SequentialTransform

class torchaug.transforms.SequentialTransform(transforms, transforms_attributes_override={'inplace': True, 'batch_inplace': True, 'batch_transform': True, 'num_chunks': -1, 'permute_chunks': False})

Sequentially apply a list of transforms.

Note

By default this SequentialTransform makes all its transforms to be inplace, batch_inplace, and batch_transform with unlimited chunks.

Parameters:

• transforms (List[RandomApplyTransform]) – A list of transforms.

• transforms_attributes_override (Optional[Dict[str, Any]], optional) – A dictionary of parameters to override the default parameters of the transforms if they exist. Useful to make transforms for batches. Default: {'inplace': True, 'batch_inplace': True, 'batch_transform': True, 'num_chunks': -1, 'permute_chunks': False}

extra_repr()

Set the extra representation of the transform.

Return type:

str

forward(*inputs)

Performs forward pass of the transform.

Parameters:

inputs (Any) – Inputs to the transform.

Return type:

Any

Returns:

Transformed inputs.