zensvi.cv.ClassifierPerceptionViT

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

Bases: zensvi.cv.classification.base.BaseClassifier

A classifier for evaluating the perception of streetscape based on a given study

Parameters:

  • perception_study (str) – The specific perception study for which the model is trained, including “safer”, “livelier”, “wealthier”, “more beautiful”, “more boring”, “more depressing”. This affects the checkpoint file used.

  • 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 human perception of streetscapes from the specified perception study.

Parameters:

  • dir_input (Union[str, Path]) – Directory containing input images.

  • dir_summary_output (Union[str, Path]) – Directory to save summary output. If None, output is not saved.

  • batch_size (int, optional) – Batch size for inference. Defaults to 1.

  • save_format (str, optional) – Save format for the output. Options are “json” and “csv”. Add a space between options. 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 dictionaries containing perception scores for each image.

Return type:

List[dict]

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