ONE - On-device Neural Engine
|
Description of tensor concatenation operation. More...
#include <ConcatOp.h>
Public Member Functions | |
ConcatOp (const std::vector< Output * > &args, int32_t axis) | |
Operation * | copyWithInputs (const std::vector< Output * > &inputs) override |
int32_t | getAxis () const |
Public Member Functions inherited from mir::Operation | |
virtual | ~Operation ()=default |
Type | getType () const |
std::size_t | getId () const |
void | setId (std::size_t id) |
std::size_t | getNumInputs () const |
std::size_t | getNumOutputs () const |
std::deque< Output * > & | getInputs () |
const std::deque< Output * > & | getInputs () const |
std::deque< Output > & | getOutputs () |
const std::deque< Output > & | getOutputs () const |
Output * | getInput (std::size_t index) |
const Output * | getInput (std::size_t index) const |
Output * | getOutput (std::size_t index) |
const Output * | getOutput (std::size_t index) const |
const Shape & | getInputShape (std::size_t index) const |
const Shape & | getOutputShape (std::size_t index) const |
void | accept (IVisitor *v) |
Additional Inherited Members | |
Public Types inherited from mir::Operation | |
enum class | Type { HANDLE_OP } |
Protected Member Functions inherited from mir::Operation | |
Operation (Type type, const std::vector< Output * > &inputs, std::size_t num_outputs=1) | |
void | setOutputType (std::size_t index, const TensorType &type) |
Description of tensor concatenation operation.
Definition at line 30 of file ConcatOp.h.
|
inline |
Definition at line 33 of file ConcatOp.h.
|
inlineoverridevirtual |
Implements mir::Operation.
Definition at line 39 of file ConcatOp.h.
|
inline |
Definition at line 44 of file ConcatOp.h.
References mir::Operation::getInputShape(), and mir::Shape::rank().
Referenced by mir_interpreter::MIRInterpreter::visit(), mir2loco::Transformer::visit(), nnc::AclCppOpGenerator::visit(), nnc::Serializer::visit(), and mir::DotNodeBuilder::visit().