Performance Regression or Improvement: pytorch_image_classification_benchmarks-resnet152-GPU-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-GPU-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 with Tesla T4 GPU.
Test link -

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

Line 151 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?from=now-90d&to=now&viewPanel=2

timestamp: Thu Sep 26 06:51:07 2024, metric_value: 131960.30
timestamp: Wed Sep 25 16:35:03 2024, metric_value: 158301.74
timestamp: Tue Sep 24 21:42:34 2024, metric_value: 118881.83 <---- Anomaly
timestamp: Mon Sep 16 06:54:38 2024, metric_value: 1110384.48
timestamp: Sun Sep 15 06:56:40 2024, metric_value: 1002364.55
timestamp: Sat Sep 14 07:11:25 2024, metric_value: 1369933.57
timestamp: Fri Sep 13 07:09:59 2024, metric_value: 1051181.39
timestamp: Thu Sep 12 07:16:52 2024, metric_value: 1080097.25
timestamp: Wed Sep 11 07:12:24 2024, metric_value: 1089064.12
timestamp: Tue Sep 10 07:03:54 2024, metric_value: 1265593.49
timestamp: Mon Sep  9 07:05:04 2024, metric_value: 954089.81
timestamp: Sun Sep  8 07:07:16 2024, metric_value: 1131592.92
timestamp: Sat Sep  7 07:01:36 2024, metric_value: 1046570.98