search

nathanin / micron2

0 stars 0 forks source link

Add learning rate decay to MoCo training funtion #1

Closed nathanin closed 3 years ago

nathanin commented 3 years ago

https://github.com/tensorflow/tensorflow/issues/37862

nathanin commented 3 years ago

This has to be done in the notebook/script using the main MoCo class:

https://github.com/nathanin/micron2/blob/1cd935450581fba555ca4e27cceeadac0cef1d46/micron2/clustering/model_moco.py#L91-L93