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

Small change of comment per reviewer's note.

Browse Source 
Change-Id: I1233b95282befebfa0e6c06173f5e928aef60b22
This commit is contained in:
Elena Zhelezina 2020-06-09 22:35:57 +01:00
parent 84afc268a7
commit dcfc2175c7
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/lite/python/convert.py
View File

@ -98,9 +98,9 @@ class OpsSet(enum.Enum):
# int16 activations and int64 bias.
# Specifying this will throw an error for operations that do not yet have
# quantized implementations.
# This quantization mode should be used in models for super-resolution,
# This quantization mode may be used in models for super-resolution,
# audio signal processing or image de-noising. It improves accuracy
# significantly, but only slightly increases the model size.
# significantly, but only slightly increases the model size.
# WARNING: These ops are currently experimental and have not yet been finalized.
# They are only compatible with CPU execution, and have not been optimized for production.
EXPERIMENTAL_TFLITE_BUILTINS_ACTIVATIONS_INT16_WEIGHTS_INT8 = \