The same as `model.named_modules()`, except that it includes duplicated modules that have more than one name.

Strip the prefix in metadata, if any. Args: state_dict (OrderedDict): a state-dict to be loaded to the model. prefix (str): p

Strip the prefix in metadata, if any. Args: state_dict (OrderedDict): a state-dict to be loaded to the model. prefix (str): p

Build a module from config dict. Args: cfg (edict): Config dict. It should at least contain the key "NAME". registry (:obj:`Regist

Earth Mover Distance (Approx) Args: xyz1 (torch.Tensor): (b, n1, 3) xyz2 (torch.Tensor): (b, n2, 3) trans

Expect input as shape [sequence len, batch] If classify, return classification logits

Expect input as shape [sequence len, batch] If classify, return classification logits

point_groups : B G N 3 ----------------- feature_global : B G C

point_groups : B G N 3 ----------------- feature_global : B G C

input: B N 3 --------------------------- output: B G M 3 center : B G 3

Args: xyz: Point positions (*, d_in) Returns: pos_emb (*, d_out)

Input: xyz: input points position data, [B, N, C] points: input points data, [B, N, C] Return: ne

Input: xyz: input points position data, [B, C, N] points: input points data, [B, D, N] Return: ne

Input: xyz1: input points position data, [B, C, N] xyz2: sampled input points position data, [B, C, S] po

Earth Mover Distance (Approx) Args: xyz1 (torch.Tensor): (b, n1, 3) xyz2 (torch.Tensor): (b, n2, 3) trans

Expect input as shape [sequence len, batch] If classify, return classification logits

Expect input as shape [sequence len, batch] If classify, return classification logits

input: B N 3 --------------------------- output: B G M 3 center : B G 3

point_groups : B G N 3 ----------------- feature_global : B G C

point_groups : B G N 3 ----------------- feature_global : B G C

Args: xyz: Point positions (*, d_in) Returns: pos_emb (*, d_out)

Input: xyz: input points position data, [B, C, N] points: input points data, [B, D, N] Return: ne

Input: xyz: input points position data, [B, C, N] points: input points data, [B, D, N] Return: ne

Input: xyz1: input points position data, [B, C, N] xyz2: sampled input points position data, [B, C, S] po

Get root logger and add a keyword filter to it. The logger will be initialized if it has not been initialized. By default a StreamHandler will

Check whether it is a sequence of some type. Args: seq (Sequence): The sequence to be checked. expected_type (type): Expected type

Check whether it is a sequence of some type. Args: seq (Sequence): The sequence to be checked. expected_type (type): Expected type

Randomly jitter points. jittering is per point. Input: BxNx3 array, original batch of point clouds Return: BxNx3

Normalize the batch data, use coordinates of the block centered at origin, Input: BxNxC array Output: BxNxC a

Print a log message. Args: msg (str): The message to be logged. logger (logging.Logger | str | None): The logger to be used.

batch_pc: BxNx3

Randomly scale the point cloud. Scale is per point cloud. Input: BxNx3 array, original batch of point clouds Return:

for acc kind, get the mean in each gpu

Register a module. A record will be added to `self._module_dict`, whose key is the class name or the specified name, and value is the

Randomly perturb the point clouds by small rotations Input: BxNx3 array, original batch of point clouds Return: B

Randomly perturb the point clouds by small rotations Input: BxNx6 array, original batch of point clouds and point normals R

Randomly rotate the point clouds to augument the dataset rotation is per shape based along up direction Input: BxNx3 array,