COMPLETE: Whisker Book Planned Downtime for ML Backend Upgrade


There will be some very limited downtime for machine learning (ML) requests tomorrow afternoon (4PM Pacific on May 27th, 2021) on Whisker Book (

The backend Wildbook IA (WBIA) system that supports all detection, classification, and ID job requests will be migrated to a larger and more powerful virtual machine in the cloud. This new virtual machine supports GPU offloading for accelerating common ML tasks, which is an upgrade from the CPU-only compute up until this point. The entire WBIA database and its complementary caches (130 GB) have already been fully transferred, but we anticipate approximately 30 minutes of additional reconfiguration and final verification to fully transfer the service and restart the main public site. All systems may experience restarts during this process. If you are unable to visit the site or execute ML jobs, please try again momentarily.

This will constitute a major upgrade in ML response times – to reflect the growth (and anticipated growth) of the project – and is done with no additional service cost.

Time offline: 05/27/2021 at 16:00 Pacific
Time complete: 05/27/2021 at 16:35 Pacific


Jason Parham
Senior Computer Vision Research Engineer
Wild Me

CC @evebohnett