Skip to content

Per channel fq2i #8

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 13 commits into from
Aug 31, 2021
Merged

Per channel fq2i #8

Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
b6feddb
WIP support per-channel quantization
Aug 23, 2021
15f105b
more WIP
Aug 23, 2021
edb62dc
More WIP
Aug 25, 2021
d438efc
fix issue with per-channel bias_add
Aug 25, 2021
1d659e0
Fix fake quantize tests (#4)
Aug 25, 2021
d94f647
Add Relu
Aug 25, 2021
a0c9b05
One more little one (#5)
Aug 25, 2021
84cf67d
Non-working Per-channel Dense
Aug 28, 2021
b4f79df
Fix legalization for non spatial operators. (#6)
Aug 30, 2021
5d73612
fix axis normalization
Aug 30, 2021
62ac8bc
Fix bug in requantize dimension expansion.
Aug 31, 2021
38b5a82
Format.
Aug 31, 2021
0dc5549
Merge branch 'per_channel_fq2i' into per_channel_fq2i
Aug 31, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion src/relay/qnn/op/requantize.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,11 +139,13 @@ Expr RequantizeLower(const Expr& input_tensor, const Expr& input_scale,
auto zero_scalar = MakeConstantScalar(DataType::Int(32), 0);
if (!IsEqualScalar(input_zero_point, zero_scalar)) {
// Broadcast input zero point if needed.
int rank = static_cast<int>(input_shape.size());
int axis = (param->axis < 0) ? ((rank > 0) ? rank + param->axis : 0) : param->axis;
Expr input_zero_broadcast = ExpandBiasToMatchAxis(Reshape(input_zero_point,
{
-1,
}),
input_shape.size(), {param->axis});
rank, {axis});
tensor = Subtract(tensor, Cast(input_zero_broadcast, DataType::Int(32)));
}

Expand Down