pytorch implementation of video captioning
when I use the train.py , the error raised....TypeError: gru() received an invalid combination of arguments
The reward calculated using the ciderD of pyciderevalCap is 0
About the performance
size mismatch
ptbtokenizer.py
'DecoderRNN' object has no attribute 'sample_beam'
Source Data download
preprocess videos and labels
Which research paper did you used in this implementation?
What is the paper corresponding to this code?