# MNIST 2c2d¶

class deepobs.tensorflow.testproblems.mnist_2c2d.mnist_2c2d(batch_size, weight_decay=None)[source]

DeepOBS test problem class for a two convolutional and two dense layered neural network on MNIST.

The network has been adapted from the TensorFlow tutorial and consists of

• two conv layers with ReLUs, each followed by max-pooling
• one fully-connected layers with ReLUs
• 10-unit output layer with softmax
• cross-entropy loss
• No regularization

The weight matrices are initialized with truncated normal (standard deviation of 0.05) and the biases are initialized to 0.05.

Parameters: batch_size (int) -- Batch size to use. weight_decay (float) -- No weight decay (L2-regularization) is used in this test problem. Defaults to None and any input here is ignored.
dataset

The DeepOBS data set class for MNIST.

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. Will always be 0.0 since no regularizer is used.

accuracy

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

set_up()[source]

Sets up the vanilla CNN test problem on MNIST.