github-actions[bot] opened a new issue, #35378:
URL: https://github.com/apache/beam/issues/35378
Performance change found in the
test:
`pytorch_image_classification_benchmarks-resnet101-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](https://github.com/apache/beam/tree/master/sdks/python/apache_beam/testing/analyzers/README.md#triage-performance-alert-issues).
`Test description:` Pytorch image classification on 50k images of size 224 x
224 with resnet 101.
Test link -
https://github.com/apache/beam/blob/42d0a6e3564d8b9c5d912428a6de18fb22a13ac1/.test-infra/jenkins/job_InferenceBenchmarkTests_Python.groovy#L34
Test dashboard -
http://metrics.beam.apache.org/d/ZpS8Uf44z/python-ml-runinference-benchmarks?orgId=1&viewPanel=2
```
timestamp: Thu Jun 19 06:15:40 2025, metric_value: 4773938.62
timestamp: Wed Jun 18 06:17:40 2025, metric_value: 5375200.95
timestamp: Tue Jun 17 06:17:48 2025, metric_value: 5338547.00 <---- Anomaly
timestamp: Mon Jun 16 06:03:35 2025, metric_value: 4573118.42
timestamp: Sun Jun 15 06:10:02 2025, metric_value: 4715557.67
timestamp: Sat Jun 14 06:02:23 2025, metric_value: 4672265.98
timestamp: Fri Jun 13 06:06:52 2025, metric_value: 5218091.32
timestamp: Thu Jun 12 06:02:26 2025, metric_value: 4675070.64
timestamp: Wed Jun 11 06:00:34 2025, metric_value: 4656410.18
timestamp: Tue Jun 10 06:05:07 2025, metric_value: 4495554.92
timestamp: Mon Jun 9 05:54:14 2025, metric_value: 4592477.63
timestamp: Sun Jun 8 05:52:00 2025, metric_value: 4519200.97
timestamp: Sat Jun 7 05:52:27 2025, metric_value: 4629124.06
```
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
