Mason Wang

About pretrained models to generate 36 per image feature

11

Thank you for your excellent work! I have a question. I'm using this bottom up attention method to generate 36/image feature. In your README, you wrote that: > To recreate...

Hi, there, I am struggling with what you send into the caption model. From what I read in your paper, I suppose you just used 2048-dimension features? Did you use...

Error when use pretrained-glove embeddings

1

Hi Ruotian Luo, thank you for your excellent codes. But I have a problem. I want to use pretrained-glove vectors as initial embeddings and set input_encoding_size=300(which is glove vector dim),...