Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
gaoqiong
MIGraphX
Commits
9b9869c4
Commit
9b9869c4
authored
Sep 04, 2019
by
Shucai Xiao
Browse files
clang format
parent
95827f48
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
6 additions
and
6 deletions
+6
-6
src/quantization.cpp
src/quantization.cpp
+6
-6
No files found.
src/quantization.cpp
View file @
9b9869c4
...
@@ -258,12 +258,12 @@ static void ins_quantize_int8(program& prog,
...
@@ -258,12 +258,12 @@ static void ins_quantize_int8(program& prog,
{
{
// Current MIOpen convolution does not support alpha and beta,
// Current MIOpen convolution does not support alpha and beta,
// so we need a separate multiply to adjust the output
// so we need a separate multiply to adjust the output
auto
conv_op
=
any_cast
<
op
::
convolution
>
(
ins
->
get_operator
());
auto
conv_op
=
any_cast
<
op
::
convolution
>
(
ins
->
get_operator
());
auto
padding
=
conv_op
.
padding
;
auto
padding
=
conv_op
.
padding
;
auto
stride
=
conv_op
.
stride
;
auto
stride
=
conv_op
.
stride
;
auto
dilation
=
conv_op
.
dilation
;
auto
dilation
=
conv_op
.
dilation
;
auto
padding_mode
=
conv_op
.
padding_mode
;
auto
padding_mode
=
conv_op
.
padding_mode
;
auto
group
=
conv_op
.
group
;
auto
group
=
conv_op
.
group
;
auto
adjust_factor
=
1.0
f
/
(
ins_quant_params
[
0
].
first
*
ins_quant_params
[
1
].
first
);
auto
adjust_factor
=
1.0
f
/
(
ins_quant_params
[
0
].
first
*
ins_quant_params
[
1
].
first
);
auto
quant_conv
=
prog
.
insert_instruction
(
auto
quant_conv
=
prog
.
insert_instruction
(
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment