DeepOBS test problem class for a stochastic version of thetwo-dimensional Rosenbrock function as the loss function.
Using the deterministic Rosenbrock function and adding stochastic noise of the form
\(u \cdot x + v \cdot y\)
yare normally distributed with mean
0.0and standard deviation
1.0we get a loss function of the form
\((1 - u)^2 + 100 \cdot (v - u^2)^2 + u \cdot x + v \cdot y\)
- 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 the two_d stochastic test problem.
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.
Sets up the stochastic two-dimensional Rosenbrock test problem. Using
1.5as a starting point for the weights