docs: Update README.md for autogram
#410
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Codecov Report✅ All modified and coverable lines are covered by tests. 🚀 New features to boost your workflow:
|
ValerianRey
force-pushed
the
autogram-readme
branch
from
8019470 to
d392656
Compare
Comment on lines
+125
to
+156
| ```diff | ||
| import torch | ||
| from torch.nn import Linear, MSELoss, ReLU, Sequential | ||
| from torch.optim import SGD | ||
|
|
||
| + from torchjd.autogram import Engine | ||
| + from torchjd.aggregation import UPGradWeighting | ||
|
|
||
| model = Sequential(Linear(10, 5), ReLU(), Linear(5, 3), ReLU(), Linear(3, 1), ReLU()) | ||
|
|
||
| - loss_fn = MSELoss() | ||
| + loss_fn = MSELoss(reduction="none") | ||
| optimizer = SGD(model.parameters(), lr=0.1) | ||
|
|
||
| + weighting = UPGradWeighting() | ||
| + engine = Engine(model.modules()) | ||
|
|
||
| inputs = torch.randn(8, 16, 10) # 8 batches of 16 random input vectors of length 10 | ||
| targets = torch.randn(8, 16) # 8 batches of 16 targets for the first task | ||
|
|
||
| for input, target in zip(inputs, targets): | ||
| output = model(input).squeeze(dim=1) # shape [16] | ||
| - loss = loss_fn(output, target) # shape [1] | ||
| + losses = loss_fn(output, target) # shape [16] | ||
|
|
||
| optimizer.zero_grad() | ||
| - loss.backward() | ||
| + gramian = engine.compute_gramian(losses) # shape: [16, 16] | ||
| + weights = weighting(gramian) # shape: [16] | ||
| + losses.backward(weights) | ||
| optimizer.step() | ||
| ``` |
There was a problem hiding this comment.
Will this be the most important example after #411 ?
There was a problem hiding this comment.
A bit early to say. Depends on what we want people to do with our library. It may be good to start with this example and to have a more complex one after. To have like:
- MTL with autojac
- IWRM with autogram
- MTL + IWRM with autogram
I think it's always much easier to have the simpler things come first and complexify after, even if what we want people to do is the complex stuff.
This is just the state of the README as it was in #387 btw, nothing new in this PR.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This should be merged when we're ready to release autogram.