zjulearning / redr Goto Github PK

When I generated the file " pred.txt"，why the file "pred.txt" is empty, did not see the generated problem？

Hi~ @ByronPan
Thx about the interesting work~
Is there any plan for opening the trained model about the ReDR?

Hello, @ByronPan . I tried your code and got a pred.txt, and also get similar results about the diversity. However, I only got BLEU = 3.93, 38.4/6.9/2.6/1.3 (BP=0.716, ratio=0.750, hyp_len=38839, ref_len=51813) and for ROUGE ROUGE(1/2/3/L/SU4): 19.61/5.65/1.85/19.32/8.48. I think you said use a smooth BLEU so how could I got this script? And as for the rouge, could you please show more detail about the test_rouge script.
Thanks a lot.

I run your code in google colab, but I meet a crucial error and I can't deal with it by google, maybe you can help me, thanks.
ps: all packages you mention is installed.

[2019-09-14 02:57:15,574 INFO]  * src vocab size = 49766
[2019-09-14 02:57:15,574 INFO]  * history vocab size = 49766
[2019-09-14 02:57:15,574 INFO]  * tgt vocab size = 49766
[2019-09-14 02:57:15,574 INFO] Building model...
Traceback (most recent call last):
  File "/content/drive/My Drive/ReDR/train.py", line 109, in <module>
    main(opt)
  File "/content/drive/My Drive/ReDR/train.py", line 41, in main
    single_main(opt, -1)
  File "/content/drive/My Drive/ReDR/onmt/train_single.py", line 86, in main
    model = build_model(model_opt, opt, fields, checkpoint)
  File "/content/drive/My Drive/ReDR/onmt/model_builder.py", line 235, in build_model
    vocab = torch.load(opt.drqa_vocab_path)
  File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 387, in load
    return _load(f, map_location, pickle_module, **pickle_load_args)
  File "/usr/local/lib/python3.6/dist-packages/torch/serialization.py", line 574, in _load
    result = unpickler.load()
AttributeError: Can't get attribute '_default_unk_index' on <module 'torchtext.vocab' from '/usr/local/lib/python3.6/dist-packages/torchtext/vocab.py'>

as above

When I was running the train.py, the following error occurs.

(base) PS D:\ReDR> python train.py -data data/coqa-cqg -save_model out_model/
[2019-08-20 23:20:28,297 INFO] * src vocab size = 49766
[2019-08-20 23:20:28,298 INFO] * history vocab size = 49766
[2019-08-20 23:20:28,298 INFO] * tgt vocab size = 49766
[2019-08-20 23:20:28,299 INFO] Building model...
Traceback (most recent call last):
File "train.py", line 109, in
main(opt)
File "train.py", line 41, in main
single_main(opt, -1)
File "D:\ReDR\onmt\train_single.py", line 86, in main
model = build_model(model_opt, opt, fields, checkpoint)
File "D:\ReDR\onmt\model_builder.py", line 235, in build_model
vocab = torch.load(opt.drqa_vocab_path)
File "D:\anaconda\lib\site-packages\torch\serialization.py", line 366, in load
f = open(f, 'rb')
FileNotFoundError: [Errno 2] No such file or directory: 'drqa_param\vocab.pt'