open3d.ml.tf.models.PointPillars#

class open3d.ml.tf.models.PointPillars(*args, **kwargs)#

Object detection model. Based on the PointPillars architecture https://github.com/nutonomy/second.pytorch.

Parameters:

  • name (string) – Name of model. Default to “PointPillars”.

  • voxel_size – voxel edge lengths with format [x, y, z].

  • point_cloud_range – The valid range of point coordinates as [x_min, y_min, z_min, x_max, y_max, z_max].

  • voxelize – Config of PointPillarsVoxelization module.

  • voxelize_encoder – Config of PillarFeatureNet module.

  • scatter – Config of PointPillarsScatter module.

  • backbone – Config of backbone module (SECOND).

  • neck – Config of neck module (SECONDFPN).

  • head – Config of anchor head module.

__init__(name='PointPillars', point_cloud_range=[0, -40.0, -3, 70.0, 40.0, 1], classes=['car'], voxelize={}, voxel_encoder={}, scatter={}, backbone={}, neck={}, head={}, loss={}, **kwargs)#
augment_data(data, attr)#
call(inputs, training=True)#

Forward pass.

Parameters:

  • inputs – tuple/list of inputs (points, bboxes, labels, calib)

  • training – toggle training run

extract_feats(points, training=False)#

Extract features from points.

get_batch_gen(dataset, steps_per_epoch=None, batch_size=1)#
get_optimizer(cfg)#

Returns an optimizer object for the model.

Parameters:

cfg_pipeline – A Config object with the configuration of the pipeline.

Returns:

Returns a new optimizer object.

inference_end(results, inputs)#

This function is called after the inference.

This function can be implemented to apply post-processing on the network outputs.

Parameters:

results – The model outputs as returned by the call() function. Post-processing is applied on this object.

Returns:

Returns True if the inference is complete and otherwise False. Returning False can be used to implement inference for large point clouds which require multiple passes.

load_gt_database(pickle_path, min_points_dict, sample_dict)#
loss(results, inputs, training=True)#

Computes loss.

Parameters:

  • results – results of forward pass (scores, bboxes, dirs)

  • inputs – tuple/list of gt inputs (points, bboxes, labels, calib)

preprocess(data, attr)#

Data preprocessing function.

This function is called before training to preprocess the data from a dataset.

Parameters:

  • data – A sample from the dataset.

  • attr – The corresponding attributes.

Returns:

Returns the preprocessed data

transform(data, attr)#

Transform function for the point cloud and features.

Parameters:

args – A list of tf Tensors.

voxelize(points)#

Apply hard voxelization to points.