-
1. Is this model fixed? Because when the training of this model is finished, users can only change the output by changing the "start token"?
2. What if I want to generate something else?
3. Compare…
-
现在vid2vid可以从视频生成视频，下一步是从视频生成速度的序列，采用seqgan https://github.com/LantaoYu/SeqGAN 类似方式进行从视频预测速度的功能。现在cnn网络后面增加了rnn网络进行序列的预测，但是判别器等优化还不完善。
训练数据可以是torcs的运行视频和运行速度的参数，后续就可以吧视频应用与动作的学习了，使用生成模型的方式进行动作的学习（pix…
-
Generative adversarial networks description
mhrmm updated
4 years ago
-
I checked files are being produced by the name of samples_MLE in sample folder but they consist of numbers. I guess they are the tokens of the individual word, if this is the case can you tell me how …
ghost updated
3 years ago
-
NLG, the other end of NLP, is important in many fields where AI is being applied. Please include the latest NLG research as well as imo it would be very helpful.
-
Regarding the synthetic data experiment, the nll-test metric is computed with the gen_data_loader (training data) so nll-test is actually nll-train (useless metric). Highly misleading.
Also, even i…
-
Hi,
I have been feeding a very simple dataset composed of consecutive ints to all GANs available in this library. The data is generated as follows, and stored in the oracle file.
```
X = [list(rang…
-
/usr/bin/python3.5 /home/scrooge/chatbot/seqGanChatbot/execute.py
/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/dtypes.py:493: FutureWarning: Passing (type, 1) or '1type' as a sy…
-
### Metadata
Authors: Stanislau Semeniuta, Aliaksei Severyn, Sylvain Gelly
Organization: Google AI
Conference: NIPS 2018
Paper: https://arxiv.org/pdf/1806.04936.pdf
-
I have trained the code in /Image CoCo ，during the training , I found there always be some 'tail tokens' after the period and some paddings, even the 451th epoch still has this kind of problem.
Like …