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

Add bug for TODO in concatenation.

Browse Source 
First TODO is removed due to duplicated code in optimized is already removed before.

PiperOrigin-RevId: 344350119
Change-Id: I8ea87cae8a3c605fdb7ab733b52cd97c090834c2
This commit is contained in:
Jaehong Kim 2020-11-25 19:09:51 -08:00 committed by TensorFlower Gardener
parent 4f8460e92f
commit 5d5e0037ec
1 changed files with 1 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
tensorflow/lite/kernels/internal/reference/concatenation.h
View File

@ -68,8 +68,7 @@ inline void Concatenation(const ConcatenationParams& params,
}
}
// TODO(prabhumk): This is the same as the optimized implementation.
// TODO(prabhumk): The quantized implementation of concatentation isn't fully
// TODO(b/174275780): The quantized implementation of concatentation isn't fully
// quantized as it takes scale as a floating point value. This should be fixed
// when optimizng this routine further.
inline void ConcatenationWithScaling(const ConcatenationParams& params,