MCPcopy Create free account
hub / github.com/CausalLearning/MultiRobustness / AugmentedDataset

Class AugmentedDataset

cifar10_input.py:150–177  ·  view source on GitHub ↗

Dataset object with built-in data augmentation. When performing adversarial attacks, we cannot include data augmentation as part of the model. If we do the adversary will try to backprop through it.

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

__init__Method · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected