Skip to content

fix evaluate_vqgan.py attempting to load nonexistent args #50

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
arthurdrake1 merged 1 commit into from
Oct 27, 2025
Merged

fix evaluate_vqgan.py attempting to load nonexistent args #50

Show file tree
Hide file tree
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
4 changes: 3 additions & 1 deletion engiopt/vqgan/evaluate_vqgan.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -84,8 +84,10 @@ def __init__(self):
super().__init__("Failed to retrieve the run")

run = artifact_transformer.logged_by()
if run is None or not hasattr(run, "config"):
if run is None:
raise RunRetrievalError
run = api.run(f"{run.entity}/{run.project}/{run.id}")

artifact_dir_cvqgan = artifact_cvqgan.download()
artifact_dir_vqgan = artifact_vqgan.download()
artifact_dir_transformer = artifact_transformer.download()
Expand Down
4 changes: 3 additions & 1 deletion engiopt/vqgan/vqgan.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -680,8 +680,8 @@ def log_images(self, x: th.Tensor, c: th.Tensor, top_k: int | None = None) -> tu
# Now we assume the dataset is of shape (N, C, H, W) and work from there
image_channels = training_ds["optimal_upsampled"][:].shape[1]
latent_size = args.image_size // (2 ** (len(args.encoder_channels) - 2))
conditions = problem.conditions_keys

conditions = problem.conditions_keys
# Optionally drop condition columns that are constant like overhang_constraint in beams2d
if args.drop_constant_conditions:
training_ds, conditions = drop_constant(training_ds, conditions)
Expand Down Expand Up @@ -787,6 +787,8 @@ def log_images(self, x: th.Tensor, c: th.Tensor, top_k: int | None = None) -> tu
wandb.define_metric("epoch_transformer", step_metric="transformer_step")
if args.early_stopping:
wandb.define_metric("transformer_val_loss", step_metric="transformer_step")
wandb.config["image_channels"] = image_channels
wandb.config["latent_size"] = latent_size

vqgan = VQGAN(
device=device,
Expand Down
Loading