Skip to content

Add check that output is quantized. #1830

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 7 commits into from
Mar 27, 2023
Merged

Add check that output is quantized. #1830

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
6386533
Add check that output is quantized.
tanmaydas82 Mar 15, 2023
b379752
Merge branch 'main' into add-check
tanmaydas82 Mar 15, 2023
e98aa5e
Add the check for int8/int16 output type.
tanmaydas82 Mar 21, 2023
8f057ca
Merge branch 'add-check' of github.com:tanmaydas82/tflite-micro into …
tanmaydas82 Mar 21, 2023
61d30cb
Thank you for suggestion! Moved the check closer to where it is used.
tanmaydas82 Mar 24, 2023
858431a
Remove comment.
tanmaydas82 Mar 26, 2023
d767944
Merge branch 'main' into add-check
advaitjain Mar 27, 2023
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
2 changes: 2 additions & 0 deletions tensorflow/lite/micro/kernels/add_common.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,8 @@ TfLiteStatus CalculateOpDataAdd(TfLiteContext* context, TfLiteAddParams* params,
data->requires_broadcast = !HaveSameShapes(input1, input2);

if (output->type == kTfLiteInt8 || output->type == kTfLiteInt16) {
TFLITE_CHECK_NE(output->quantization.type, kTfLiteNoQuantization);

// 8bit -> 8bit general quantized path, with general rescalings
data->input1_offset = -input1->params.zero_point;
data->input2_offset = -input2->params.zero_point;
Expand Down