2D Branin¶
-
class
deepobs.tensorflow.testproblems.two_d_branin.
two_d_branin
(batch_size, weight_decay=None)[source]¶ DeepOBS test problem class for a stochastic version of thetwo-dimensional Branin function as the loss function.
Using the deterministic Branin function and adding stochastic noise of the form
\(u \cdot x + v \cdot y\)
where
x
andy
are normally distributed with mean0.0
and standard deviation1.0
we get a loss function of the form\((v - 5.1/(4 \cdot \pi^2) u^2 + 5/ \pi u - 6)^2 +\ 10 \cdot (1-1/(8 \cdot \pi)) \cdot \cos(u) + 10 + u \cdot x + v \cdot y\).
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 the two_d stochastic test problem.
-
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.