ONE - On-device Neural Engine
|
Pass to quantize weights. More...
#include <QuantizeDequantizeWeightsPass.h>
Data Structures | |
struct | Context |
Public Member Functions | |
QuantizeDequantizeWeightsPass (std::unique_ptr< Context > &&ctx) | |
QuantizeDequantizeWeightsPass (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 QuantizeDequantizeWeightsPass.h.
|
inline |
Definition at line 44 of file QuantizeDequantizeWeightsPass.h.
|
inline |
Definition at line 50 of file QuantizeDequantizeWeightsPass.h.
|
inlinevirtual |
Reimplemented from logo::Pass.
Definition at line 60 of file QuantizeDequantizeWeightsPass.h.
|
virtual |
Run the pass.
Implements logo::Pass.
Definition at line 432 of file QuantizeDequantizeWeightsPass.cpp.
References loco::active_nodes(), INFO, luci::layer_info_map(), LOGGER, luci::CircleNode::name(), and loco::output_nodes().
Referenced by package.infer.session::inference().