github-actions[bot] opened a new issue, #35158:
URL: https://github.com/apache/beam/issues/35158
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: Wed Jun 4 05:56:07 2025, metric_value: 4543039.80
timestamp: Tue Jun 3 05:52:22 2025, metric_value: 4584034.63
timestamp: Mon Jun 2 06:09:28 2025, metric_value: 4570347.21
timestamp: Sun Jun 1 06:07:56 2025, metric_value: 4626779.34
timestamp: Sat May 31 06:17:39 2025, metric_value: 4353596.06 <---- Anomaly
timestamp: Fri May 30 06:10:14 2025, metric_value: 5406102.39
timestamp: Thu May 29 06:05:30 2025, metric_value: 5275811.68
timestamp: Wed May 28 06:23:57 2025, metric_value: 5161158.81
timestamp: Tue May 27 06:01:56 2025, metric_value: 4683810.84
timestamp: Mon May 26 06:01:28 2025, metric_value: 4942145.06
timestamp: Sun May 25 06:24:45 2025, metric_value: 4823168.05
timestamp: Sat May 24 05:59:20 2025, metric_value: 4740554.80
timestamp: Fri May 23 05:57:44 2025, metric_value: 4823484.64
timestamp: Thu May 22 06:02:23 2025, metric_value: 4790359.38
timestamp: Wed May 21 06:01:13 2025, metric_value: 4824620.89
```
--
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]
