Ejemplo n.º 1
0
def densepose_chart_predictions_to_dict(instances):
    segmentations = ToMaskConverter.convert(instances.pred_densepose,
                                            instances.pred_boxes,
                                            instances.image_size)

    results = []
    for k in range(len(instances)):
        densepose_results_quantized = quantize_densepose_chart_result(
            ToChartResultConverter.convert(instances.pred_densepose[k],
                                           instances.pred_boxes[k]))
        densepose_results_quantized.labels_uv_uint8 = (
            densepose_results_quantized.labels_uv_uint8.cpu())
        segmentation = segmentations.tensor[k]
        segmentation_encoded = mask_utils.encode(
            np.require(segmentation.numpy(),
                       dtype=np.uint8,
                       requirements=["F"]))
        segmentation_encoded["counts"] = segmentation_encoded["counts"].decode(
            "utf-8")
        result = {
            "densepose": densepose_results_quantized,
            "segmentation": segmentation_encoded,
        }
        results.append(result)
    return results
Ejemplo n.º 2
0
    def __call__(self, instances: Instances) -> BitMasks:
        """
        Converts predicted data from `instances` into the GT mask data

        Args:
            instances (Instances): predicted results, expected to have `pred_densepose` field

        Returns:
            Boolean Tensor of the size of the input image that has non-zero
            values at pixels that are estimated to belong to the detected object
        """
        return ToMaskConverter.convert(instances.pred_densepose,
                                       instances.pred_boxes,
                                       instances.image_size)