open3d.ml.tf.ops.sparse_conv_backprop_filter

open3d.ml.tf.ops.sparse_conv_backprop_filter(filters, inp_features, inp_importance, 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 backprop for the filter of the SparseConv

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’.

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

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

  • 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. Tensor of the same shape as ‘neighbors_index’ with a scalar value that is used to scale the features of each neighbor.

  • neighbors_row_splits – A Tensor of type int64. The exclusive prefix sum of the neighbor count for the output points including the total neighbor count as the last element. The size of this array is the number of output points + 1.

  • out_features_gradient – A Tensor. Must have the same type as filters. A Tensor with the gradient for the outputs of the SparseConv 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 output 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