xpark.dataset.ImageAestheticScore#

class xpark.dataset.ImageAestheticScore(_local_model: str = 'shunk031/aesthetics-predictor-v2-sac-logos-ava1-l14-linearMSE', normalized: bool = False)[source]#

Image aesthetic score calculation processor for CPU, GPU. Image aesthetic score is a value between 0 and 10, with higher scores indicating better image quality.

Parameters:

  • _local_model – The CLIP base aesthetic model name for CPU or GPU. default model is “shunk031/aesthetics-predictor-v2-sac-logos-ava1-l14-linearMSE” available models: [‘shunk031/aesthetics-predictor-v2-sac-logos-ava1-l14-linearMSE’, ‘shunk031/aesthetics-predictor-v1-vit-large-patch14’]

  • normalized – Whether to normalize the score to [0, 1], default is False

Examples

from xpark.dataset.expressions import col
from xpark.dataset import ImageAestheticScore, 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",
    ImageAestheticScore()
    .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#