deepinv.utils#

This module provides various plotting and utility functions. Please refer to the user guide for more information.

Plotting#

User Guide: refer to Plotting for more information.

`deepinv.utils.plot`	Plots a list of images.
`deepinv.utils.plot_curves`	Plots the metrics of a Plug-and-Play algorithm.
`deepinv.utils.plot_parameters`	Plot the parameters of the model before and after training.
`deepinv.utils.plot_inset`	Plots a list of images with zoomed-in insets extracted from the images.
`deepinv.utils.plot_videos`	Plots and animates a list of image sequences.
`deepinv.utils.save_videos`	Saves an animation of a list of image sequences.
`deepinv.utils.plot_ortho3D`	Plots an orthogonal view of 3D images.
`deepinv.utils.disable_tex`	Globally disable LaTeX
`deepinv.utils.enable_tex`	Globally enable LaTeX
`deepinv.utils.normalize_signal`	Normalize a batch of signals between zero and one.
`deepinv.utils.plotting.config_matplotlib`	Config matplotlib for nice plots in the examples.

User Guide: refer to TensorList for more information.

Represents a list of torch.Tensor with different shapes.

`deepinv.utils.zeros_like`	Returns a `deepinv.utils.TensorList` or `torch.Tensor` with the same type as x, filled with zeros.
`deepinv.utils.ones_like`	Returns a `deepinv.utils.TensorList` or `torch.Tensor` with the same type as x, filled with ones.
`deepinv.utils.randn_like`	Returns a `deepinv.utils.TensorList` or `torch.Tensor` with the same type as x, filled with standard gaussian numbers.
`deepinv.utils.rand_like`	Returns a `deepinv.utils.TensorList` or `torch.Tensor` with the same type as x, filled with random uniform numbers in [0,1].

User Guide: refer to Logging for more information.

`deepinv.utils.AverageMeter`	Compute and store aggregates online from a stream of scalar values
`deepinv.utils.ProgressMeter`
`deepinv.utils.get_timestamp`	Get current timestamp string.

User Guide: refer to Mixins for more information.

`deepinv.utils.MRIMixin`	Mixin base class for MRI functionality.
`deepinv.utils.TimeMixin`	Base class for temporal capabilities for physics and models.
`deepinv.utils.TiledMixin2d`	Mixin base class for 2D tiled patch extraction and reconstruction.

User Guide: refer to Image Loading for more information.

`deepinv.utils.load_dicom`	Load image from DICOM file.
`deepinv.utils.load_nifti`	Load volume from nifti file as torch tensor.
`deepinv.utils.load_url`	Load URL to a buffer.
`deepinv.utils.load_np`	Load numpy array from file as torch tensor.
`deepinv.utils.load_torch`	Load torch tensor from file.
`deepinv.utils.load_mat`	Load MATLAB array from file.
`deepinv.utils.load_raster`	Load a raster image and return patches as tensors using `rasterio`.
`deepinv.utils.load_ismrmd`	Load complex MRI data from ISMRMD format.

User Guide: refer to Demo Utils for more information.

`deepinv.utils.load_image`	Load an image from a file and return a torch.Tensor with a batch dimension.
`deepinv.utils.load_url_image`	Load an image from a URL and return a torch.Tensor with a batch dimension.
`deepinv.utils.load_np_url`	Load a numpy array from url and convert to tensor.
`deepinv.utils.load_torch_url`	Load an array from url and read it by torch.load.
`deepinv.utils.load_example`	Load example image from the DeepInverse HuggingFace.
`deepinv.utils.download_example`	Download an image from the DeepInverse HuggingFace to file.
`deepinv.utils.get_data_home`	Return a folder to store deepinv datasets.
`deepinv.utils.get_image_url`	Get URL for image from DeepInverse HuggingFace repository.
`deepinv.utils.get_degradation_url`	Get URL for degradation from DeepInverse HuggingFace repository.
`deepinv.utils.load_dataset`	Loads an ImageFolder dataset from DeepInverse HuggingFace repository.
`deepinv.utils.load_degradation`	Loads a degradation tensor from DeepInverse HuggingFace repository.

User Guide: refer to Other for more information.

`deepinv.utils.get_freer_gpu`	Returns the GPU device with the most free memory.
`deepinv.utils.dirac`	Returns a `torch.Tensor` with a Dirac delta in 2D at the center.
`deepinv.utils.dirac_like`	Returns a `deepinv.utils.TensorList` or `torch.Tensor` with the same type as x, filled with zeros.
`deepinv.utils.dirac_comb`	Returns a `torch.Tensor` with a Dirac comb in 2D (impulse train) at the given step.
`deepinv.utils.dirac_comb_like`	Returns a `deepinv.utils.TensorList` or `torch.Tensor` with the same type as x, filled with a Dirac comb at the given step.