Colombo c7ab9653c5 new optimized training: ...

for every batch_size*16 samples,
model collects the samples with the highest error and learns them again
therefore hard samples will be trained more often

2020-02-27 11:19:53 +04:00

..

__init__.py

removed SAEv2,

2019-10-08 15:09:28 +04:00

Model.py

new optimized training:

2020-02-27 11:19:53 +04:00