You are viewing a plain text version of this content. The canonical link for it is here.
Posted to github@beam.apache.org by "github-actions[bot] (via GitHub)" <gi...@apache.org> on 2023/08/19 22:08:59 UTC
[GitHub] [beam] github-actions[bot] opened a new issue, #28067: Performance Regression or Improvement: pytorch_image_classification_benchmarks-resnet101-mean_inference_batch_latency_micro_secs:mean_inference_batch_latency_micro_secs
github-actions[bot] opened a new issue, #28067:
URL: https://github.com/apache/beam/issues/28067
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: Sat Aug 19 18:18:09 2023, metric_value: 4442828.55
timestamp: Fri Aug 18 18:18:58 2023, metric_value: 4518560.76
timestamp: Thu Aug 17 18:18:38 2023, metric_value: 4518552.26
timestamp: Wed Aug 16 18:18:41 2023, metric_value: 4572899.04
timestamp: Tue Aug 15 18:20:19 2023, metric_value: 4434901.51
timestamp: Mon Aug 14 18:19:03 2023, metric_value: 4499253.64
timestamp: Sun Aug 13 18:18:21 2023, metric_value: 4579284.80
timestamp: Sat Aug 12 18:18:01 2023, metric_value: 4540231.68
timestamp: Fri Aug 11 18:22:50 2023, metric_value: 4562882.83 <---- Anomaly
timestamp: Thu Aug 10 18:31:22 2023, metric_value: 4706314.64
timestamp: Wed Aug 9 18:20:39 2023, metric_value: 4499391.44
timestamp: Tue Aug 8 19:33:41 2023, metric_value: 4648045.91
timestamp: Mon Aug 7 18:21:00 2023, metric_value: 4527919.92
timestamp: Sun Aug 6 18:18:21 2023, metric_value: 4593467.59
timestamp: Sat Aug 5 18:18:37 2023, metric_value: 4640704.50
timestamp: Fri Aug 4 18:18:47 2023, metric_value: 4701437.57
timestamp: Thu Aug 3 18:30:50 2023, metric_value: 4478775.48
timestamp: Wed Aug 2 18:22:25 2023, metric_value: 4627538.10
timestamp: Wed Aug 2 13:43:54 2023, metric_value: 4730867.34
```
--
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: github-unsubscribe@beam.apache.org.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [beam] AnandInguva closed issue #28067: Performance Regression or Improvement: pytorch_image_classification_benchmarks-resnet101-mean_inference_batch_latency_micro_secs:mean_inference_batch_latency_micro_secs
Posted by "AnandInguva (via GitHub)" <gi...@apache.org>.
AnandInguva closed issue #28067:
Performance Regression or Improvement: pytorch_image_classification_benchmarks-resnet101-mean_inference_batch_latency_micro_secs:mean_inference_batch_latency_micro_secs
URL: https://github.com/apache/beam/issues/28067
--
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: github-unsubscribe@beam.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [beam] AnandInguva commented on issue #28067: Performance Regression or Improvement: pytorch_image_classification_benchmarks-resnet101-mean_inference_batch_latency_micro_secs:mean_inference_batch_latency_micro_secs
Posted by "AnandInguva (via GitHub)" <gi...@apache.org>.
AnandInguva commented on issue #28067:
URL: https://github.com/apache/beam/issues/28067#issuecomment-1686190445
Closing this as noise.
--
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: github-unsubscribe@beam.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org