lasagne.random
¶
A module with a package-wide random number generator,
used for weight initialization and seeding noise layers.
This can be replaced by a numpy.random.RandomState
instance with a
particular seed to facilitate reproducibility.
Note: When using cuDNN, the backward passes of convolutional and max-pooling
layers will introduce additional nondeterminism (for performance reasons).
For 2D convolutions, you can enforce a deterministic backward pass
implementation via the Theano flags dnn.conv.algo_bwd_filter=deterministic
and dnn.conv.algo_bwd_data=deterministic
. Alternatively, you can disable
cuDNN completely with dnn.enabled=False
.