# Mixup¶

class mmcls.models.utils.batch_augments.Mixup(alpha)[source]

Mixup batch augmentation.

Mixup is a method to reduces the memorization of corrupt labels and increases the robustness to adversarial examples. It’s proposed in mixup: Beyond Empirical Risk Minimization

Parameters

alpha (float) – Parameters for Beta distribution to generate the mixing ratio. It should be a positive number. More details are in the note.

Note

The $$\alpha$$ (alpha) determines a random distribution $$Beta(\alpha, \alpha)$$. For each batch of data, we sample a mixing ratio (marked as $$\lambda$$, lam) from the random distribution.

mix(batch_inputs, batch_scores)[source]

Mix the batch inputs and batch one-hot format ground truth.

Parameters
• batch_inputs (Tensor) – A batch of images tensor in the shape of (N, C, H, W).

• batch_scores (Tensor) – A batch of one-hot format labels in the shape of (N, num_classes).

Returns

The mixed inputs and labels.

Return type

Tuple[Tensor, Tensor)