Transforms

Eztorch supports transforms from Torchaug and from Torchvision.

On top of that, several video transforms have been defined.

Video transforms

Apply key

class eztorch.transforms.ApplyTransformToKey(key, transform)[source]

Applies transform to key of dictionary input.

Parameters:
  • key (str) – The dictionary key the transform is applied to.

  • transform (Module) – The transform that is applied.

class eztorch.transforms.ApplyTransformToKeyOnList(key, transform)[source]

Applies transform to key of dictionary input where input is a list :type key: str :param key: the dictionary key the transform is applied to. :type transform: Module :param transform: the transform that is applied.

Example::
>>>  transforms.ApplyTransformToKeyOnList(
>>>       key='input',
>>>       transform=UniformTemporalSubsample(num_video_samples),
>>>   )
class eztorch.transforms.ApplySameTransformInputKeyOnList(transform, dim=1)[source]

Apply same transform to the input list key.

Parameters:
  • transform (Module) – The transform to apply.

  • dim (int, optional) – The dimension to retrieve the various elements of the list.

    Default: 1

class eztorch.transforms.ApplySameTransformToKeyOnList(key, transform, dim=1)[source]

Applies the same transform to key of dictionary input where input is a list.

Parameters:
  • key (str) – the dictionary key the transform is applied to.

  • transform (Module) – the transform that is applied.

  • dim (int, optional) – The dimension to retrieve the various elements of the list.

    Default: 1

class eztorch.transforms.ApplyTransformAudioKey(transform)[source]

Apply Transform to the audio key.

Parameters:

transform (Module) – The transform to apply.

class eztorch.transforms.ApplyTransformAudioKeyOnList(transform)[source]

Apply Transform to the audio key.

Parameters:

transform (Module) – The transform to apply.

class eztorch.transforms.ApplyTransformInputKey(transform)[source]

Apply Transform to the input key.

Parameters:

transform (Module) – The transform to apply.

class eztorch.transforms.ApplyTransformInputKeyOnList(transform)[source]

Apply Transform to the input key.

Parameters:

transform (Module) – The transform to apply.

class eztorch.transforms.ApplyTransformOnDict(transform)[source]

Apply Transform to the audio key.

Parameters:

transform (Module) – The transform to apply.

Apply transform on list

class eztorch.transforms.ApplyTransformOnList(transform, list_len=2)[source]

Apply transform to a list of input.

Parameters:
  • transform (Module) – A transform for the list of input.

  • list_len (int, optional) – len of the input.

    Default: 2

class eztorch.transforms.ApplyTransformsOnList(transforms)[source]

Apply transform to a list of input.

Parameters:
  • transform – A transform for the list of input.

  • list_len – len of the input.

Dict keep keys

class eztorch.transforms.DictKeepKeys(keys)[source]

Keep specified keys in dict.

References

Parameters:

keys (List[str]) – The list of keys to keep.

class eztorch.transforms.DictKeepInputLabel[source]

Transform dict to list containing values of only 'input' and 'label'.

class eztorch.transforms.DictKeepInputLabelIdx[source]

Transform dict to list containing values of only 'input', 'label', 'index' and 'aug_index'.

Div 255

class eztorch.transforms.Div255Input(inplace=True, dtype=torch.float32)[source]

Perform Division by 255 on a tensor or list of tensor.

Multi-crop

class eztorch.transforms.MultiCropTransform(set_transforms)[source]

Define multi crop transform that apply several sets of transform to the inputs.

Parameters:

set_transforms (List[Any]) – List of Dictionary of sets of transforms specifying transforms and number of views per set.

Example:

set_transforms = [
    {'transform': [...], 'num_views': ...},
    {'transform': [...], 'num_views': ...},
    ...
]

transform = MultiCropTransform(
    set_transforms
)

Only input transform

class eztorch.transforms.OnlyInputTransform(transform)[source]

Apply Transform to only the key 'input' in a sample dictionary.

Parameters:

transform (Callable) – The transform to apply.

class eztorch.transforms.OnlyInputListTransform(transform)[source]

Apply Transform to only the key 'input' in a list of sample dictionary.

Parameters:

transform (Callable) – The transform to apply.

class eztorch.transforms.OnlyInputListSameTransform(transform)[source]

Apply the same transform to only the key 'input' in a list of sample dictionary.

Parameters:

transform (Callable) – The transform to apply.

class eztorch.transforms.OnlyInputTransformWithDictTransform(transform, dict_transform, first_dict=False)[source]

Apply Transform to only the key 'input' in a sample dictionary with a transformation on the dictionary afterwards.

Parameters:
  • transform (Callable) – The transform to apply to the input.

  • dict_transform (Callable) – The transform to apply to the dictionary.

  • first_dict (bool, optional) – If True, first apply the transformation on the dict, else, first apply the transformation on the input.

    Default: False

class eztorch.transforms.OnlyInputListTransformWithDictTransform(transform, dict_transform, first_dict=False)[source]

Apply Transform to only the key 'input' in a list of sample dictionary with a transformation on the dictionary afterwards.

Parameters:
  • transform (Callable) – The transform to apply to the input.

  • dict_transform (Callable) – The transform to apply to the dictionary.

  • first_dict (bool, optional) – If True, first apply the transformation on the dict, else, first apply the transformation on the input.

    Default: False

Random Resized Crop

class eztorch.transforms.RandomResizedCrop(size, scale=[0.08, 1.0], ratio=[0.75, 1.3333333333333333], interpolation='bilinear', antialias=True, **kwargs)[source]

Remove key

class eztorch.transforms.RemoveKey(key)[source]

Removes the given key from the input dict. Useful for removing modalities from a video clip that aren’t needed.

Parameters:

key (str) – The dictionary key to remove.

class eztorch.transforms.RemoveAudioKey[source]

Remove audio key from sample dictionary.

class eztorch.transforms.RemoveInputKey[source]

Remove video key from sample dictionary.