Yang Feng

Are you using tensorflow==1.13.1?

1.12 should be fine. I used some earlier versions in 2018.

How did you solve the problem? Someone else is facing similar issues.

I inspect the rewards in Tensorboard to see whether the training is healthy. The event files are also provided in Google Drive.

Could you first try to reproduce the results in table 1?

The difference lays in the processing. You need to generate a new word_count file and change the subsequent files.

You don't need glove_vocab.pkl in the unpaired setting. Just use all the words appearing more than four times in MSCOCO training set.

@hugddygff I have not tried to train the model you mentioned. I will train one a few months later and share the results.

In fact, the hyperparameters reported in the paper are the same for both datasets. I will provide the input files and checkpoints for MSCOCO later.

@HYPJUDY I used 4 GPUs. I think using batch_size=512 and lr=1e-3 should produce similar results. The second results you posted is good enough to me. The current eval_all.py supports multi-gpu....