-
Notifications
You must be signed in to change notification settings - Fork 250
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Update stochastic sampler #673
base: main
Are you sure you want to change the base?
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Small changes requested.
input, | ||
img_shape_y, | ||
img_shape_x, | ||
patch_shape_y, | ||
patch_shape_x, | ||
batch_size, | ||
overlap_pix, | ||
boundary_pix, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can we add the type hints back?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes for sure. Sorry for delay in response, the notification went to my personal email
input.shape[0], input.shape[1], padded_shape_x, padded_shape_y | ||
).cuda() | ||
input.shape[0], input.shape[1], padded_shape_y, padded_shape_x | ||
).to(input.device) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can we initialize on the device instead?
input, | ||
img_shape_y, | ||
img_shape_x, | ||
patch_shape_y, | ||
patch_shape_x, | ||
batch_size, | ||
overlap_pix, | ||
boundary_pix, | ||
input_interp=None, |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Add back type hints
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good to me
net, | ||
latents, | ||
img_lr, | ||
class_labels=None, | ||
randn_like=torch.randn_like, | ||
img_shape=448, | ||
patch_shape=448, | ||
overlap_pix=4, | ||
boundary_pix=2, | ||
mean_hr=None, | ||
num_steps=18, | ||
sigma_min=0.002, | ||
sigma_max=800, | ||
rho=7, | ||
S_churn=0, | ||
S_min=0, | ||
S_max=float("inf"), | ||
S_noise=1, | ||
): |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Type hints
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
looks good to me
# sigma_max = min(sigma_max, net.sigma_max) | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
uncomment?
Modulus Pull Request
Description
Update stochastic sampler
Checklist
Dependencies