Frees all allocated memory chunks */

Frees all allocated memory chunks */

Frees all allocated memory chunks */

Return layers for the image model

Get a logging-friendly message to report parameter names (keys) that are in the model but not found in a checkpoint. Args: keys (

Get a logging-friendly message to report parameter names (keys) that are in the checkpoint but not found in the model. Args: keys

Perform per-sample random masking by per-sample shuffling. Per-sample shuffling is done by argsort random noise. x: [N, L, 3]

ST-gumple-softmax w/o random gumbel samplings input: [*, n_class] return: flatten --> [*, n_class] an one-hot vector

Input: points: input points data, [B, N, C] idx: sample index data, [B, S] Return: new_points:, indexed points data,

Infer the scope of registry. The name of the package where registry is defined will be returned. Example: # in mmdet/model

Infer the scope of registry. The name of the package where registry is defined will be returned. Example: # in mmdet/model

Input: nsample: max sample number in local region xyz: all points, [B, N, C] new_xyz: query points, [B, S, C] Return:

Input: nsample: max sample number in local region xyz: all points, [B, N, C] new_xyz: query points, [B, S, C] Return:

Input: nsample: max sample number in local region xyz: all points, [B, N, C] new_xyz: query points, [B, S, C] Return:

Get the distances and indices to a fixed number of neighbors Args: support ([tensor]): [B, N, C] query ([tensor]): [B,

* Returns a pointer to a piece of new memory of the given size in bytes * allocated from the pool. */

* Returns a pointer to a piece of new memory of the given size in bytes * allocated from the pool. */

* Returns a pointer to a piece of new memory of the given size in bytes * allocated from the pool. */

Args: feature [input feature]: (B, N, d) interp_idx [Nearest neighbor index]: (B, N_up, 1) Return: interpolated_feat

Converts input to 1-hot encoding given a set of allowable values. Additionally maps inputs not in the allowable set to the last element.

pc: NxC, return NxC

pc: NxC, return NxC

pc: NxC, return NxC

:param points: [batch, num_points, 3] :param rot_mat: [batch, 3] :param translation: [batch, 1, 3] :return:

:param points: [B, num_points, 3] :param image_width: :param image_height: :param size_x: :param size_y: :return: dep

Input: radius: local region radius nsample: max sample number in local region xyz: all points, [B, N, 3] new_xyz:

Perform per-sample random masking by per-sample shuffling. Per-sample shuffling is done by argsort random noise. x: [N, L, D]

Perform per-sample random masking by per-sample shuffling. Per-sample shuffling is done by argsort random noise. x: [N, L, 3]

batch_pc: BxNx3

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

Ravel the coordinates after subtracting the min coordinates.