Performance Regression or Improvement: pytorch_image_classification_benchmarks-resnet101-mean_load_model_latency_milli_secs:mean_load_model_latency_milli_secs

[github-actions]

Performance change found in the
test: pytorch_image_classification_benchmarks-resnet101-mean_load_model_latency_milli_secs for the metric: mean_load_model_latency_milli_secs.

For more information on how to triage the alerts, please look at
Triage performance alert issues section of the README.

Test description: Pytorch image classification on 50k images of size 224 x 224 with resnet 101.
Test link -

beam/.test-infra/jenkins/job_InferenceBenchmarkTests_Python.groovy

Line 34 in 42d0a6e

test : 'apache_beam.testing.benchmarks.inference.pytorch_image_classification_benchmarks',

Test dashboard - http://metrics.beam.apache.org/d/ZpS8Uf44z/python-ml-runinference-benchmarks?orgId=1&viewPanel=7

timestamp: Sun Nov 23 07:08:10 2025, metric_value: 76594.22
timestamp: Sat Nov 22 06:59:33 2025, metric_value: 76963.93
timestamp: Fri Nov 21 07:04:58 2025, metric_value: 77347.39
timestamp: Thu Nov 20 06:58:55 2025, metric_value: 76755.67
timestamp: Tue Nov 18 07:26:22 2025, metric_value: 78306.94
timestamp: Mon Nov 17 07:09:37 2025, metric_value: 77856.51
timestamp: Sun Nov 16 07:04:04 2025, metric_value: 76486.47
timestamp: Sat Nov 15 07:00:49 2025, metric_value: 78236.31
timestamp: Fri Nov 14 07:25:59 2025, metric_value: 77515.71
timestamp: Thu Nov 13 07:09:23 2025, metric_value: 77857.21 <---- Anomaly
timestamp: Wed Nov 12 07:02:40 2025, metric_value: 79965.49
timestamp: Tue Nov 11 17:25:40 2025, metric_value: 81531.55
timestamp: Mon Nov 10 07:10:12 2025, metric_value: 77955.43
timestamp: Sun Nov  9 07:02:49 2025, metric_value: 79051.45
timestamp: Sat Nov  8 08:19:50 2025, metric_value: 80985.69
timestamp: Fri Nov  7 07:01:58 2025, metric_value: 80079.85
timestamp: Thu Nov  6 07:02:37 2025, metric_value: 84554.85
timestamp: Wed Nov  5 07:15:38 2025, metric_value: 80506.53
timestamp: Tue Nov  4 07:17:09 2025, metric_value: 80485.48
timestamp: Mon Nov  3 07:05:09 2025, metric_value: 81903.54