rml_op_conv_2d_transpose_params

Parameters for the RML_OP_CONV_2D_TRANSPOSE operation.

API

Graph Manipulation

Items

Name	Type	Description
input	rml_op	Operation that outputs tensor with input data.
weights	rml_op	Constant operation that outputs tensor with the filter weights.
padding_type	rml_padding_type	Padding calculation algorithm.
strides	rml_size_2d	Stride along each spatial axis. If it holds zeros, the stride is set to 1 along each spatial axis.
dilations	rml_size_2d	Dilation value along each spatial axis of the kernel. If it holds zeros, the dilation is set to 1 along each spatial axis.
start_paddings	rml_size_2d	Number of pixels added to the beginning of the each spatial axis. Only make sense if padding type is RML_PADDING_EXPLICIT.
end_paddings	rml_size_2d	Number of pixels added to the end of the each spatial axis. Only make sense if padding type is RML_PADDING_EXPLICIT.
num_groups	uint32_t	Number of groups input channels and output channels are divided into. A zero value is replaced with the default value 1.
output_shape	rml_size_2d	The shape of the output tensor.
output_paddings	rml_size_2d	The zero-padding added to one side of the output.