SVHN Wide Resnet¶
-
class
deepobs.pytorch.testproblems.svhn_wrn164.
svhn_wrn164
(batch_size, l2_reg=0.0005)[source]¶ DeepOBS test problem class for the Wide Residual Network 16-4 architecture for SVHN.
Details about the architecture can be found in the original paper. L2-Regularization is used on the weights (but not the biases) which defaults to
5e-4
.Training settings recommended in the original paper:
batch size = 128
,num_epochs = 160
using the Momentum optimizer with \(\mu = 0.9\) and an initial learning rate of0.01
with a decrease by0.1
after80
and120
epochs.Parameters: - batch_size (int) -- Batch size to use.
- l2_reg (float) -- L2-regularization factor. L2-Regularization (weight decay)
is used on the weights but not the biases.
Defaults to
5e-4
.