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

Addressed reviewer's comments.

Browse Source 
Change-Id: I27fc31bbc32597d5e8f0e50fc78d2f5602dfb9d0
This commit is contained in:
Elena Zhelezina 2020-09-14 10:34:28 +01:00
parent 354111f60d
commit 26bf5ac3e0
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
tensorflow/lite/g3doc/performance/model_optimization.md
View File

@ -129,7 +129,7 @@ the numbers here:
[Quantization with int16 activations](https://www.tensorflow.org/model_optimization/guide/quantization/post_training) is a full integer quantization scheme with activations in int16 and weights in int8. This mode can improve accuracy of the quantized model in comparison to the full integer quantization scheme with both activations and weights in int8 keeping a similar model size. It is recommended when activations are sensitive to the quantization.
Currently only non-optimized reference kernel implementation is available in TFLite so that by default the performance will be slow compared to int8 kernels. Full advantages of this mode can currently be accessed via specialised hardware, or custom software.
<i>NOTE:</i> Currently only non-optimized reference kernel implementations are available in TFLite for this quantization scheme, so by default the performance will be slow compared to int8 kernels. Full advantages of this mode can currently be accessed via specialised hardware, or custom software.
Below are the accuracy results for some models that benefit from this mode.
<figure>