Skip to content
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

Improving the GATv2 example. #6035

Merged
merged 5 commits into from
Jul 27, 2023
Merged

Improving the GATv2 example. #6035

merged 5 commits into from
Jul 27, 2023

Conversation

drivanov
Copy link
Contributor

Description

In the current PR we eliminate the following warnings:

/usr/local/lib/python3.10/dist-packages/dgl/data/utils.py:354: UserWarning: Property dataset.num_labels will be deprecated, please use dataset.num_classes instead.

/usr/local/lib/python3.10/dist-packages/numpy/core/fromnumeric.py:3474: RuntimeWarning: Mean of empty slice.
  return _methods._mean(a, axis=axis, dtype=dtype,

/usr/local/lib/python3.10/dist-packages/numpy/core/_methods.py:189: RuntimeWarning: invalid value encountered in double_scalars
  ret = ret.dtype.type(ret / rcount)

and few nan outputs:

Epoch 00000 | Time(s) nan | Loss 1.9473 | TrainAcc 0.1143 | ValAcc 0.1900 | ETputs(KTEPS) nan
Epoch 00001 | Time(s) nan | Loss 1.9422 | TrainAcc 0.1643 | ValAcc 0.2840 | ETputs(KTEPS) nan
Epoch 00002 | Time(s) nan | Loss 1.9434 | TrainAcc 0.2000 | ValAcc 0.4260 | ETputs(KTEPS) nan

Current PR is quite similar to #5999,

The average duration of the epoch calculations, which was previously done with np.mean(dur), is now done recursively.

Checklist

Please feel free to remove inapplicable items for your PR.

  • I've leverage the tools to beautify the python and c++ code.
  • The PR is complete and small, read the Google eng practice (CL equals to PR) to understand more about small PR. In DGL, we consider PRs with less than 200 lines of core code change are small (example, test and documentation could be exempted).
  • All changes have test coverage
  • Code is well-documented
  • To the best of my knowledge, examples are either not affected by this change, or have been fixed to be compatible with this change

Changes

@dgl-bot
Copy link
Collaborator

dgl-bot commented Jul 24, 2023

Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:

  • @dgl-bot

@dgl-bot
Copy link
Collaborator

dgl-bot commented Jul 24, 2023

Commit ID: 0c0cd3b

Build ID: 1

Status: ❌ CI test failed in Stage [Authentication].

Report path: link

Full logs path: link

@frozenbugs
Copy link
Collaborator

@dgl-bot

@dgl-bot
Copy link
Collaborator

dgl-bot commented Jul 27, 2023

Not authorized to trigger CI. Please ask core developer to help trigger via issuing comment:

  • @dgl-bot

@dgl-bot
Copy link
Collaborator

dgl-bot commented Jul 27, 2023

Commit ID: a089eb4

Build ID: 3

Status: ❌ CI test failed in Stage [Authentication].

Report path: link

Full logs path: link

@dgl-bot
Copy link
Collaborator

dgl-bot commented Jul 27, 2023

Commit ID: a089eb4

Build ID: 2

Status: ❌ CI test failed in Stage [CPU Build].

Report path: link

Full logs path: link

@frozenbugs frozenbugs merged commit 1f93101 into dmlc:master Jul 27, 2023
1 check passed
@frozenbugs
Copy link
Collaborator

Lint passed, the example is not covered by CI, so merge without waiting for CI complete.

@frozenbugs
Copy link
Collaborator

@drivanov Thank you for contributing in improving the code quality!

Rhett-Ying pushed a commit that referenced this pull request Aug 10, 2023
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
DominikaJedynak pushed a commit to DominikaJedynak/dgl that referenced this pull request Mar 12, 2024
Co-authored-by: Hongzhi (Steve), Chen <chenhongzhi.nkcs@gmail.com>
This pull request was closed.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants