lazyslide.tl.text_embedding

Contents

lazyslide.tl.text_embedding#

text_embedding(texts, model='plip', amp=None, autocast_dtype=None, device='cpu')#

Embed the text into a vector in the text-vision co-embedding using

Parameters:
textsList[str]

The list of texts.

model{“plip”, “conch”, “omiclip”}, default: “plip”

The text embedding multimodal model

ampbool, default: False

Whether to use automatic mixed precision (AMP) for inference.

autocast_dtypetorch.dtype, default: torch.float16

The dtype for automatic mixed precision.

devicestr, default: “cpu”

The device to use for computation (e.g., ‘cpu’, ‘cuda’, ‘mps’).

Returns:
DataFrame

The embeddings of the texts, with texts as index.

Examples

>>> import lazyslide as zs
>>> wsi = zs.datasets.sample()
>>> zs.pp.find_tissues(wsi)
>>> zs.pp.tile_tissues(wsi, 256, mpp=0.5, key_added="text_tiles")
>>> zs.tl.feature_extraction(wsi, "plip", tile_key="text_tiles")
>>> terms = ["mucosa", "submucosa", "musclaris", "lymphocyte"]
>>> zs.tl.text_embedding(terms, model="plip")
Contents