projects
/
pytorch.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
Update.
[pytorch.git]
/
minidiffusion.py
diff --git
a/minidiffusion.py
b/minidiffusion.py
index
e1f6abd
..
65ca947
100755
(executable)
--- a/
minidiffusion.py
+++ b/
minidiffusion.py
@@
-207,8
+207,10
@@
print(f'nb_parameters {sum([ p.numel() for p in model.parameters() ])}')
######################################################################
# Generate
######################################################################
# Generate
-def generate(size, alpha, alpha_bar, sigma, model):
+def generate(size, alpha, alpha_bar, sigma, model, train_mean, train_std):
+
with torch.no_grad():
with torch.no_grad():
+
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):
@@
-267,9
+269,11
@@
if train_input.dim() == 2:
fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)
fig = plt.figure()
ax = fig.add_subplot(1, 1, 1)
+ # Nx1 -> histogram
if train_input.size(1) == 1:
if train_input.size(1) == 1:
- x = generate((10000, 1), alpha, alpha_bar, sigma, model)
+ x = generate((10000, 1), alpha, alpha_bar, sigma,
+ model, train_mean, train_std)
ax.set_xlim(-1.25, 1.25)
ax.spines.right.set_visible(False)
ax.set_xlim(-1.25, 1.25)
ax.spines.right.set_visible(False)
@@
-287,9
+291,11
@@
if train_input.dim() == 2:
ax.legend(frameon = False, loc = 2)
ax.legend(frameon = False, loc = 2)
+ # Nx2 -> scatter plot
elif train_input.size(1) == 2:
elif train_input.size(1) == 2:
- x = generate((1000, 2), alpha, alpha_bar, sigma, model)
+ x = generate((1000, 2), 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_xlim(-1.5, 1.5)
ax.set_ylim(-1.5, 1.5)
@@
-315,9
+321,11
@@
if train_input.dim() == 2:
plt.get_current_fig_manager().window.setGeometry(2, 2, 1024, 768)
plt.show()
plt.get_current_fig_manager().window.setGeometry(2, 2, 1024, 768)
plt.show()
+# NxCxHxW -> image
elif train_input.dim() == 4:
elif train_input.dim() == 4:
- x = generate((128,) + train_input.size()[1:], alpha, alpha_bar, sigma, model)
+ 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)
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)