MNIST LogReg¶

class deepobs.mnist.mnist_logreg.set_up(batch_size, weight_decay=None)[source]¶

Class providing the functionality for multinomial logistic regression on MNIST.

The model uses no regularization. All weights and biasses are initialized to be 0.

Parameters:	batch_size (int) -- Batch size of the data points. No default value specified. weight_decay (float) -- Weight decay factor. In this model there is no weight decay implemented. Defaults to `None`.

data_loading¶

Data loading class for MNIST, mnist_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

Returns the losses and the accuray of the model.

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

set_up(weight_decay)[source]¶

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