Modules

Reference information for the multimodal Modules API.

eva.multimodal.models.modules.VisionLanguageModule

Bases: ModelModule

Model module for vision-language tasks.

Parameters:

Name	Type	Description	Default
model	Module	Model instance to use for forward pass.	required
metrics	MetricsSchema | None	Metrics schema for evaluation.	None
postprocess	BatchPostProcess | None	A helper function to post-process model outputs before evaluation.	None

Source code in src/eva/multimodal/models/modules/vision_language.py

def __init__(
    self,
    model: nn.Module,
    metrics: metrics_lib.MetricsSchema | None = None,
    postprocess: batch_postprocess.BatchPostProcess | None = None,
) -> None:
    """Initializes the text inference module.

    Args:
        model: Model instance to use for forward pass.
        metrics: Metrics schema for evaluation.
        postprocess: A helper function to post-process model outputs before evaluation.
    """
    super().__init__(metrics=metrics, postprocess=postprocess)

    self.model = model