Permutes data in the channel dimension of the input. More...
#include <shuffle_channels.hpp>
Public Member Functions | |
const NodeTypeInfo & | get_type_info () const override |
ShuffleChannels (const Output< Node > &data, const int64_t axis=1, const int64_t group=1) | |
Constructs a ShuffleChannels node. More... | |
bool | visit_attributes (AttributeVisitor &visitor) override |
size_t | get_zero_based_axis () const |
virtual void | pre_validate_and_infer_types () override |
virtual OutputVector | decompose_op () const override |
virtual std::shared_ptr< Node > | clone_with_new_inputs (const OutputVector &new_args) const override |
int64_t | get_axis () const |
int64_t | get_group () const |
Static Public Attributes | |
static constexpr NodeTypeInfo | type_info {"ShuffleChannels", 0} |
Permutes data in the channel dimension of the input.
ngraph::op::v0::ShuffleChannels::ShuffleChannels | ( | const Output< Node > & | data, |
const int64_t | axis = 1 , |
||
const int64_t | group = 1 |
||
) |
Constructs a ShuffleChannels node.
data | - Node producing the input tensor |
axis | - channel dimension index in the data tensor. A negative value means that the index should be calculated from the back of the input data shape. |
group | - number of group the channel dimension specified by axis should be split into |