update global_step

[raytroop]

Oreilly-Learning-TensorFlow/06__word_embeddings_and_rnns/word2vec.py

Line 104 in 826f01d

train_step = tf.train.GradientDescentOptimizer(learningRate).minimize(loss)

argument 'global_step = global_step' should be inserted at 'minimize()'.
Only in this way, global_step increments one by one every training iteration and weights decay

# Learning rate decay
global_step = tf.Variable(0, trainable=False)
learningRate = tf.train.exponential_decay(learning_rate=0.1,
                                          global_step=global_step,
                                          decay_steps=1000,
                                          decay_rate=0.95,
                                          staircase=True)
train_step = tf.train.GradientDescentOptimizer(learningRate).minimize(loss, global_step= global_step)