AnandInguva opened a new issue, #25880:
URL: https://github.com/apache/beam/issues/25880
Performance change found in the
test: `Pytorch image classification on 50k images of size 224 x 224 with
resnet 152 with Tesla T4 GPU` 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).
timestamp: Wed Mar 15 18:39:24 2023, metric_value: `110663.89090909091`
timestamp: Tue Mar 14 18:20:28 2023, metric_value: `106096.67857142857`
timestamp: Mon Mar 13 18:52:40 2023, metric_value: `124759.4`
timestamp: Sun Mar 12 18:17:56 2023, metric_value: `134102.17857142858`
timestamp: Sat Mar 11 18:19:42 2023, metric_value: `136957.125`
timestamp: Fri Mar 10 18:21:33 2023, metric_value: `152183.0892857143`
timestamp: Thu Mar 9 18:26:05 2023, metric_value: `156150.64285714287`
timestamp: Wed Mar 8 18:25:08 2023, metric_value: `147711.76785714287`
timestamp: Tue Mar 7 18:23:57 2023, metric_value: `146152.57142857142`
timestamp: Tue Mar 7 01:20:20 2023, metric_value: `152064.64285714287`
timestamp: Mon Mar 6 18:24:23 2023, metric_value: `140394.9655172414` <----
Anomaly
timestamp: Sun Mar 5 18:22:04 2023, metric_value: `136059.73214285713`
timestamp: Sat Mar 4 18:18:43 2023, metric_value: `135242.625`
--
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-unsubscr...@beam.apache.org.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
