-
How to use other data? How to create vocab.txt file?
The program crashed / stalled my PC after about 8 hours creating the training. How ever it was using CPU, so I tried to create a smaller data …
-
Hey @CR-Gjx Thanks for providing this open source code. Very helpful to study and I love the idea of hierarchical reinforcement learning.
In the recent AlphaGo Zero paper and [Thinking Fast and Slo…
-
面白そうなので読み始めた。強化学習、よく知らないので楽しみ。
-
Hi,
I was trying to write a function for computing reinforce loss (as below) when I realized you have this [here](https://github.com/asyml/texar/blob/caa931a276ec215ef85bb1cfc1d486cdf877b1fd/texar/…
-
how i can run my mode after training it on my data
hmqt updated
5 months ago
-
- https://arxiv.org/abs/1912.00609
- 2019 NLPCC
本研究では，Generative Adversarial Networks (GAN)に基づく自動プログラミング手法であるGANCoderを提案する．
GANは，与えられた自然言語の発話を条件として，同一の機能的かつ論理的なプログラミング言語コードを生成することができる．
生成器と識別器の…
e4exp updated
3 years ago
-
Dear yuanyuan, I am studying this paper of yours recently. In the baselines, I see that you run the SeqGAN to generate the active sequence. I would very sincerely like to know, when you generate data …
-
您好，相较于原版，你的这个版本简直太清晰了！点赞👍
我有一个关于generator的loss function的问题，在原版的SeqGAN里有 [repo](https://github.com/LantaoYu/SeqGAN/issues/33)
我看到你的代码里也是取的正确类别的accuracy：
`reward_allseq = np.concatenate((reward_roll…
-
你好，我使用真实的语料集作为训练数据，但是发现生成文本的质量很不好，请问有什么在训练上的建议嘛？谢谢~
wyxcc updated
11 months ago
-
您好，有些疑问，生成模型中def build_sample_network(self):函数的输入是什么？不太理解函数里面的sample_word？麻烦您讲讲
ZNZHL updated
11 months ago