Function detector_postprocess

semantic_sam/modules/postprocessing.py:9–75

Resize the output instances. The input images are often resized when entering an object detector. As a result, we often need the outputs of the detector in a different resolution from its inputs. This function will resize the raw outputs of an R-CNN detector to produce outp

(
    results: Instances, output_height: int, output_width: int, mask_threshold: float = 0.5
)

# perhaps should rename to "resize_instance"
def detector_postprocess(
    results: Instances, output_height: int, output_width: int, mask_threshold: float = 0.5
):
    """
    Resize the output instances.
    The input images are often resized when entering an object detector.
    As a result, we often need the outputs of the detector in a different
    resolution from its inputs.

    This function will resize the raw outputs of an R-CNN detector
    to produce outputs according to the desired output resolution.

    Args:
        results (Instances): the raw outputs from the detector.
            `results.image_size` contains the input image resolution the detector sees.
            This object might be modified in-place.
        output_height, output_width: the desired output resolution.

    Returns:
        Instances: the resized output from the model, based on the output resolution
    """
    if isinstance(output_width, torch.Tensor):
        # This shape might (but not necessarily) be tensors during tracing.
        # Converts integer tensors to float temporaries to ensure true
        # division is performed when computing scale_x and scale_y.
        output_width_tmp = output_width.float()
        output_height_tmp = output_height.float()
        new_size = torch.stack([output_height, output_width])
    else:
        new_size = (output_height, output_width)
        output_width_tmp = output_width
        output_height_tmp = output_height

    scale_x, scale_y = (
        output_width_tmp / results.image_size[1],
        output_height_tmp / results.image_size[0],
    )
    results = Instances(new_size, **results.get_fields())

    if results.has("pred_boxes"):
        output_boxes = results.pred_boxes
    elif results.has("proposal_boxes"):
        output_boxes = results.proposal_boxes
    else:
        output_boxes = None
    assert output_boxes is not None, "Predictions must contain boxes!"

    output_boxes.scale(scale_x, scale_y)
    output_boxes.clip(results.image_size)

    results = results[output_boxes.nonempty()]

    if results.has("pred_masks"):
        if isinstance(results.pred_masks, ROIMasks):
            roi_masks = results.pred_masks
        else:
            # pred_masks is a tensor of shape (N, 1, M, M)
            roi_masks = ROIMasks(results.pred_masks[:, 0, :, :])