xpark.dataset.ImageTextSimilarityScore#

class xpark.dataset.ImageTextSimilarityScore(text: str, _local_model: str = 'openai/clip-vit-base-patch32')[source]#

Image text similarity score calculation processor for CPU, GPU

Parameters:

  • text – The text to be used for similarity score calculation.

  • _local_model – The CLIP model name for CPU or GPU. default is “openai/clip-vit-base-patch32” available models: [‘openai/clip-vit-base-patch32’]

Examples

from xpark.dataset.expressions import col
from xpark.dataset import ImageTextSimilarityScore, from_items
import numpy as np

ds = from_items([
    {"image": np.random.randint(0, 255, (256, 256, 3)).astype(np.uint8), "path": "test.jpg"}
])
ds = ds.with_column(
    "image_score",
    ImageTextSimilarityScore(text="a photo of a cat")
    .options(num_workers={"CPU": 4}, batch_size=1)
    .with_column(col("image")),
)
print(ds.take(1))

Methods

__call__(images)

Call self as a function.

options(**kwargs)

with_column(images)

__call__(images: pa.ChunkedArray) → pa.Array#

Call self as a function.

options(**kwargs: Unpack[ExprUDFOptions]) → Self#
with_column(images: pa.ChunkedArray) → pa.Array#