Show-Attend-and-Tell
Show-Attend-and-Tell copied to clipboard
A PyTorch implementation of the paper Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Hello @AaronCCWong , Thanks for the code. It was a great help. I saw you have implemented the training and validation scores. But I want to run testing on Flickr8k...
I have been trying for a while using VGG for training. But the generated captions is not right! 
First of all, thank you for your great work When I finish training and try to generate caption, there are something issue with the result. `AttributeError: 'Tensor' object has no...
Hello, I have some new ideas. I wonder if I could ask for some advice?
`RuntimeError: shape '[14, 14]' is invalid for input of size 49` is the error thrown. Naively reshaping the alphas to fit the input size causes weird cropping issues in the...