According to the paper, rollout policy is the same with generator policy. So self.Wi = self.lstm.Wi, but in the code, here update parameters of rollout policy in a different way. Can you please explain why? Thank you very much @LantaoYu @wnzhang

Hello,

i don't understand the combination of reward and loss function. The label which are given to the discriminator are defined as followed:

positive_labels = [[0, 1] for _ in positive_examples] negative_labels = [[1, 0] for _ in negative_examples]

The reward then is always the second, positive label:

ypred_for_auc = sess.run(discriminator.ypred_for_auc, feed) ypred = np.array([item[1] for item in ypred_for_auc])

So if the reward gets larger, the samples are identified as real class. But then in the loss function of the generator, the reward is multiplied to the loss:

self.g_loss = -tf.reduce_sum( tf.reduce_sum( tf.one_hot(tf.to_int32(tf.reshape(self.x, [-1])), self.num_emb, 1.0, 0.0) * tf.log( tf.clip_by_value(tf.reshape(self.g_predictions, [-1, self.num_emb]), 1e-20, 1.0) ), 1) * tf.reshape(self.rewards, [-1]) )

I don't understand that, since the loss gets minimized, the rewards will be minimized too. So shouldn't be taken the label item[0] for ypred?

I noticed that there is a class named TARGET_LSTM which uses the predefined parameters from target_params.pkl. My question is that if I use my own data and different global parameters, such as EMB_DIM, HIDDEN_DIM, SEQ_LENGTH.., how to obtain the parameters for TARGET_LSTM? What is the usage of TARGET_LSTM?

hi, I am trying run this repo under pyhton3, original implements using python2, code is fine but the target_params.pkl can not open, do you have an alternate version of that file which can open using python3?

Hi there, I got a question about the evaluation on text generation. In your AAAI2017 paper, you have mentioned that for the Chinese poem generation you "use the whole test set as the references" to caculate the BLEU score. What is the meaning of "references"? How to use the test samples as the "positive examples" as you mentioned? Are all the test samples loaded to the model as the input? And then the BLEU scores are calculated based on the corresponding output from the model? I would appreciate if you could explain more details about the evaluation procedure. Thanks in advance!

Hi.

I would like to start generating models from my own data but I'm unable to get the code working. Running ubuntu 16 & 14 64 bit and current tensorflow 12.1 on nvidia gpu. I've checked several forums and there are similar issues with tensorflow 12.

If this cannot be fixed is it possible to post your previous code that works on earlier versions of tensorflow?

Thanks

Traceback (most recent call last): File "pretrain_experiment.py", line 123, in main() File "pretrain_experiment.py", line 93, in main sess.run(tf.global_variables_initializer) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 766, in run run_metadata_ptr) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 951, in _run fetch_handler = _FetchHandler(self._graph, fetches, feed_dict_string) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 407, in init self._fetch_mapper = _FetchMapper.for_fetch(fetches) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 238, in for_fetch return _ElementFetchMapper(fetches, contraction_fn) File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 271, in init % (fetch, type(fetch), str(e))) TypeError: Fetch argument <function global_variables_initializer at 0x7fb92909bb18> has invalid type <type 'function'>, must be a string or Tensor. (Can not convert a function into a Tensor or Operation.)

Similar error when running sequence_gan.py

In this loop:

https://github.com/LantaoYu/SeqGAN/blob/5f2c0a5c978826febe94864da69c77c00f237f81/rollout.py#L79

This is N Time Monte Carlo sampling with n = 16 in the code. But how are the different samples generated? given_num represents how many tokens to use from the input, and irepresents the i'th sample. Why are the samples different for different values of i? Is the rollout network being updated somewhere within call to get_reward and I'm missing it? I also don't see where the randomness is coming in for the Monte Carlo estimation of the partial sequence reward.

From my examination of the code, the network doesn't get updated and the session parameters are the same so I'm not sure how different samples are being generated.

Can someone help me understand how a) different samples are being generated, b) where is the randomness coming from, c) if the rollout network has the same parameters as the Generator network, how is it generating different samples than the generator?

Any help is greatly appreciated! Thank you for providing this code it has been very helpful to me.

Hi, I have read your code in generator.py (line 106-113), # Unsupervised Training self.g_loss = -tf.reduce_sum( tf.reduce_sum( tf.one_hot(tf.to_int32(tf.reshape(self.x, [-1])), self.num_emb, 1.0, 0.0) * tf.log( tf.clip_by_value(tf.reshape(self.g_predictions, [-1, self.num_emb]), 1e-20, 1.0) ), 1) * tf.reshape(self.rewards, [-1]) ) I find the the variable (self.g_predictions and self.x) is the same as the variable in self.pretrain_loss, but since this is for the Unsupervised Training, the variable self.g_predictions should be replaced with the variable ( line 50, tf.nn.softmax(o_t) ). After all, the line 47-56 do not use the supervised information (self.x). Is there any reason ?

Can you provide any guidance on how to train and generate from my own data? I would like to try SeqGAN with various English poetry and prose, but I am not sure how to change this code to train on my own data and then generate new writing.

Hey - looks like you heavily based this code on my implementation at https://github.com/ofirnachum/sequence_gan

It's nice to see that you got it working on bigger problems, but please cite/reference my work.

It seems that according to the generator, at the beginning of unrolling, the input is START_TOKEN. And seems that there's no source of randomness to feed into the network, so shouldn't the trained network be deterministic?

Has anyone tried to implement this code? I have generated a lot of combinations of numbers, such as ‘7811 3499 2314’. I don’t know the meaning of these numbers. Who can give me an answer?

I am running the sequence_gan.py file, the pre-training has been started. Since it is running on Colab, it will stop after a specific time. What's the procedure to resume it after the next time starts on Colab?

I run the code and some text files are mentioned in the code file sequence_gan.py such as positive_file = 'save/real_data.txt' and negative_file = 'save/generator_sample.txt' and eval_file = 'save/eval_file.txt' which I do not know where those files came from because there are no such files in the save folder. please help me

Hi, I am very interested in your work. About 'g, d and k', I think 'g' means one epoch in the paper. But in code, I think it may be one batch. So, could u help me with it ? Thanks a lot.