experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

minor typo fix: is_sign -> is_signed

Browse Source 
The parameter is usually named is_signed, and its usages also write it as /*is_signed=*/. Changing this resolves linter warnings.

PiperOrigin-RevId: 344725141
Change-Id: I8e1a7939417ee88a1a9296eb86547c029c4fbb22
This commit is contained in:
Taehee Jeong 2020-11-29 16:29:15 -08:00 committed by TensorFlower Gardener
parent 68d2777a17
commit 4d1142b04b
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
tensorflow/compiler/mlir/lite/quantization/quantization_utils.h
View File

@ -485,7 +485,7 @@ ElementsAttr Quantize(Attribute real_value, Type tensor_type);
// are adjusted to be symmetric if `symmetric` flag is set to True. And
// `symmetric` can only be set to true when it is signed and narrow_range.
Type GetUniformQuantizedTypeForWeight(ElementsAttr attr, bool symmetric,
unsigned num_bits, bool is_sign,
unsigned num_bits, bool is_signed,
bool narrow_range);
// Returns the per channel quantized type for an element attribute.
@ -494,7 +494,7 @@ Type GetUniformQuantizedTypeForWeight(ElementsAttr attr, bool symmetric,
// be set to true when it is signed and narrow_range.
Type GetUniformQuantizedPerAxisTypeForWeight(ElementsAttr attr, int quant_dim,
bool symmetric, unsigned num_bits,
bool is_sign, bool narrow_range);
bool is_signed, bool narrow_range);
// Returns the quantized type of a bias input, given the quantized types of
// other operands which are multiply-accumulated (the bias is added to the