* weight compat break, activate norm3 for final block of final stage (equivalent to pre-head norm, but while still in BLC shape) * remove fold/unfold for TPU compat, add commented out roll code for TPU * add option for end of stage norm in all stages * allow weight_init to be selected between pytorch default inits and xavier / moco style vit variant |
||
---|---|---|
.. | ||
data | ||
loss | ||
models | ||
optim | ||
scheduler | ||
utils | ||
__init__.py | ||
version.py |