List of Visualizers

The following non-container visualizers are currently available. They all derive from BaseVisualizer.

CrackedEdgeVisualizer([width, connective_dims])	Visualize the boundaries of a segmentation.
DiagonalSplitVisualizer([offset])	Combine two input images, displaying one above and one below the diagonal.
IdentityVisualizer(**super_kwargs)	Visualizer that returns the tensor passed to it.
ImageVisualizer(**super_kwargs)	Same as IdentityVisualizer, but acting on ‘image’.
InputVisualizer(**super_kwargs)	Same as IdentityVisualizer, but acting on ‘input’.
MSEVisualizer(**super_kwargs)	Visualize the Mean Squared Error (MSE) between two tensors (e.g.
MaskVisualizer(mask_label, **super_kwargs)	Returns a mask that is 1 where the input image equals the mask label passed at initialization, and 0 elsewhere
MaskedPcaVisualizer([ignore_label, …])	Version of PcaVisualizer that allows for an ignore mask.
NormVisualizer([order, dim])	Visualize the norm of a tensor, along a given direction (by default over the channels).
PcaVisualizer([n_components, joint_specs])	PCA Visualization of high dimensional embedding tensor.
PredictionVisualizer(**super_kwargs)	Same as IdentityVisualizer, but acting on ‘prediction’.
RGBVisualizer(**super_kwargs)	Visualize the input tensor as RGB images.
SegmentationVisualizer(**super_kwargs)	Same as IdentityVisualizer, but acting on ‘segmentation’.
TargetVisualizer(**super_kwargs)	Same as IdentityVisualizer, but acting on ‘target’.
ThresholdVisualizer(threshold[, mode])	Returns a mask resulting from thresholding the input tensor.
TsneVisualizer([joint_dims, n_components])	tSNE Visualization of high dimensional embedding tensor.
UmapVisualizer([joint_dims, n_components, …])	UMAP Visualization of high dimensional embedding tensor.
UpsamplingVisualizer(specs[, shape, factors])	Upsample a tensor along a list of axis (specified via specs) to a specified shape, by a list of specified factors or the shape of a reference tensor (given as an optional argument to visualize).

These are the available visualizers combining multiple visualizations. Their base class is the ContainerVisualizer.

ColumnVisualizer(*super_args, **super_kwargs)	Visualizer that arranges outputs of child visualizers in a grid of images, with different child visualizations stacked horizontally (side by side).
ImageGridVisualizer([row_specs, …])	Visualizer that arranges outputs of child visualizers in a grid of images.
OverlayVisualizer(*super_args, **super_kwargs)	Visualizer that overlays the outputs of its child visualizers on top of each other, using transparency based on the alpha channel.
RiffleVisualizer([riffle_dim])	Riffles the outputs of its child visualizers along specified dimension.
RowVisualizer(*super_args, **super_kwargs)	Visualizer that arranges outputs of child visualizers in a grid of images, with different child visualizations stacked vertically.
StackVisualizer([stack_dim])	Stacks the outputs of its child visualizers along specified dimension.