Evaluator Memory

[bhack]

The append approach is going to require a lot of memory:

aot-benchmark/networks/managers/evaluator.py

Line 402 in 04fe7d9

all_preds.append(pred_prob)

Also bypassing this and materialising each prediction in the else branch for each step the PAOT branch it is really consuming a lot of memory.
Any hint on why it has a so large overhead if we compare with the main branch also when limiting the max long term mem?