open3d.ml.tf.ops.sparse_conv_transpose_backprop_filter

open3d.ml.tf.ops.sparse_conv_transpose_backprop_filter(filters, out_importance, inp_features, inp_neighbors_importance_sum, inp_neighbors_row_splits, neighbors_index, neighbors_kernel_index, neighbors_importance, neighbors_row_splits, out_features_gradient, output_type=tf.float32, normalize=False, max_temp_mem_MB=64, name=None)

Computes the backrop for the filter of the SparseConvTranspose

Parameters

• filters –

  A Tensor. Must be one of the following types: float32, float64, bfloat16.

  The filter parameters. The shape of the filter is [depth, height, width, in_ch, out_ch]. The dimensions ‘depth’, ‘height’, ‘width’ define the spatial resolution of the filter. The spatial size of the filter is defined by the parameter ‘extents’.

• out_importance – A Tensor. Must have the same type as filters.

• inp_features – A Tensor. Must have the same type as filters. A 2D tensor which stores a feature vector for each input point.

• inp_neighbors_importance_sum – A Tensor. Must have the same type as filters.

• inp_neighbors_row_splits – A Tensor of type int64. The number of neighbors for each input point as exclusive prefix sum.

• neighbors_index –

  A Tensor. Must be one of the following types: int32, int64.

  The neighbors_index stores a list of indices of neighbors for each output point as nested lists. The start and end of each list can be computed using ‘neighbors_row_splits’.

• neighbors_kernel_index –

  A Tensor. Must be one of the following types: uint8, int16.

  Defines which kernel element to use for each neighbor. This array has the same length as neighbors_index.

• neighbors_importance – A Tensor. Must have the same type as filters.

• neighbors_row_splits – A Tensor of type int64. The number of neighbors for each output point as exclusive prefix sum.

• out_features_gradient – A Tensor. Must have the same type as filters. A Tensor with the gradient for the outputs of the SparseConvTranspose in the forward pass.

• output_type – An optional tf.DType from: tf.float32, tf.float64, tf.bfloat16. Defaults to tf.float32. The type for the output.

• normalize – An optional bool. Defaults to False. If True the input feature values will be normalized by the number of neighbors.

• max_temp_mem_MB – An optional int. Defaults to 64. Defines the maximum temporary memory in megabytes to be used for the GPU implementation. More memory means fewer kernel invocations. Note that the a minimum amount of temp memory will always be allocated even if this variable is set to 0.

• name – A name for the operation (optional).

Returns

A Tensor of type output_type. The gradients for the filter