forked from mrq/DL-Art-School
036684893e
- Added LARS and SGD optimizer variants that support turning off certain features for BN and bias layers - Added a variant of pytorch's resnet model that supports gradient checkpointing. - Modify the trainer infrastructure to support above - Fix bug with BYOL (should have been nonfunctional) |
||
---|---|---|
.. | ||
larc.py | ||
sgd.py |