Skip to content

Internal change #172

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
copybara-service wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Internal change #172

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
14 changes: 14 additions & 0 deletions recml/core/utils/keras_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,13 +74,15 @@ def __init__(
checkpoint_dir: str,
max_to_keep: int = 5,
save_interval_epochs: int = 1,
choose_store_cell: bool = True,
):
"""Initializes a KerasOrbaxCheckpointManager.

Args:
checkpoint_dir: The directory to save checkpoints to.
max_to_keep: The maximum number of checkpoints to keep.
save_interval_epochs: The interval (in epochs) to save checkpoints.
choose_store_cell: Whether to dynamically select the CNS2 store cell.
"""
if keras.backend.backend() != "jax":
raise ValueError(
Expand All @@ -92,6 +94,11 @@ def __init__(
options=ocp.CheckpointManagerOptions(
save_interval_steps=save_interval_epochs,
max_to_keep=max_to_keep,
file_options=ocp.options.FileOptions(
cns2_storage_options=ocp.options.Cns2StorageOptions(
choose_store_cell=choose_store_cell,
),
),
),
)

Expand Down Expand Up @@ -430,20 +437,27 @@ def __init__(
checkpoint_dir: str,
max_to_keep: int = 5,
save_interval_epochs: int = 1,
choose_store_cell: bool = True,
):
"""Initializes a KerasOrbaxCheckpointManager.

Args:
checkpoint_dir: The directory to save checkpoints to.
max_to_keep: The maximum number of checkpoints to keep.
save_interval_epochs: The interval (in epochs) to save checkpoints.
choose_store_cell: Whether to dynamically select the CNS2 store cell.
"""
super().__init__(
directory=checkpoint_dir,
checkpointers=ocp.AsyncCheckpointer(ocp.PyTreeCheckpointHandler()),
options=ocp.CheckpointManagerOptions(
save_interval_steps=save_interval_epochs,
max_to_keep=max_to_keep,
file_options=ocp.options.FileOptions(
cns2_storage_options=ocp.options.Cns2StorageOptions(
choose_store_cell=choose_store_cell,
),
),
),
)

Expand Down
Loading