github-actions[bot] commented on issue #36624:
URL: https://github.com/apache/beam/issues/36624#issuecomment-3478417901
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](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=7
```
timestamp: Sun Nov 2 06:56:10 2025, metric_value: 79818.31
timestamp: Sat Nov 1 07:06:58 2025, metric_value: 79146.39
timestamp: Fri Oct 31 07:05:19 2025, metric_value: 79737.41
timestamp: Thu Oct 30 07:20:17 2025, metric_value: 85212.44
timestamp: Wed Oct 29 07:04:27 2025, metric_value: 80071.65
timestamp: Tue Oct 28 07:27:19 2025, metric_value: 80317.07 <---- Anomaly
timestamp: Mon Oct 27 07:07:06 2025, metric_value: 94501.86
timestamp: Sun Oct 26 07:02:25 2025, metric_value: 94895.39
timestamp: Sat Oct 25 07:05:44 2025, metric_value: 78584.49
timestamp: Fri Oct 24 18:25:11 2025, metric_value: 92706.41
timestamp: Fri Oct 24 10:49:31 2025, metric_value: 93639.36
timestamp: Thu Oct 23 23:51:02 2025, metric_value: 85854.42
timestamp: Wed Oct 8 22:15:12 2025, metric_value: 83701.28
timestamp: Sat Sep 13 06:57:47 2025, metric_value: 91354.80
timestamp: Fri Sep 12 06:56:48 2025, metric_value: 87093.69
timestamp: Thu Sep 11 07:10:14 2025, metric_value: 84028.75
```
--
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]
