ada-dl

BLEU-4 score @ beam size of 5 is 0.0606. result on author's model.

8

Hi I have used the authors' WORDMAP and checkpoint files but after running the eval.py on these files with correct filepaths, I received a BLEU-4 score @ beam size of...

always returns the same caption

3

I used the pretrained checkpoint and wordmap, when I ran it through different images, it always returns the same caption? Why could this be? Could you please help me?