seqgan-text-tensorflow
seqgan-text-tensorflow copied to clipboard
codekansas
:dango: SeqGAN implementation for generating text using an RNN.
# Keeps track of the "expected reward" at each timestep. expected_reward = tf.Variable(tf.zeros((SEQUENCE_MAXLEN,))) reward = d_preds - expected_reward[:tf.shape(d_preds)[1]] # minus zeros?? mean_reward = tf.reduce_mean(reward) # This variable is updated to...
In the original paper, they used rollout to get the intermediate rewards during sequence generation, in this codes, it seems the generator only gets rewards when the whole sequence is...
Metadata
Owner
Metadata
:dango: SeqGAN implementation for generating text using an RNN.