Hi, thanks for open-source the code!

However, when I change the 'dec_hidden_size' to 256, an error occurs:

Traceback (most recent call last):
  File "train.py", line 351, in <module>
    train=True)
  File "/search/data3/xxx/py3_pytorch_venv/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/search/data3/xxx/FocusSeq2Seq/models.py", line 272, in forward
    diversity_lambda=diversity_lambda)
  File "/search/data3/xxx/py3_pytorch_venv/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/search/data3/xxx/FocusSeq2Seq/layers/decoder.py", line 296, in forward
    s = self.rnncell(dec_input, s)
  File "/search/data3/xxx/py3_pytorch_venv/lib/python3.7/site-packages/torch/nn/modules/module.py", line 547, in __call__
    result = self.forward(*input, **kwargs)
  File "/search/data3/xxx/py3_pytorch_venv/lib/python3.7/site-packages/torch/nn/modules/rnn.py", line 1015, in forward
    self.check_forward_input(input)
  File "/search/data3/xxx/py3_pytorch_venv/lib/python3.7/site-packages/torch/nn/modules/rnn.py", line 761, in check_forward_input
    input.size(1), self.input_size))
RuntimeError: input has inconsistent input_size: got 812, expected 556

I guess it is because the 'context' doesn't 'bridge' to the right size.
How should I fix it? Thank you so much.

I amfacing this issue while running the train.py command

I am using CUDA=10.0 and GPU= GeForce GTX 1660 Ti

COMMAND : python train.py --task=QG --model=NQG --load_glove=True --feature_rich --data=squad --rnn=GRU --dec_hidden_size=512 --dropout=0.5 --batch_size=64 --eval_batch_size=64 --use_focus=True --n_mixture=3 --decoding=greedy

#==== Weight Initialization ====#

Total Parameters: 12295050

Loaded word embedding!
Traceback (most recent call last):
File "train.py", line 110, in
model.to(device)
File "/home/xxx/FocusSeq2Seq/focus/lib/python3.6/site-packages/torch/nn/modules/module.py", line 386, in to
return self._apply(convert)
File "/home/xxxx/FocusSeq2Seq/focus/lib/python3.6/site-packages/torch/nn/modules/module.py", line 193, in _apply
module._apply(fn)
File "/home/xxxx/FocusSeq2Seq/focus/lib/python3.6/site-packages/torch/nn/modules/module.py", line 193, in _apply
module._apply(fn)
File "/home/xxxx/FocusSeq2Seq/focus/lib/python3.6/site-packages/torch/nn/modules/module.py", line 193, in _apply
module._apply(fn)
[Previous line repeated 1 more time]
File "/home/xxxx/FocusSeq2Seq/focus/lib/python3.6/site-packages/torch/nn/modules/rnn.py", line 127, in _apply
self.flatten_parameters()
File "/home/xxx/FocusSeq2Seq/focus/lib/python3.6/site-packages/torch/nn/modules/rnn.py", line 123, in flatten_parameters
self.batch_first, bool(self.bidirectional))
RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED

Hi
I used conda to install all lib mention in requirement.txt
however, when I try
python train.py --task=QG --model=NQG --load_glove=True --feature_rich --data=squad --rnn=GRU --dec_hidden_size=512 --dropout=0.5 --batch_size=64 --eval_batch_size=64 --use_focus=True --n_mixture=3 --decoding=greedy

I got this result：
Traceback (most recent call last): File "train.py", line 22, in <module> from utils.tensor_utils import repeat File "/home/alznn/focusseq2seq/FocusSeq2Seq/utils/__init__.py", line 1, in <module> from .rouge import * File "/home/alznn/focusseq2seq/FocusSeq2Seq/utils/rouge/__init__.py", line 1, in <module> from .perl_rouge import * File "/home/alznn/focusseq2seq/FocusSeq2Seq/utils/rouge/perl_rouge.py", line 13, in <module> assert os.path.exists(rouge_path) AssertionError
Do anyone have any idea about this error?

\QG_data_loader.py", line 237, in preprocess_single_example
if word in word2id:
NameError: name 'word2id' is not defined

It would be nice if you could help resolve the issue !!

Hello and thank you for the code!

Is there a simple way to perform inference using a trained model?

Here's a mistake

On executing train.py, I am getting the following error:

Epoch [0/20] | Iteration [1345/1346] | NLL Loss : 3.776 | NLL Loss (running avg) : 3.881 | Focus Loss : 0.176 | Time taken: : 11.62
Epoch Done! It took 338.58s
Evaluation start!
/pytorch/aten/src/ATen/native/cuda/LegacyDefinitions.cpp:14: UserWarning: masked_fill_ received a mask with dtype torch.uint8, this behavior is now deprecated,please use a mask with dtype torch.bool instead.
/pytorch/aten/src/ATen/native/cuda/LegacyDefinitions.cpp:14: UserWarning: masked_fill_ received a mask with dtype torch.uint8, this behavior is now deprecated,please use a mask with dtype torch.bool instead.
/pytorch/aten/src/ATen/native/cuda/LegacyDefinitions.cpp:14: UserWarning: masked_fill_ received a mask with dtype torch.uint8, this behavior is now deprecated,please use a mask with dtype torch.bool instead.
/pytorch/aten/src/ATen/native/cuda/LegacyDefinitions.cpp:14: UserWarning: masked_fill_ received a mask with dtype torch.uint8, this behavior is now deprecated,please use a mask with dtype torch.bool instead.
/pytorch/aten/src/ATen/native/cuda/LegacyDefinitions.cpp:14: UserWarning: masked_fill_ received a mask with dtype torch.uint8, this behavior is now deprecated,please use a mask with dtype torch.bool instead.
/pytorch/aten/src/ATen/native/cuda/LegacyDefinitions.cpp:14: UserWarning: masked_fill_ received a mask with dtype torch.uint8, this behavior is now deprecated,please use a mask with dtype torch.bool instead.
/pytorch/aten/src/ATen/native/cuda/LegacyDefinitions.cpp:14: UserWarning: masked_fill_ received a mask with dtype torch.uint8, this behavior is now deprecated,please use a mask with dtype torch.bool instead.
Traceback (most recent call last):
File "train.py", line 440, in
val_loader, model, epoch, config)
File "/home/riturajk/my_notebook_env/Q_Gen_exp_1/FocusSeq2Seq/evaluate.py", line 146, in evaluate
diversity_lambda=config.diversity_lambda)
File "/home/riturajk/my_notebook_env/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in call
result = self.forward(*input, **kwargs)
File "/home/riturajk/my_notebook_env/Q_Gen_exp_1/FocusSeq2Seq/models.py", line 272, in forward
diversity_lambda=diversity_lambda)
File "/home/riturajk/my_notebook_env/lib/python3.6/site-packages/torch/nn/modules/module.py", line 547, in call
result = self.forward(*input, **kwargs)
File "/home/riturajk/my_notebook_env/Q_Gen_exp_1/FocusSeq2Seq/layers/decoder.py", line 472, in forward
finished += generated_eos
RuntimeError: expected device cuda:0 and dtype Byte but got device cuda:0 and dtype Bool

How to use question generation model to generate questions from the text we have?

I have run through the code following the instructions and trained a QG model. My best checkpoint was 7.

So this next time round, I just want to load the saved checkpoint and look at the outputs from the val set.

Here are my configs:

!python train.py --task=QG --model=NQG --load_glove=True --feature_rich --data=squad \ --load --load_ckpt=7 --eval_only

I keep on getting this error:

Traceback (most recent call last):
File "train.py", line 136, in
n_iter = len(train_loader)
TypeError: object of type 'NoneType' has no len()

So if I understand it correctly, with eval_only, I should by-pass loading the training and validation sets and just test it.

However, there is no actual code in train.py to look at "eval_only" as far as I can see. It will always assume I am going through the whole training.

On executing the command: python train.py --task=QG --model=NQG --load_glove=True --feature_rich --data=squad --rnn=GRU --dec_hidden_size=512 --dropout=0.5 --batch_size=64 --eval_batch_size=64 --use_focus=True --n_mixture=3 --decoding=greedy

I get following error:

'chmod' is not recognized as an internal or external command,
operable program or batch file.
Traceback (most recent call last):
File "train.py", line 22, in
from utils.tensor_utils import repeat
File "C:\Users\Emergent Tech HP\my_projects\NQG_python3.6\FocusSeq2Seq\utils_init_.py", line 1, in
from .rouge import *
File "C:\Users\Emergent Tech HP\my_projects\NQG_python3.6\FocusSeq2Seq\utils\rouge_init_.py", line 1, in
from .perl_rouge import *
File "C:\Users\Emergent Tech HP\my_projects\NQG_python3.6\FocusSeq2Seq\utils\rouge\perl_rouge.py", line 15, in
_ = Rouge155(rouge_dir, log_level=0)
TypeError: init() got an unexpected keyword argument 'log_level'

Am I getting this error because I am using windows machine ??