Skip to content

Fix ICEBERG forward prediction on pip-install / CPU / pytorch_lightning 2.x #35

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
hugogontijomachado wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix ICEBERG forward prediction on pip-install / CPU / pytorch_lightning 2.x #35

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
5 changes: 4 additions & 1 deletion src/ms_pred/dag_pred/iceberg_elucidation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -273,7 +273,10 @@ def iceberg_prediction(
df.to_csv(save_dir / f'cands_df_{exp_name}.tsv', sep='\t', index=False)

# run iceberg to generate in-silico spectrum
cmd = (f'''{python_path} src/ms_pred/dag_pred/predict_smis.py \\
# Resolve predict_smis.py relative to this package, not the current working
# directory, so it also works when ms_pred is pip-installed (no src/ checkout).
predict_script = Path(__file__).resolve().parent / "predict_smis.py"
cmd = (f'''{python_path} {predict_script} \\
--batch-size {batch_size} \\
--num-workers {num_workers} \\
--dataset-labels {save_dir / f"cands_df_{exp_name}.tsv"} \\
Expand Down
5 changes: 3 additions & 2 deletions src/ms_pred/dag_pred/predict_smis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -78,7 +78,7 @@ def predict():
save_dir = Path(kwargs["save_dir"])
debug = kwargs["debug"]
common.setup_logger(save_dir, log_name="joint_pred.log", debug=debug)
pl.utilities.seed.seed_everything(kwargs.get("seed"))
pl.seed_everything(kwargs.get("seed"))

# Dump args
yaml_args = yaml.dump(kwargs)
Expand Down Expand Up @@ -195,7 +195,8 @@ def producer_func(batch):
else:
device = "cpu"
model.to(device)
torch.cuda.set_device(gpu_id) # avoids error in pe_embedding under multithreading.
if gpu and avail_gpu_num > 0:
torch.cuda.set_device(gpu_id) # avoids error in pe_embedding under multithreading

# for batch in batched_entries:
smis, spec_names, colli_eng_vals, adducts, instruments, precursor_mzs, h5_names = list(zip(*batch))
Expand Down