diff --git a/src/mednet/libs/classification/scripts/upload.py b/src/mednet/libs/classification/scripts/upload.py
index 7e95426a7496a72ccdeb9a753161f339a42f577a..1224edf62024090e1dca8a731654f3d38212f488 100644
--- a/src/mednet/libs/classification/scripts/upload.py
+++ b/src/mednet/libs/classification/scripts/upload.py
@@ -54,123 +54,26 @@ def upload(
upload_limit_mb: int,
**_, # ignored
) -> None: # numpydoc ignore=PR01
- """Upload results from an experiment folder to GitLab's MLFlow server."""
-
- import json
- import os
- import tempfile
-
- import mlflow
- from mednet.libs.common.utils.checkpointer import (
- get_checkpoint_to_run_inference,
- )
- from mednet.libs.common.utils.gitlab import (
- gitlab_instance_and_token,
- sanitize_filename,
- size_in_mb,
- )
-
- logger.info("Retrieving GitLab credentials for access to hosted MLFlow server...")
- gitlab, token = gitlab_instance_and_token()
- project = gitlab.projects.get(project_path)
- os.environ["MLFLOW_TRACKING_TOKEN"] = token
- os.environ["MLFLOW_TRACKING_URI"] = (
- gitlab.api_url + f"/projects/{project.id}/ml/mlflow"
- )
-
- # get train files
- train_folder = experiment_folder
- train_log_file = train_folder / "trainlog.pdf"
- train_meta_file = train_folder / "train.meta.json"
- train_model_file = get_checkpoint_to_run_inference(train_folder)
- train_files = [train_meta_file, train_model_file, train_log_file]
-
- # get evaluation files
- evaluation_file = experiment_folder / "evaluation.json"
- evaluation_meta_file = experiment_folder / "evaluation.meta.json"
- evaluation_meta_file = experiment_folder / "evaluation.rst"
- evaluation_log_file = experiment_folder / "evaluation.pdf"
- evaluation_files = [
- evaluation_file,
- evaluation_meta_file,
- evaluation_log_file,
+ """Upload results from a classification experiment folder to GitLab's MLFlow server."""
+
+ from mednet.libs.common.scripts.upload import upload as upload_
+
+ metrics = [
+ "threshold",
+ "precision",
+ "recall",
+ "f1_score",
+ "average_precision_score",
+ "specificity",
+ "auc_score",
+ "accuracy",
]
- # checks for maximum upload limit
- total_size_mb = sum([size_in_mb(f) for f in train_files + evaluation_files])
- if upload_limit_mb != 0 and total_size_mb > upload_limit_mb:
- raise RuntimeError(
- f"Total size of upload ({total_size_mb:.2f} MB) exceeds "
- f"permitted maximum ({upload_limit_mb:.2f} MB)."
- )
-
- with train_meta_file.open("r") as meta_file:
- train_data = json.load(meta_file)
-
- with evaluation_file.open("r") as meta_file:
- evaluation_data = json.load(meta_file)
- evaluation_data = evaluation_data["test"]
-
- # get lowest validation epoch
- best_epoch = str(train_model_file).split(".")[0].split("=")[1]
-
- experiment_name = (
- experiment_name or f"{train_data['model-name']}-{train_data['database-name']}"
- )
- run_name = run_name or train_data["datetime"]
-
- click.secho(
- f"Uploading entry `{run_name}` to experiment `{experiment_name}` "
- f"on GitLab project {project_path} (id: {project.id})...",
- bold=True,
- fg="green",
- )
- exp_meta = mlflow.set_experiment(experiment_name=experiment_name)
- with mlflow.start_run(run_name=run_name):
- click.echo("Uploading package metadata...")
- click.echo(f" -> `version` ({train_data['package-version']})")
- mlflow.log_param("package version", train_data["package-version"])
-
- click.echo("Uploading metrics...")
-
- for k in [
- "epochs",
- "batch-size",
- ]:
- click.secho(f" -> `{k}` ({train_data[k]})")
- mlflow.log_param(k, train_data[k])
-
- click.secho(f" -> `#accumulations` ({train_data['accumulate-grad-batches']})")
- mlflow.log_param("#Accumulations", train_data["accumulate-grad-batches"])
- click.secho(f" -> `epoch (best)` ({best_epoch})")
- mlflow.log_param("Epoch (best)", best_epoch)
-
- for k in [
- "threshold",
- "precision",
- "recall",
- "f1_score",
- "average_precision_score",
- "specificity",
- "auc_score",
- "accuracy",
- ]:
- click.secho(f" -> `{k}` ({evaluation_data[k]:.3g})")
- mlflow.log_metric(k, evaluation_data[k])
-
- click.echo("Uploading artifacts (files)...")
-
- with tempfile.TemporaryDirectory() as tmpdir_name:
- tmpdir = pathlib.Path(tmpdir_name)
- for f in train_files + evaluation_files:
- assert f.exists(), f"File `{f}` does not exist - cannot upload!"
- clean_path = str(sanitize_filename(tmpdir, f))
- click.secho(f" -> `{clean_path}` ({size_in_mb(f):.2f} MB)")
- mlflow.log_artifact(clean_path)
-
- click.secho(f"Uploaded {total_size_mb:.2f} MB to server.", bold=True, fg="green")
- click.secho(
- f"Visit {gitlab.url}/{project.path_with_namespace}/-/ml/experiments/{exp_meta.experiment_id}",
- bold=True,
- fg="blue",
+ upload_(
+ project_path,
+ experiment_folder,
+ experiment_name,
+ run_name,
+ metrics,
+ upload_limit_mb,
)
diff --git a/src/mednet/libs/common/scripts/upload.py b/src/mednet/libs/common/scripts/upload.py
index 5302adbc59ac4625413e0831dde20d675b21b45f..3d51efbbbf817de48e648918336e7b7803560748 100644
--- a/src/mednet/libs/common/scripts/upload.py
+++ b/src/mednet/libs/common/scripts/upload.py
@@ -81,3 +81,140 @@ def reusable_options(f):
return f(*args, **kwargs)
return wrapper_reusable_options
+
+
+def upload(
+ project_path: str,
+ experiment_folder: pathlib.Path,
+ experiment_name: str,
+ run_name: str,
+ metrics: list[str],
+ upload_limit_mb: int,
+) -> None:
+ """Upload results from an experiment folder to GitLab's MLFlow server.
+
+ Parameters
+ ----------
+ project_path
+ Path to the project where to upload model entries.
+ experiment_folder
+ Directory in which to upload results from.
+ experiment_name
+ A string indicating the experiment name (e.g. "exp-pasa-mc" or "exp-densenet-mc-ch").
+ run_name
+ A string indicating the run name (e.g. "run-1").
+ metrics
+ List of metrics to upload.
+ upload_limit_mb
+ Maximim upload size in MB (set to 0 for no limit).
+ """
+
+ import json
+ import os
+ import tempfile
+
+ import mlflow
+ from mednet.libs.common.utils.checkpointer import (
+ get_checkpoint_to_run_inference,
+ )
+ from mednet.libs.common.utils.gitlab import (
+ gitlab_instance_and_token,
+ sanitize_filename,
+ size_in_mb,
+ )
+
+ logger.info("Retrieving GitLab credentials for access to hosted MLFlow server...")
+ gitlab, token = gitlab_instance_and_token()
+ project = gitlab.projects.get(project_path)
+ os.environ["MLFLOW_TRACKING_TOKEN"] = token
+ os.environ["MLFLOW_TRACKING_URI"] = (
+ gitlab.api_url + f"/projects/{project.id}/ml/mlflow"
+ )
+
+ # get train files
+ train_folder = experiment_folder
+ train_log_file = train_folder / "trainlog.pdf"
+ train_meta_file = train_folder / "train.meta.json"
+ train_model_file = get_checkpoint_to_run_inference(train_folder)
+ train_files = [train_meta_file, train_model_file, train_log_file]
+
+ # get evaluation files
+ evaluation_file = experiment_folder / "evaluation.json"
+ evaluation_meta_file = experiment_folder / "evaluation.meta.json"
+ evaluation_meta_file = experiment_folder / "evaluation.rst"
+ evaluation_log_file = experiment_folder / "evaluation.pdf"
+ evaluation_files = [
+ evaluation_file,
+ evaluation_meta_file,
+ evaluation_log_file,
+ ]
+
+ # checks for maximum upload limit
+ total_size_mb = sum([size_in_mb(f) for f in train_files + evaluation_files])
+ if upload_limit_mb != 0 and total_size_mb > upload_limit_mb:
+ raise RuntimeError(
+ f"Total size of upload ({total_size_mb:.2f} MB) exceeds "
+ f"permitted maximum ({upload_limit_mb:.2f} MB)."
+ )
+
+ with train_meta_file.open("r") as meta_file:
+ train_data = json.load(meta_file)
+
+ with evaluation_file.open("r") as meta_file:
+ evaluation_data = json.load(meta_file)
+ evaluation_data = evaluation_data["test"]
+
+ # get lowest validation epoch
+ best_epoch = str(train_model_file).split(".")[0].split("=")[1]
+
+ experiment_name = (
+ experiment_name or f"{train_data['model-name']}-{train_data['database-name']}"
+ )
+ run_name = run_name or train_data["datetime"]
+
+ click.secho(
+ f"Uploading entry `{run_name}` to experiment `{experiment_name}` "
+ f"on GitLab project {project_path} (id: {project.id})...",
+ bold=True,
+ fg="green",
+ )
+ exp_meta = mlflow.set_experiment(experiment_name=experiment_name)
+ with mlflow.start_run(run_name=run_name):
+ click.echo("Uploading package metadata...")
+ click.echo(f" -> `version` ({train_data['package-version']})")
+ mlflow.log_param("package version", train_data["package-version"])
+
+ click.echo("Uploading metrics...")
+
+ for k in [
+ "epochs",
+ "batch-size",
+ ]:
+ click.secho(f" -> `{k}` ({train_data[k]})")
+ mlflow.log_param(k, train_data[k])
+
+ click.secho(f" -> `#accumulations` ({train_data['accumulate-grad-batches']})")
+ mlflow.log_param("#Accumulations", train_data["accumulate-grad-batches"])
+ click.secho(f" -> `epoch (best)` ({best_epoch})")
+ mlflow.log_param("Epoch (best)", best_epoch)
+
+ for k in metrics:
+ click.secho(f" -> `{k}` ({evaluation_data[k]:.3g})")
+ mlflow.log_metric(k, evaluation_data[k])
+
+ click.echo("Uploading artifacts (files)...")
+
+ with tempfile.TemporaryDirectory() as tmpdir_name:
+ tmpdir = pathlib.Path(tmpdir_name)
+ for f in train_files + evaluation_files:
+ assert f.exists(), f"File `{f}` does not exist - cannot upload!"
+ clean_path = str(sanitize_filename(tmpdir, f))
+ click.secho(f" -> `{clean_path}` ({size_in_mb(f):.2f} MB)")
+ mlflow.log_artifact(clean_path)
+
+ click.secho(f"Uploaded {total_size_mb:.2f} MB to server.", bold=True, fg="green")
+ click.secho(
+ f"Visit {gitlab.url}/{project.path_with_namespace}/-/ml/experiments/{exp_meta.experiment_id}",
+ bold=True,
+ fg="blue",
+ )
diff --git a/src/mednet/libs/segmentation/scripts/upload.py b/src/mednet/libs/segmentation/scripts/upload.py
index 9abbbd277b37855f0bd8a29960908617d78065e7..bd523442a773d159ea4758a91cee047d6b166351 100644
--- a/src/mednet/libs/segmentation/scripts/upload.py
+++ b/src/mednet/libs/segmentation/scripts/upload.py
@@ -54,122 +54,25 @@ def upload(
upload_limit_mb: int,
**_, # ignored
) -> None: # numpydoc ignore=PR01
- """Upload results from an experiment folder to GitLab's MLFlow server."""
-
- import json
- import os
- import tempfile
-
- import mlflow
- from mednet.libs.common.utils.checkpointer import (
- get_checkpoint_to_run_inference,
- )
- from mednet.libs.common.utils.gitlab import (
- gitlab_instance_and_token,
- sanitize_filename,
- size_in_mb,
- )
-
- logger.info("Retrieving GitLab credentials for access to hosted MLFlow server...")
- gitlab, token = gitlab_instance_and_token()
- project = gitlab.projects.get(project_path)
- os.environ["MLFLOW_TRACKING_TOKEN"] = token
- os.environ["MLFLOW_TRACKING_URI"] = (
- gitlab.api_url + f"/projects/{project.id}/ml/mlflow"
- )
-
- # get train files
- train_folder = experiment_folder
- train_log_file = train_folder / "trainlog.pdf"
- train_meta_file = train_folder / "train.meta.json"
- train_model_file = get_checkpoint_to_run_inference(train_folder)
- train_files = [train_meta_file, train_model_file, train_log_file]
-
- # get evaluation files
- evaluation_file = experiment_folder / "evaluation.json"
- evaluation_meta_file = experiment_folder / "evaluation.meta.json"
- evaluation_meta_file = experiment_folder / "evaluation.rst"
- evaluation_log_file = experiment_folder / "evaluation.pdf"
- evaluation_files = [
- evaluation_file,
- evaluation_meta_file,
- evaluation_log_file,
+ """Upload results from a segmentation experiment folder to GitLab's MLFlow server."""
+
+ from mednet.libs.common.scripts.upload import upload as upload_
+
+ metrics = [
+ "precision",
+ "recall",
+ "f1",
+ "average_precision_score",
+ "specificity",
+ "auc_score",
+ "accuracy",
]
- # checks for maximum upload limit
- total_size_mb = sum([size_in_mb(f) for f in train_files + evaluation_files])
- if upload_limit_mb != 0 and total_size_mb > upload_limit_mb:
- raise RuntimeError(
- f"Total size of upload ({total_size_mb:.2f} MB) exceeds "
- f"permitted maximum ({upload_limit_mb:.2f} MB)."
- )
-
- with train_meta_file.open("r") as meta_file:
- train_data = json.load(meta_file)
-
- with evaluation_file.open("r") as meta_file:
- evaluation_data = json.load(meta_file)
- evaluation_data = evaluation_data["test"]
-
- # get lowest validation epoch
- best_epoch = str(train_model_file).split(".")[0].split("=")[1]
-
- experiment_name = (
- experiment_name or f"{train_data['model-name']}-{train_data['database-name']}"
- )
- run_name = run_name or train_data["datetime"]
-
- click.secho(
- f"Uploading entry `{run_name}` to experiment `{experiment_name}` "
- f"on GitLab project {project_path} (id: {project.id})...",
- bold=True,
- fg="green",
- )
- exp_meta = mlflow.set_experiment(experiment_name=experiment_name)
- with mlflow.start_run(run_name=run_name):
- click.echo("Uploading package metadata...")
- click.echo(f" -> `version` ({train_data['package-version']})")
- mlflow.log_param("package version", train_data["package-version"])
-
- click.echo("Uploading metrics...")
-
- for k in [
- "epochs",
- "batch-size",
- ]:
- click.secho(f" -> `{k}` ({train_data[k]})")
- mlflow.log_param(k, train_data[k])
-
- click.secho(f" -> `#accumulations` ({train_data['accumulate-grad-batches']})")
- mlflow.log_param("#Accumulations", train_data["accumulate-grad-batches"])
- click.secho(f" -> `epoch (best)` ({best_epoch})")
- mlflow.log_param("Epoch (best)", best_epoch)
-
- for k in [
- "precision",
- "recall",
- "f1",
- "average_precision_score",
- "specificity",
- "auc_score",
- "accuracy",
- ]:
- click.secho(f" -> `{k}` ({evaluation_data[k]:.3g})")
- mlflow.log_metric(k, evaluation_data[k])
-
- click.echo("Uploading artifacts (files)...")
-
- with tempfile.TemporaryDirectory() as tmpdir_name:
- tmpdir = pathlib.Path(tmpdir_name)
- for f in train_files + evaluation_files:
- assert f.exists(), f"File `{f}` does not exist - cannot upload!"
- clean_path = str(sanitize_filename(tmpdir, f))
- click.secho(f" -> `{clean_path}` ({size_in_mb(f):.2f} MB)")
- mlflow.log_artifact(clean_path)
-
- click.secho(f"Uploaded {total_size_mb:.2f} MB to server.", bold=True, fg="green")
- click.secho(
- f"Visit {gitlab.url}/{project.path_with_namespace}/-/ml/experiments/{exp_meta.experiment_id}",
- bold=True,
- fg="blue",
+ upload_(
+ project_path,
+ experiment_folder,
+ experiment_name,
+ run_name,
+ metrics,
+ upload_limit_mb,
)