ONE - On-device Neural Engine
|
Pass to quantize weights. More...
#include <QuantizeWeightsPass.h>
Data Structures | |
struct | Context |
Public Member Functions | |
QuantizeWeightsPass (std::unique_ptr< Context > &&ctx) | |
QuantizeWeightsPass (loco::DataType input_model_dtype, loco::DataType output_model_dtype, QuantizationGranularity granularity) | |
virtual const char * | name (void) const |
bool | run (loco::Graph *graph) |
Run the pass. | |
Public Member Functions inherited from logo::Pass | |
virtual | ~Pass ()=default |
Pass to quantize weights.
Definition at line 32 of file QuantizeWeightsPass.h.
|
inline |
Definition at line 43 of file QuantizeWeightsPass.h.
|
inline |
Definition at line 49 of file QuantizeWeightsPass.h.
|
inlinevirtual |
Reimplemented from logo::Pass.
Definition at line 59 of file QuantizeWeightsPass.h.
|
virtual |
Run the pass.
Implements logo::Pass.
Definition at line 26 of file QuantizeWeightsPass.cpp.
References loco::active_nodes(), INFO, LOGGER, and loco::output_nodes().
Referenced by package.infer.session::inference().