Performance Regression or Improvement: pytorch_image_classification_benchmarks-resnet152-mean_inference_batch_latency_micro_secs:mean_inference_batch_latency_micro_secs

[github-actions]

Performance change found in the
test: pytorch_image_classification_benchmarks-resnet152-mean_inference_batch_latency_micro_secs for the metric: mean_inference_batch_latency_micro_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 152.
Test link -

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

Line 63 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=2

timestamp: Sun Apr 13 05:31:08 2025, metric_value: 7349034.09
timestamp: Sat Apr 12 05:01:10 2025, metric_value: 7369311.04
timestamp: Fri Apr 11 05:08:29 2025, metric_value: 7732282.09 <---- Anomaly
timestamp: Thu Apr 10 05:06:27 2025, metric_value: 6853519.86
timestamp: Wed Apr  9 05:06:46 2025, metric_value: 6716715.90
timestamp: Tue Apr  8 04:59:52 2025, metric_value: 6814646.31
timestamp: Mon Apr  7 11:09:25 2025, metric_value: 6615117.47
timestamp: Mon Apr  7 05:02:44 2025, metric_value: 6695634.66
timestamp: Sun Apr  6 05:11:13 2025, metric_value: 6769270.19
timestamp: Sat Apr  5 05:03:52 2025, metric_value: 6862590.61
timestamp: Fri Apr  4 05:14:12 2025, metric_value: 6813321.14
timestamp: Thu Apr  3 05:07:55 2025, metric_value: 6777022.85
timestamp: Wed Apr  2 05:08:12 2025, metric_value: 6816992.18