lydyc
Results
3
comments of
lydyc
@geroge-gao yes,you can refer to https://github.com/axon-research/c3d-keras
@joaoluiscarreira if minibatch size is 6 for each gpu, it seems to be too small for training batch norm layer because batch norm is useful only when batch size is...
@joaoluiscarreira thanks for your help.