RMN

RMN copied to clipboard

text feature processing

1

Sir, can you share the link to process the text features and from which you have generated a caption.pkl file.

DeepaliVerma

https://github.com/tgc1997/RMN/blob/14a9eff9a936030bcea104cb2c65f5378136cd87/train.py#L128 Hi, Ganchao. I found the above judgement may miss some conditions during executing the project. e.g. When the train_batch_size is set to 2 or 3, the step of the...

HXYNODE

a problem about region_feature file

3

the shape of sfeats of msvd_region_feature.h5 is 1970 x 26 x 36 x 5, what's the meaning of the last dimensions?thank you!

pplee2020

How to download the dataset without an account?

4


ydwl-lynn

您好！我想请教一下您这里的POS词性是怎么获得的，我看到只有0，1，2这三种类型，请问他们分别代表什么词性？谢谢！

lalalalala7

qqdrwz0101

When I try to run evaluate.py, I ran into an error. I tried some methods but couldn't solve the problem. I hope I can get your help. 

river-0


monic7

hi, I want to know why you use two similar parameters(opt.hidden_size) here, and I think the last parameter should be opt.att_size. Is it wrong? btw, your job is so awesome...

Dorothylyly

File "/RMN-master/models/allennlp_beamsearch.py", line 257, in search state_tensor.reshape(batch_size, self.beam_size, *last_dims) RuntimeError: gather_out_cuda(): Expected dtype int64 for index

maybekssss