Pengyi Li

question about the bleu and meteor

2

def compute_score(self, gts, res): assert(gts.keys() == res.keys()) imgIds = gts.keys() bleu_scorer = BleuScorer(n=self._n) for id in imgIds: hypo = res[id] ref = gts[id] # Sanity check. assert(type(hypo) is list) assert(len(hypo)...

Thank you very much for your project, which is very useful for me, but I have a few doubts. In the original text, the modified structure of LSTM is only...

Now the code generates negative samples in advance every time, and then shuffles the order, and then randomly selects from the set of positive and negative samples for training. If...

num_env problem

1

Hello, I have read the code carefully, and I have some doubts about num_env. 1: If this parameter equal to 4, is it equivalent to training four models? Or is...

Word embedding problems

6

I carefully read the code, I found the word embedding is only used to calculate the adjacency matrix, each epoch will calculate all the results,every time the input is always...

test data and mini-batch question

29

I found that the test data was also calculated into the adjacency matrix in the preprocessing stage, so if I have a sentence that does not appear in the data...

I went through the code and found a problem I didn't understand.  I think of p_reg as a regular term, and the regular term as a constraint on **the...

the 284~285 lines in the Real_dataset train.py why a pretraining process in adv process in realdata？

SeqAggregator

1

Hi ，I have encountered some troubles. I did not find a specific description of the LSTM part in the paper, so I have several problems： `（1）：`initial_state = self.cell.zero_state(batch_size, tf.float32) used...