chiphuyen/stanford-tensorflow-tutorials

07_convnet_layers.py self.training should use tf.placeholder

TonyZZX opened this issue · 0 comments

If you use a Python bool, the value of training won't change because you already build the logits before the session and you can't change the graph during the session.
The correct way should use tf.placeholder like this:
self.training = tf.placeholder(tf.bool, name='is_train')
And set sess.run(init, feed_dict={self.is_training: True}) when trainingand sess.run(init, feed_dict={self.is_training: False}) when evalating