Running out of memory

Part 1 (2019)
7

You may check out this documentaion

Here below some information about learn.purge() extracted from this discussion

  1. learn.purge() removes any of the Learner guts that are no longer needed and reloads the model on GPU, which also helps to reduce memory fragmentation

  2. Run learn.purge() before any big change in your model training (image size, unfreeze, etc.).