zensvi.cv.ClassifierGlare

class zensvi.cv.ClassifierGlare(device=None, verbosity=1)

Bases: zensvi.cv.classification.base.BaseClassifier

A classifier for identifying glare in images using the model from Hou et al (2024) (https://github.com/ualsg/global-streetscapes).

Parameters:

  • device (str, optional) – The device that the model should be loaded onto. Options are “cpu”, “cuda”, or “mps”. If None, the model tries to use a GPU if available; otherwise, falls back to CPU.

  • verbosity (int, optional) – Level of verbosity for progress bars. Defaults to 1. 0 = no progress bars, 1 = outer loops only, 2 = all loops.

classify(dir_input: str | pathlib.Path, dir_summary_output: str | pathlib.Path, batch_size=1, save_format='json csv', verbosity: int = None) → List[str]

Classifies images based on presence of glare.

Processes images from the input directory and classifies them as having glare (“True”) or not having glare (“False”). Results can be saved in JSON and/or CSV format.

Parameters:

  • dir_input – Directory containing input images or path to a single image.

  • dir_summary_output – Directory to save classification results.

  • batch_size – Number of images to process simultaneously. Defaults to 1.

  • save_format – Space-separated string of output formats. Options are “json” and “csv”. Defaults to “json csv”.

  • verbosity (int, optional) – Level of verbosity for progress bars. If None, uses the instance’s verbosity level. 0 = no progress bars, 1 = outer loops only, 2 = all loops.

Returns:

List of glare classifications (“True” or “False”) for each image.

property verbosity

Property for the verbosity level of progress bars.

Returns:

verbosity level (0=no progress, 1=outer loops only, 2=all loops)

Return type:

int