Fashion-MNIST 2c2d

class deepobs.fmnist.fmnist_2c2d.set_up(batch_size, weight_decay=None)

Class providing the functionality for a vanilla CNN architecture on Fashion-MNIST adapted from the TensorFlow tutorial for MNIST.

It consists of two convolutional layers with ReLU activations, each followed by max-pooling, followed by one fully-connected layer with ReLU activations and a 10-unit output layer with softmax. The model uses cross-entroy loss and no regularization. The weight matrices are initialized with truncated normal (stddev= 0.05) and the biases are initialized to 0.05.

Parameters:

• batch_size (int) -- Batch size of the data points. Defaults to 128.
• weight_decay (float) -- Weight decay factor. In this model there is no weight decay implemented. Defaults to None.

data_loading

Data loading class for Fashion-MNIST, fmnist_input.data_loading.

Type:deepobs.data_loading

losses

Tensor of size batch_size containing the individual losses per data point.

Type:tf.Tensor

accuracy

Tensor containing the accuracy of the model.

Type:tf.Tensor

train_init_op

A TensorFlow operation to be performed before starting every training epoch.

Type:tf.Operation

train_eval_init_op

A TensorFlow operation to be performed before starting every training eval epoch.

Type:tf.Operation

test_init_op

A TensorFlow operation to be performed before starting every test evaluation phase.

Type:tf.Operation

bias_variable(name, shape, init_val)

Creates a bias variable of given shape and initialized to a given value.

Parameters:

• name (str) -- Name of the bias variable.
• shape (list) -- Dimensionality of the bias variable.
• init_val (float) -- Initial value of the bias variable.

Returns:

Bias variable.

Return type:

tf.Variable

conv2d(x, W, stride=1, padding='SAME')

Creates a two dimensional convolutional layer on top of a given input.

Parameters:

• x (tf.Variable) -- Input to the layer.
• W (tf.Variable) -- Weight variable of the convolutional layer.
• stride (int) -- Stride of the convolution. Defaults to 1.
• padding (str) -- Padding of the convolutional layers. Can be SAME or VALID. Defaults to SAME.

Returns:

Output after the convolutional layer.

Return type:

tf.Variable

get()

Returns the losses and the accuray of the model.

Returns:Tupel consisting of the losses and the accuracy. Return type:tupel

max_pool_2x2(x)

Creates a 2 by 2 max pool layer on top of a given input.

Parameters:x (tf.Variable) -- Input to the layer. Returns:Output after the max pool layer. Return type:tf.Variable

set_up(weight_decay=None)

Sets up the test problem.

Parameters:weight_decay (float) -- Weight decay factor. In this model there is no weight decay implemented. Defaults to None. Returns:Tupel consisting of the losses and the accuracy. Return type:tupel