The codes of paper "Long Text Generation via Adversarial Training with Leaked Information" on AAAI 2018. Text generation using GAN and Hierarchical Reinforcement Learning.
How many batches are we supposed to go through?
I'm started adversarial training and I'm batch 405 for target length 20. But on your github page, the maximum number of batches is 91. I cloned everything you had and ran it accordingly. Am I doing something wrong or is this expected?
How many batches are we supposed to go through? I'm started adversarial training and I'm batch 405 for target length 20. But on your github page, the maximum number of batches is 91. I cloned everything you had and ran it accordingly. Am I doing something wrong or is this expected?
Thanks