homelifes

thanks all! @luo3300612 may I know if you've changed any thing or any hyperparameters in the code to achieve this score?

actually @ruotianluo I set the patience to 1. meaning if there is no improvement for one epoch, I decay the learning rate by half (multiply by 0.5). Is that fine?

but actually when the learning rate decayed, it improved for one epoch directly, and then stopped to improve. I will re-try it with patience 10

@sgrvinod im waiting for you reply

Hi @arjung128, Have you made it work? I am curious to know the results for image paragraph captioning using a transformer, as a transformer is suited for long sequences such...

Thank you for your answer.

@ruotianluo i also want to ask. 1- Is the top-down uploaded model trained with cider or cross entropy? 2-And did you use bottom up or resent features for the att2in2...

@ruotianluo waiting for your kind reply.

@zplizzi I do get the point that we are using the dropped version in the forward pass, but when backpropagating we are updating the raw weights. However, in the forward...

@ruotianluo Thanks for your reply. So is the `att_feats` extracted from the `prepro_feats.py` file, which is of size `(7,7,2048)`? And what about `p_att_feats`? May you tell me from where we...