tooder
tooder
when I use the coco-caption evaluation code, the bleu1-4 scores are normal, but the script always reports some errors on the meteor . how can I deal with it? valid_score...
Hi, I am reading your excellent code, but find no beam search during caption generation as the source code in https://github.com/kelvinxu/arctic-captions, is there any reason ?
In this line, https://github.com/eladhoffer/seq2seq.pytorch/blob/348276b2fcc5a60352b3dccaae7102666dbbd4ac/seq2seq/tools/beam_search.py#L216, the decrease of num_hyp will increase the value of k, which then leads to the out-of-bounds for the words[idx][k], I don't know why you use num_hyp?
As you said in the paper, there is a description on stopping criteria. "For all our models, we stop training after K consecutive epochs with descending summarization F-score on the...
When i run the script create_dataset.sh in /exp/ted, the script produces the error : Please set SCRIPTS variable correctly to point to Moses scripts. So the Moses needs to be...
Hello,I run your code as you describe.But when I run tests.py, I find that the terminal print the information 'too many indices for array,====== [ ERROR: Caffe was not found....
Can you release your C3D 1.1 sports-1m model (conv3d_deepnetA_sport1m_iter_1900000), and I need to use the C3D to retrain my own network.