DeepOBS test problem class for multinomial logistic regression on Fasion-MNIST.
No regularization is used and the weights and biases are initialized to
- batch_size (int) -- Batch size to use.
- weight_decay (float) -- No weight decay (L2-regularization) is used in this
test problem. Defaults to
Noneand any input here is ignored.
The DeepOBS data set class for Fashion-MNIST.
A tensorflow operation initializing the test problem for the training phase.
A tensorflow operation initializing the test problem for evaluating on training data.
A tensorflow operation initializing the test problem for evaluating on test data.
A tf.Tensor of shape (batch_size, ) containing the per-example loss values.
A scalar tf.Tensor containing a regularization term. Will always be
0.0since no regularizer is used.
A scalar tf.Tensor containing the mini-batch mean accuracy.
Set up the logistic regression test problem on Fashion-MNIST.