torchelie.data_learning¶

class
torchelie.data_learning.
CorrelateColors
¶ Takes an learnable image and applies the inverse color decorrelation from ImageNet (ie, it correlates the color like ImageNet to ease optimization)

invert
(t: torch.Tensor) → torch.Tensor¶ Decorrelate the color of the image t and return the result


class
torchelie.data_learning.
ParameterizedImg
(*shape: int, init_sd: float = 0.06, init_img: Optional[torch.Tensor] = None, space: typing_extensions.Literal[spectral, pixel] = 'spectral', colors: typing_extensions.Literal[uncorr, corr] = 'uncorr')¶ A convenient wrapper around PixelImage and SpectralImage and CorrelateColors to make a learnable image.
 Parameters
*shape (int) – shape of the image: channel, height, width
init_sd (float) – standard deviation for initializing the image if init_img is None
init_img (tensor) – an image to use as initialization
space (str) – either “pixel” or “spectral” to have the underlying representation be a PixelImage or a SpectralImage
colors (str) – either “corr” or “uncorr”, to use a correlated or decorrelated color space

forward
()¶ Return the tensor

render
()¶ Return the tensor on cpu and detached, ready to be transformed to a PIL image

class
torchelie.data_learning.
PixelImage
(shape: Tuple[int, …], sd: float = 0.01, init_img: Optional[torch.Tensor] = None)¶ A learnable image parameterized by its pixel values
 Parameters
shape (tuple of int) – a tuple like (channels, height, width)
sd (float) – pixels are initialized with a random gaussian value of mean 0.5 and standard deviation sd
init_img (tensor, optional) – an image tensor to initialize the pixel values

forward
()¶ Return the image

class
torchelie.data_learning.
SpectralImage
(shape: Tuple[int, …], sd: float = 0.01, decay_power: int = 1, init_img: Optional[torch.Tensor] = None)¶ A learnable image parameterized by its Fourier representation.
See https://distill.pub/2018/differentiableparameterizations/
Implementation ported from https://github.com/tensorflow/lucid/blob/master/lucid/optvis/param/spatial.py
 Parameters
shape (tuple of int) – a tuple like (channels, height, width)
sd (float) – amplitudes are initialized with a random gaussian value of mean 0.5 and standard deviation sd
init_img (tensor, optional) – an image tensor to initialize the image

forward
() → torch.Tensor¶ Return the image