High loss for Text CNN in Stage 1 and COCO dataset questions

Hey layumi, I am trying to replicate your results for mscoco in tensorflow I had some questions about processing data and loss:

1. At the end of Stage 1 my text CNN ('objective_txt') loss is high around 5.5, what was the loss you got at the end of Stage 1?

2. in dataset/MSCOCO-prepare/prepare_wordcnn_feature2.m you create
   wordcnn = zeros(32,611765,'int16')
   then loop over all the captions in MSCOCO, but there is 616,767 captions in MSCOCO, so what's the reason of this 5002 difference? it throws an out of range error when I implemented it in tensorflow because there is more captions than the rows/columns in the matrix wordcnn created

3. coco_dictionary.mat dimensions is 29972 in your code but my dimensions are different? I wonder if this is the reason why the loss is high or it might be because tensorflow uses a different random generator than matlab, if you have any suggestion on this that would be great

Thank you!

Start with dataset/MSCOCO-prepare/prepare_wordcnn_feature2.m and the Stage 1 objective_txt loss; compare the caption count, wordcnn dimensions, and coco_dictionary.mat dimensions against the TensorFlow reproduction. Done means explaining the 5002-caption discrepancy and identifying whether the loss difference comes from data dimensions or random initialization.