You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Sep 4, 2021. It is now read-only.
Hi HU,
I notices that the is_training parameter of batch_norm layers(tf.contrib.layers.batch_norm) in your project didn't set to False during the inference period.
But according to the helper document of TensorFlow. this parameter should be set to False during the inference time. https://www.tensorflow.org/api_docs/python/tf/contrib/layers/batch_norm
The text was updated successfully, but these errors were encountered:
Thanks! You are absolutely right! However, in practice, it makes little
difference with one single pass on the test data, so it wasn't set only for
simplicity of the demo. This should be updated as you suggested.
label-reg/labelreg/layers.py
Line 40 in 3fe086f
Hi HU,
I notices that the is_training parameter of batch_norm layers(tf.contrib.layers.batch_norm) in your project didn't set to False during the inference period.
But according to the helper document of TensorFlow. this parameter should be set to False during the inference time.
https://www.tensorflow.org/api_docs/python/tf/contrib/layers/batch_norm
The text was updated successfully, but these errors were encountered: