) + (1,) * (x0.dim() - 1), device = x0.device)
eps = torch.randn_like(x0)
xt = torch.sqrt(alpha_bar[t]) * x0 + torch.sqrt(1 - alpha_bar[t]) * eps
t = torch.randint(T, (x0.size(0),) + (1,) * (x0.dim() - 1), device = x0.device)
eps = torch.randn_like(x0)
xt = torch.sqrt(alpha_bar[t]) * x0 + torch.sqrt(1 - alpha_bar[t]) * eps
-
input = torch.cat((xt, t.expand_as(x0[:,:1]) / (T - 1) - 0.5), 1
)
- loss = (eps -
model(input)
).pow(2).mean()
+
output = model((xt, t / (T - 1) - 0.5)
)
+ loss = (eps -
output
).pow(2).mean()
acc_loss += loss.item() * x0.size(0)
optimizer.zero_grad()
acc_loss += loss.item() * x0.size(0)
optimizer.zero_grad()
@@
-327,6
+343,9
@@
elif train_input.dim() == 4:
x = generate((128,) + train_input.size()[1:], alpha, alpha_bar, sigma,
model, train_mean, train_std)
x = 1 - x.clamp(min = 0, max = 255) / 255
x = generate((128,) + train_input.size()[1:], alpha, alpha_bar, sigma,
model, train_mean, train_std)
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)
+
+ filename = f'diffusion_{args.data}.png'
+ print(f'saving {filename}')
+ torchvision.utils.save_image(x, filename, nrow = 16, pad_value = 0.8)
######################################################################
######################################################################