Skip to content

feat(zero_order): implemented the zero order feature #93

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.

Sign up for GitHub

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

Merged
merged 14 commits into from
Oct 11, 2022
Merged

feat(zero_order): implemented the zero order feature #93

Changes from 1 commit
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
48ddc30
fix(implicit): fix bug if input is nn.Parameter
JieRen98 Sep 16, 2022
ce60054
fix(adam): fix inplace bug
JieRen98 Sep 20, 2022
80516f9
feat(implicit): add cg solver wrapper
JieRen98 Sep 21, 2022
f54bfe5
feat(zero_order): init
JieRen98 Sep 25, 2022
6ec17e3
sync: resolve conflicts
Benjamin-eecs Oct 7, 2022
fbbcff5
Merge branch 'main' into zero_order
Benjamin-eecs Oct 9, 2022
1e23c50
fix: pass lint
Benjamin-eecs Oct 9, 2022
930f68b
fix: pass lint
Benjamin-eecs Oct 9, 2022
d0d6255
fix: pass lint
Benjamin-eecs Oct 9, 2022
606ff56
feat(zero_grad): add switch function
JieRen98 Oct 10, 2022
768c591
style(zero_grad): format
JieRen98 Oct 10, 2022
54e2dd2
fix(zero_grad): fix bug
JieRen98 Oct 10, 2022
87f1f59
chore: cleanup
XuehaiPan Oct 11, 2022
a470a67
chore: cleanup
XuehaiPan Oct 11, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
fix(zero_grad): fix bug
  • Loading branch information
@JieRen98
JieRen98 committed Oct 10, 2022
commit 54e2dd29c47d31be45e1b6501e690bb668f762c1
4 changes: 2 additions & 2 deletions torchopt/zero_grad_diff.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -277,8 +277,8 @@ def get_loss(transform_fn):

return fn(*args)

loss = get_loss(lambda tensor, noise: torch.add(noise, alpha=sigma)) - get_loss(
lambda tensor, noise: torch.sub(noise, alpha=sigma)
loss = get_loss(lambda tensor, noise: tensor.add(noise, alpha=sigma)) - get_loss(
lambda tensor, noise: tensor.sub(noise, alpha=sigma)
)
weighted_grad = grad_outputs[0].mul(loss).mul_(0.5 / sigma)

Expand Down
pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy