diff options
author | 2016-10-25 16:08:15 -0800 | |
---|---|---|
committer | 2016-10-25 17:19:00 -0700 | |
commit | df99c74678ed3bde55062860397b0a8c5cea9f70 (patch) | |
tree | 2f1bad33d9393caea40374c4ec5b4ee0f8fb6534 | |
parent | ed4304c74964ff8cb5ad431934159d97f32f8f69 (diff) |
Change callers of tf.image.per_image_whitening() to use tf.image.per_image_standardization(). Once these changes are submitted, per_image_whitening() can be removed.
Change: 137221877
-rw-r--r-- | tensorflow/g3doc/tutorials/deep_cnn/index.md | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/tensorflow/g3doc/tutorials/deep_cnn/index.md b/tensorflow/g3doc/tutorials/deep_cnn/index.md index 89ba53ac6f..a5302df914 100644 --- a/tensorflow/g3doc/tutorials/deep_cnn/index.md +++ b/tensorflow/g3doc/tutorials/deep_cnn/index.md @@ -122,7 +122,7 @@ The images are processed as follows: * They are cropped to 24 x 24 pixels, centrally for evaluation or [randomly](../../api_docs/python/constant_op.md#random_crop) for training. -* They are [approximately whitened](../../api_docs/python/image.md#per_image_whitening) +* They are [approximately whitened](../../api_docs/python/image.md#per_image_standardization) to make the model insensitive to dynamic range. For training, we additionally apply a series of random distortions to |