lingvo.tasks.car.kitti_decoder module

Base models for point-cloud based detection.

class lingvo.tasks.car.kitti_decoder.KITTIDecoder(*args, **kwargs)

Bases: lingvo.tasks.car.base_decoder.BaseDecoder

A decoder to use for decoding a detector model on KITTI.

This class implements the basic Decoder metrics for KITTI to provide visualizations and AP calculations.

classmethod Params()

Returns the layer params.

CreateDecoderMetrics()

Decoder metrics for KITTI.

_CreateFrustumMask(bbox_corners_image, bbox2d_corners_image_clipped, image_height, image_width)

Creates a box mask for boxes whose projections fall outside of image.

_BBox2DImage(bbox_corners_image, input_images)

Compute [xmin, ymin, xmax, ymax] 2D bounding boxes from corners.

ProcessOutputs(input_batch, model_outputs)

Produce additional decoder outputs for KITTI.

Parameters

• input_batch – A .NestedMap of the inputs to the model.

• model_outputs –

  A .NestedMap of the outputs of the model, including::

  • per_class_predicted_bboxes: [batch, num_classes, num_boxes, 7] float Tensor with per class 3D (7 DOF) bounding boxes.

  • per_class_predicted_bbox_scores: [batch, num_classes, num_boxes] float Tensor with per class, per box scores.

  • per_class_valid_mask: [batch, num_classes, num_boxes] masking Tensor indicating which boxes were still kept after NMS for each class.

Returns

A NestedMap of additional decoder outputs needed for PostProcessDecodeOut.

PostProcessDecodeOut(dec_out_dict, dec_metrics_dict)

Post-processes the decoder outputs.