ValueError: could not convert string to float: 'Error: specify Meteor stats'

[ivy94419]

I used Python3.5 and Pytorch0.4 in ubuntu, I got this errors:

init COCO-EVAL scorer
Traceback (most recent call last):
  File "eval.py", line 122, in <module>
    main(opt)
  File "eval.py", line 91, in main
    test(model, crit, dataset, dataset.get_vocab(), opt)
  File "eval.py", line 57, in test
    valid_score = scorer.score(gts, samples, samples.keys())
  File "/host/xxx/video_caption/video_caption_pytorch/misc/cocoeval.py", line 88, in score
    score, scores = scorer.compute_score(gts, res)
  File "coco-caption/pycocoevalcap/meteor/meteor.py", line 44, in compute_score
    score = float(self.meteor_p.stdout.readline().decode().strip())
ValueError: could not convert string to float: 'Error: specify Meteor stats'

How to deal with it?

[zhjohnchan]

I has faced the same problem as you. I found the data loader was empty when running eval.py because it was empty in [test] of my info.json. My steps to solve this problem are as follows:

1. Download the three json files from baiduyun.
2. Rerun prepro_vocab.py.
3. Retrain model.

[ivy94419]

@zhjohnchan Thank you！

[DogeFlow]

@zhjohnchan Hello, I encountered the same error, but now only two json files can be downloaded. What is the third json file?