SVHN 3c3d

class deepobs.tensorflow.testproblems.svhn_3c3d.svhn_3c3d(batch_size, weight_decay=0.002)[source]

DeepOBS test problem class for a three convolutional and three dense layered neural network on SVHN.

The network consists of

  • thre conv layers with ReLUs, each followed by max-pooling
  • two fully-connected layers with 512 and 256 units and ReLU activation
  • 10-unit output layer with softmax
  • cross-entropy loss
  • L2 regularization on the weights (but not the biases) with a default factor of 0.002

The weight matrices are initialized using Xavier initialization and the biases are initialized to 0.0.

Parameters:
  • batch_size (int) -- Batch size to use.
  • weight_decay (float) -- Weight decay factor. Weight decay (L2-regularization) is used on the weights but not the biases. Defaults to 0.002.
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 vanilla CNN test problem on SVHN.