SVHN WideResNet 16-4

class deepobs.tensorflow.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 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.
dataset

The DeepOBS data set class for SVHN.

train_init_op

A tensorflow operation initializing the test problem for the training phase.

train_eval_init_op

A tensorflow operation initializing the test problem for evaluating on training data.

test_init_op

A tensorflow operation initializing the test problem for evaluating on test data.

losses

A tf.Tensor of shape (batch_size, ) containing the per-example loss values.

regularizer

A scalar tf.Tensor containing a regularization term.

accuracy

A scalar tf.Tensor containing the mini-batch mean accuracy.

set_up()[source]

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