Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
aidge_quantization
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Iterations
Wiki
Requirements
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Snippets
Locked files
Build
Pipelines
Jobs
Pipeline schedules
Test cases
Artifacts
Deploy
Releases
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
CI/CD analytics
Repository analytics
Code review analytics
Issue analytics
Insights
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Terms and privacy
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
Eclipse Projects
aidge
aidge_quantization
Merge requests
!49
Forked from add_matmul (merged automatically)
Code
Review changes
Check out branch
Download
Patches
Plain diff
Merged
Forked from add_matmul (merged automatically)
quantizer_only
into
dev
Overview
3
Commits
15
Pipelines
2
Changes
10
Merged
Benjamin Halimi
requested to merge
quantizer_only
into
dev
2 months ago
Overview
3
Commits
15
Pipelines
2
Changes
10
Expand
Merged automatically when
!45 (merged)
was merged.
Edited
2 months ago
by
Benjamin Halimi
0
0
Merge request reports
Compare
dev
dev (base)
and
latest version
latest version
58ab5a51
15 commits,
2 months ago
10 files
+
448
−
292
Inline
Compare changes
Side-by-side
Inline
Show whitespace changes
Show one file at a time
Files
10
Search (e.g. *.vue) (Ctrl+P)
include/aidge/quantization/QAT/QAT_LSQ.hpp
+
25
−
25
Options
@@ -9,30 +9,30 @@
*
********************************************************************************/
#ifndef AIDGE_QUANTIZATION_QUANTIZATION_QAT_LSQ_H_
#define AIDGE_QUANTIZATION_QUANTIZATION_QAT_LSQ_H_
#include
<cstddef>
// std::size_t
#include
<memory>
#include
"aidge/data/Tensor.hpp"
#include
"aidge/graph/GraphView.hpp"
namespace
Aidge
{
namespace
QuantLSQ
{
/**
* @brief Given a GraphView with parameters properly initialized, insert
* the LSQ quantizer nodes, and setup the adjustment their step-sizes.
* @param graphView The GraphView containing the network to quantize.
* @param nbBits Number of quantization bits.
*/
void
setupQuantizers
(
std
::
shared_ptr
<
GraphView
>
graphView
,
size_t
nbBits
);
}
// namespace QuantLSQ
}
// namespace Aidge
#endif
/* AIDGE_QUANTIZATION_QUANTIZATION_QAT_LSQ_H_ */
#ifndef AIDGE_QUANTIZATION_QUANTIZATION_QAT_LSQ_H_
#define AIDGE_QUANTIZATION_QUANTIZATION_QAT_LSQ_H_
#include
<cstddef>
// std::size_t
#include
<memory>
#include
"aidge/data/Tensor.hpp"
#include
"aidge/graph/GraphView.hpp"
namespace
Aidge
{
namespace
QuantLSQ
{
/**
* @brief Given a GraphView with parameters properly initialized, insert
* the LSQ quantizer nodes, and setup the adjustment their step-sizes.
* @param graphView The GraphView containing the network to quantize.
* @param nbBits Number of quantization bits.
*/
void
setupQuantizers
(
std
::
shared_ptr
<
GraphView
>
graphView
,
size_t
nbBits
);
}
// namespace QuantLSQ
}
// namespace Aidge
#endif
/* AIDGE_QUANTIZATION_QUANTIZATION_QAT_LSQ_H_ */
\ No newline at end of file
Loading