Skip to content

Latest commit

 

History

History
11 lines (6 loc) · 435 Bytes

logging.md

File metadata and controls

11 lines (6 loc) · 435 Bytes

Loggings

Tensorboard logging

Thanks to Fabric and wrappers, a Tensorboard is instantiates on the server side to check on the training, using all metrics sent by the clients.

The tensorboard is available (on the server side) by running:

Rich Logging

Pybiscus use the Rich Console to print beautifully some informations on both server and client sides during training, in addition to the already existant logging by Flower.