Skip to content

Fix: update DimeNet pretrained checkpoint loading for compatibility with Tensorflow v2.X #10547

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

Open
nhadler wants to merge 2 commits into
base: master
Choose a base branch
from
Open

Fix: update DimeNet pretrained checkpoint loading for compatibility with Tensorflow v2.X #10547

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
8831694
Update TensorFlow checkpoint loading for compatibility with tensorflo…
nhadler Dec 5, 2025
39afb5d
Update CHANGELOG for DimeNet fix
nhadler Dec 5, 2025
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
2 changes: 2 additions & 0 deletions CHANGELOG.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,8 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).

### Fixed

- Fixed DimeNet pretrained checkpoint loading for compatibility with Tensorflow v2.X

### Security

## [2.7.0] - 2025-10-14
Expand Down
4 changes: 2 additions & 2 deletions torch_geometric/nn/models/dimenet.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -593,7 +593,7 @@ def from_qm9_pretrained(
download_url(f'{url}/ckpt.index', path)

path = osp.join(path, 'ckpt')
reader = tf.train.load_checkpoint(path)
reader = tf.compat.v1.train.load_checkpoint(path)

model = cls(
hidden_channels=128,
Expand Down Expand Up @@ -865,7 +865,7 @@ def from_qm9_pretrained(
download_url(f'{url}/ckpt.index', path)

path = osp.join(path, 'ckpt')
reader = tf.train.load_checkpoint(path)
reader = tf.compat.v1.train.load_checkpoint(path)

# Configuration from DimeNet++:
# https://github.com/gasteigerjo/dimenet/blob/master/config_pp.yaml
Expand Down
Loading