ONE - On-device Neural Engine
|
Pass to create a quantized graph from a graph fake-quantized on onnx. More...
#include <QuantizeOnnxFakeQuantModelPass.h>
Data Structures | |
struct | Context |
Public Member Functions | |
QuantizeOnnxFakeQuantModelPass (std::unique_ptr< Context > &&ctx) | |
virtual const char * | name (void) const |
bool | run (loco::Graph *graph) |
Public Member Functions inherited from logo::Pass | |
virtual | ~Pass ()=default |
Pass to create a quantized graph from a graph fake-quantized on onnx.
Definition at line 32 of file QuantizeOnnxFakeQuantModelPass.h.
|
inline |
Definition at line 41 of file QuantizeOnnxFakeQuantModelPass.h.
|
inlinevirtual |
Reimplemented from logo::Pass.
Definition at line 47 of file QuantizeOnnxFakeQuantModelPass.h.
|
virtual |
How QuantizeOnnxFakeQuantModel works?
Before
[node(fp32)] -> [OnnxQuantizeLinear] -> [OnnxDequantizeLinear]
After
[node(q)]
Before
[Const(q w/o qparam)] -> [OnnxDequantizeLinear]
After
[Const(q)]
Implements logo::Pass.
Definition at line 63 of file QuantizeOnnxFakeQuantModelPass.cpp.
References loco::active_nodes(), INFO, luci::is_quantized(), LOGGER, loco::output_nodes(), luci::QuantizeOnnxDequantizeLinearPass::run(), luci::QuantizeOnnxQDQPass::run(), and luci::QuantizeWithPredecessorPass::run().
Referenced by package.infer.session::inference().