open3d.ml.tf.models

Classes

BaseModel(*args, **kwargs)	Base class for models.
BatchNormBlock(*args, **kwargs)
DataProcessing()
GlobalAverageBlock(*args, **kwargs)
IdentityBlock(*args, **kwargs)
KDTree(X[, leaf_size, metric])	KDTree for fast generalized N-point problems
KPConv(*args, **kwargs)
KPFCNN(*args, **kwargs)	Class defining KPFCNN.
MaxPoolBlock(*args, **kwargs)
NearestUpsampleBlock(*args, **kwargs)
Path(*args, **kwargs)	PurePath subclass that can make system calls.
RandLANet(*args, **kwargs)	Class defining RandLANet.
ResnetBottleneckBlock(*args, **kwargs)
SimpleBlock(*args, **kwargs)
UnaryBlock(*args, **kwargs)
tqdm(*_, **__)	Decorate an iterable object, returning an iterator which acts exactly like the original iterable, but prints a dynamically updating progressbar every time a value is requested.

Functions

abspath(path)	Return an absolute path.
batch_grid_subsampling(points, batches, dl)	TODO: add doc.
batch_ordered_neighbors(queries, supports, …)	TODO: add doc.
block_decider(block_name, radius, in_dim, …)
build_spatial_hash_table(points, radius, …)	Creates a spatial hash table meant as input for fixed_radius_search
closest_pool(x, inds)	This tensorflow operation compute a pooling according to the list of indices ‘inds’.
confusion_matrix(y_true, y_pred, *[, …])	Compute confusion matrix to evaluate the accuracy of a classification.
continuous_conv(filters, out_positions, …)	Continuous convolution of two pointclouds.
continuous_conv_backprop_filter(filters, …)	Computes the backprop for the filter of the ContinuousConv
continuous_conv_transpose(filters, …[, …])	Continuous tranpose convolution of two pointclouds.
continuous_conv_transpose_backprop_filter(…)	Computes the backrop for the filter of the ContinuousConvTranspose
create_kernel_points(radius, num_kpoints, …)
dirname(p)	Returns the directory component of a pathname
exists(path)	Test whether a path exists.
fixed_radius_search(points, queries, radius, …)	Computes the indices of all neighbors within a radius.
get_bias(shape)
get_weight(shape)
global_average(x, batch_lengths)	Block performing a global average over batch pooling :param x: [N, D] input features :param batch_lengths: [B] list of batch lengths :return: [B, D] averaged features
grid_subsampling(points, dl[, name])	TODO: add doc.
invert_neighbors_list(num_points, …[, name])	Inverts a neighbors list made of neighbors_index and neighbors_row_splits.
isfile(path)	Test whether a path is a regular file
join(a, *p)	Join two or more pathname components, inserting ‘/’ as needed.
knn_search(points, queries, k, …[, …])	Computes the indices of k nearest neighbors.
makedirs(name [[, mode, exist_ok])	Super-mkdir; create a leaf directory and all intermediate ones.
max_pool(x, inds)	Pools features with the maximum values.
ordered_neighbors(queries, supports, radius)	TODO: add doc.
radius_gaussian(sq_r, sig[, eps])	Compute a radius gaussian (gaussian of distance) :param sq_r: input radiuses [dn, …, d1, d0] :param sig: extents of gaussians [d1, d0] or [d0] or float :return: gaussian of sq_r [dn, …, d1, d0]
radius_search(points, queries, radii, …[, …])	Computes the indices and distances of all neigbours within a radius.
reduce_subarrays_sum(values, row_splits[, name])	Computes the sum for each subarray in a flat vector of arrays.
split(p)	Split a pathname.
tf_batch_neighbors(queries, supports, …[, …])	TODO: add doc.
tf_batch_subsampling(points, batches, dl[, name])	TODO: add doc.
trans_augment(points, t_augment)	Implementation of an augmentation transform for point clouds.
trans_crop_pc(points, feat, labels, …)
trans_normalize(pc, feat, t_normalize)
voxel_pooling(positions, features, voxel_size)	Spatial pooling for point clouds by combining points that fall into the same voxel bin.
voxel_pooling_grad(positions, features, …)	Gradient for features in VoxelPooling.