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: Sat Jun 27 09:08:21 2026, metric_value: 7035506.74
timestamp: Fri Jun 26 09:34:34 2026, metric_value: 7561454.70
timestamp: Thu Jun 25 23:17:23 2026, metric_value: 7513922.60 <---- Anomaly
timestamp: Thu Jun 25 09:20:41 2026, metric_value: 6729006.35
timestamp: Wed Jun 24 08:56:33 2026, metric_value: 6807110.91
timestamp: Tue Jun 23 09:08:21 2026, metric_value: 7001589.26
timestamp: Sun Jun 14 09:08:18 2026, metric_value: 6726891.67
timestamp: Sat Jun 13 09:05:59 2026, metric_value: 6673693.48
timestamp: Fri Jun 12 09:50:17 2026, metric_value: 6923317.53
timestamp: Thu Jun 11 08:53:35 2026, metric_value: 6831659.06
timestamp: Wed Jun 10 09:11:21 2026, metric_value: 6850856.07
timestamp: Tue Jun  9 08:46:09 2026, metric_value: 7139572.59
timestamp: Wed Jun  3 17:17:13 2026, metric_value: 6929294.35