diff options
| author |  Akshay Modi <nareshmodi@google.com> | 2018-06-18 21:00:34 -0700 |
|---|---|---|
| committer |  TensorFlower Gardener <gardener@tensorflow.org> | 2018-06-18 21:04:00 -0700 |
| commit | 6070ae0e148f50dbc8f36e1654f0a3f53b8b067e (patch) | |
| tree | 165e4c050220180a76512e304b70eee0cd02a2db /tensorflow/contrib/quantize | |
| parent | 60b78d6152e6f8d985f3086930ff986c140c36bf (diff) | |
Merge changes from github.
PiperOrigin-RevId: 201110240
Diffstat (limited to 'tensorflow/contrib/quantize')
| -rw-r--r-- | tensorflow/contrib/quantize/README.md | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/tensorflow/contrib/quantize/README.md b/tensorflow/contrib/quantize/README.md index c83623ec94..27a933c0f9 100644 --- a/tensorflow/contrib/quantize/README.md +++ b/tensorflow/contrib/quantize/README.md @@ -6,7 +6,7 @@ inference. The details of the transformation implemented in this package is described here [1]. This is done using the -[fake quantization op](https://www.tensorflow.org/versions/r0.12/api_docs/python/array_ops/fake_quantization). +[fake quantization op](https://www.tensorflow.org/api_guides/python/array_ops#Fake_quantization). Literature has shown that fixed point networks provide comparable performance to floating point networks [2]. This is achieved by modeling the quantization |