Class for easily obtaining simulated camera image observations in pybullet

Basic convolutional module consisting of a Conv3d, non-linearity and optional batchnorm/groupnorm. The order of operations can be specified v

A single module from the encoder path consisting of the optional max pooling layer (one may specify the MaxPool kernel_size to be different

`UNet` class is based on https://arxiv.org/abs/1505.04597 The U-Net is a convolutional encoder-decoder neural network. Contextual spatial in

3DUnet model from `"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation" <https://arxiv.org/pdf/1606.06650.pdf>`.

Upsamples a given multi-channel 3D data using either interpolation or learned transposed convolution. Args: transposed_conv (bool):

A single module for decoder path consisting of the upsampling layer (either learned ConvTranspose3d or nearest neighbor interpolation) follow

A helper Module that performs 2 convolutions and 1 MaxPool. A ReLU activation follows each convolution.

PointNet-based encoder network with ResNet blocks for each point. Number of input points are fixed. Args: c_dim (int): dimen

Fully connected ResNet Block class. Args: size_in (int): input dimension size_out (int): output dimension size_h (int):

A helper Module that performs 2 convolutions and 1 UpConvolution. A ReLU activation follows each convolution.

Add new keys to the given input Args: s (float): the defined voxel size pos_encoding (str): method for the positional encoding,

Positional Encoding (presented in NeRF) Args: basis_function (str): basis function

Base class for standard and residual UNet. Args: in_channels (int): number of input channels out_channels (int): number of o

A module consisting of two consecutive convolution layers (e.g. BatchNorm3d+ReLU+Conv3d). We use (Conv3d+ReLU+GroupNorm3d) by default. Th

Basic UNet block consisting of a SingleConv followed by the residual block. The SingleConv takes care of increasing/decreasing the number of

A module consisting of a convolution layer (e.g. Conv3d+ReLU+GroupNorm3d) and the final 1x1 convolution which reduces the number of channels

A Pdb subclass that may be used from a forked multiprocessing child

Base class for our policies that operate on local point features. Input processing and output processing are the same, the only thing that di

Class for collision checking between different segmented pointclouds, based on convex hull inclusion. Args: collision_pcds (list): E

Attributes: parent (int): Index used to refer to previous state visited in planning point_cloud (np.ndarray): N X 3 pointcloud ob

Class for representing object configurations based on point clouds, nodes in a search tree where edges represent rigid transformations between

Residual 3DUnet model implementation based on https://arxiv.org/pdf/1706.00120.pdf. Uses ExtResNetBlock as a basic building block, summation

r"""Generates collate function for coords, feats, labels. Please refer to `the training example <https://nvidia.github.io/MinkowskiEngine/dem