robustness.tools.helpers module¶
-
robustness.tools.helpers.
has_attr
(obj, k)¶ Checks both that obj.k exists and is not equal to None
-
robustness.tools.helpers.
calc_est_grad
(func, x, y, rad, num_samples)¶
-
robustness.tools.helpers.
ckpt_at_epoch
(num)¶
-
robustness.tools.helpers.
accuracy
(output, target, topk=(1, ), exact=False)¶ Computes the top-k accuracy for the specified values of k
Parameters: - output (ch.tensor) – model output (N, classes) or (N, attributes) for sigmoid/multitask binary classification
- target (ch.tensor) – correct labels (N,) [multiclass] or (N, attributes) [multitask binary]
- topk (tuple) – for each item “k” in this tuple, this method will return the top-k accuracy
- exact (bool) – whether to return aggregate statistics (if False) or per-example correctness (if True)
Returns: A list of top-k accuracies.
-
class
robustness.tools.helpers.
InputNormalize
(new_mean, new_std)¶ Bases:
sphinx.ext.autodoc.importer._MockObject
A module (custom layer) for normalizing the input to have a fixed mean and standard deviation (user-specified).
-
forward
(x)¶
-
-
class
robustness.tools.helpers.
AverageMeter
¶ Bases:
object
Computes and stores the average and current value
-
reset
()¶
-
update
(val, n=1)¶
-
-
robustness.tools.helpers.
get_label_mapping
(dataset_name, ranges)¶
-
robustness.tools.helpers.
restricted_label_mapping
(classes, class_to_idx, ranges)¶
-
robustness.tools.helpers.
custom_label_mapping
(classes, class_to_idx, ranges)¶