Visualize the embeddings in 2D or 3D using UMAP projection
TFSimilarity.visualization.projector(
labels: Optional[Sequence[Any]] = None,
class_mapping: Optional[Sequence[int]] = None,
image_size: int = 64,
tooltips_info: Optional[Mapping[str, Sequence[str]]] = None,
pt_size: int = 3,
colorize: bool = True,
pastel_factor: float = 0.1,
plot_size: int = 600,
active_drag: str = box_zoom,
densmap: bool = True
)
embeddings | The embeddings outputed by the model that are to be visualized |
labels | Labels associated with the embeddings. If not supplied treat each example as its own classes. |
class_mapping | Dictionary or list that maps the class numerical ids to their name. |
images | Images to display in tooltip on hover. Usually x_test tensor. |
image_size | size of the images displayed in the tool tip. Defaults to 64. |
pt_size | Size of the points displayed on the visualization. Defaults to 3. |
tooltips_info | Dictionary of information to display in the tooltips. |
colorize | Colorize the clusters. Defaults to true. |
pastel_factor | Modify the color palette to be more pastel. |
densmap | Use UMAP dense mapper which provides better density estimation but is a little slower. Defaults to True. |