SVHN Wide Resnet

class deepobs.pytorch.testproblems.svhn_wrn164.svhn_wrn164(batch_size, l2_reg=0.0005)

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 of 0.01 with a decrease by 0.1 after 80 and 120 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.

get_regularization_groups()

Creates regularization groups for the parameters.

Returns:A dictionary where the key is the regularization factor and the value is a list of parameters. Return type:dict

set_up()

Set up the Wide ResNet 16-4 test problem on SVHN.