Closed pandapool closed 5 months ago
This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.
This issue has been automatically closed because it has not had recent activity. Please comment "/reopen" to reopen it.
Environment
1.8.1
KFP SDK version:
1.8.19
Steps to reproduce
Create a function to check logging of scalars: def foo(runid) ->NamedTuple("EvaluationOutput", [('mlpipeline_ui_metadata', 'UI_metadata')]):
import subprocess subprocess.run(["pip","install","tensorboardX==2.5"]) from tensorboardX import SummaryWriter from minio import Minio
log_dir = " /tensorboard_logs/" writer = SummaryWriter(log_dir)
for i in range(20):
Log loss to TensorBoard
writer.flush()
from pipelines.utils.minio_utils import upload_local_directory_to_minio
upload_local_directory_to_minio(client, bucket_name, " /tensorboard_logs/","foo_logs")
metadata = { 'outputs': [{ 'type': 'tensorboard', 'source': f'http://:/minio/datasets/foo_logs',
}]
}
out_tuple = namedtuple("EvaluationOutput", ["mlpipeline_ui_metadata"]) return out_tuple(json.dumps(metadata))
Expected result
Tensorboard should show a graph for the scalars written to events file. The issue is not with the events file as it works for a locally deployed tensorboard server.
Materials and reference
Labels
Impacted by this bug? Give it a 👍.