seanie12 / info-hcvae Goto Github PK

Dear authors,
I just come across a small questions about the implementation of generating different question/QA pairs from the same paragraph. My question is:
How to generate many different questions or QA pairs in Table 6 and Table 7 respectively, when given the same paragraph? I mean, in your released code, it seems that I could not find the relevant part. If possible, could your please share the code about these part. I am just curious about how to generate different questions/QA pairs from the same paragraph, from a implementation perspective.
Any feedback would be appriciated! Thanks

Runtime error : lengths should be 1-D CPU int64 tensor, got cuda:0 Long tensor

I read the derivation you provided in appendix A, but I don't know how the last approximation is obtained, I hope to get your answer, thank you very much

Hi,

Thanks for open sourcing the work. Is the pre-trained model available with which I can infer on my text?

{"context": "[UNK] \u4e16 [UNK] \u672c [UNK] [UNK] \u6709 [UNK] [UNK] \u795e [UNK] \u7684 \uff0c [UNK] [UNK] \u592a \u53e4 [UNK] [UNK] \uff0c \u4eba [UNK] [UNK] [UNK] [UNK] [UNK] \u4e16 [UNK] \uff0c [UNK] [UNK] [UNK] [UNK] \u4e4b \u4e8b \uff0c [UNK] [UNK] [UNK] [UNK] \uff0c [UNK] [UNK] [UNK] [UNK] \uff0c [UNK] \u6709 \u5929 [UNK] \u4eba [UNK] \uff0c [UNK] [UNK] [UNK] [UNK] \uff0c [UNK] [UNK] [UNK] \u91ce \uff0c [UNK] [UNK] \u4eba \u529b [UNK] [UNK] [UNK] \uff0c [UNK] [UNK] [UNK] [UNK] \u3002 [UNK] [UNK] [UNK] [UNK] \u5929 \u4e4b \u4e0a \uff0c \u6709 [UNK] [UNK] \u795e [UNK] \uff0c [UNK] [UNK] \u4e4b \u4e0b \uff0c [UNK] [UNK] [UNK] [UNK] [UNK] [UNK] \uff0c [UNK] [UNK] [UNK] \u5802 \u3002 [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD]", "question": "[CLS] neck \u767a game continueser [SEP] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD]", "answer": "\uff0c"}

The version of Python is 3.11.5, Why is this error reported below？

Traceback (most recent call last):
File "main.py", line 116, in
main(args)
File "main.py", line 38, in main
trainer.train(c_ids, q_ids, a_ids, start_positions, end_positions)
File "/home/2018/Info-HCVAE-master/vae/trainer.py", line 35, in train
loss.backward()
File "/home/2018/anaconda3/envs/transformers/lib/python3.6/site-packages/torch/tensor.py", line 150, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph)
File "/home/2018/anaconda3/envs/transformers/lib/python3.6/site-packages/torch/autograd/init.py", line 99, in backward
allow_unreachable=True) # allow_unreachable flag
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED

cuda:9.0 cudnn:7
python3.6 pytorch1.3

thank you for your work! I am trying to train the model but I’ve got an error that is “RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED”. I got this problem when this part of code runs: loss.backward()
Can you help me to solve it?

/pytorch/aten/src/THC/THCTensorIndex.cu:361: void indexSelectLargeIndex(TensorInfo<T, IndexType>, TensorInfo<T, IndexType>, TensorInfo<long, IndexType>, int, int, IndexType, IndexType, long) [with T = float, IndexType = unsigned int, DstDim = 2, SrcDim = 2, IdxDim = -2, IndexIsMajor = true]: block: [57,0,0], thread: [90,0,0] Assertion srcIndex < srcSelectDimSize failed.
/pytorch/aten/src/THC/THCTensorIndex.cu:361: void indexSelectLargeIndex(TensorInfo<T, IndexType>, TensorInfo<T, IndexType>, TensorInfo<long, IndexType>, int, int, IndexType, IndexType, long) [with T = float, IndexType = unsigned int, DstDim = 2, SrcDim = 2, IdxDim = -2, IndexIsMajor = true]: block: [57,0,0], thread: [91,0,0] Assertion srcIndex < srcSelectDimSize failed.
/pytorch/aten/src/THC/THCTensorIndex.cu:361: void indexSelectLargeIndex(TensorInfo<T, IndexType>, TensorInfo<T, IndexType>, TensorInfo<long, IndexType>, int, int, IndexType, IndexType, long) [with T = float, IndexType = unsigned int, DstDim = 2, SrcDim = 2, IdxDim = -2, IndexIsMajor = true]: block: [57,0,0], thread: [92,0,0] Assertion srcIndex < srcSelectDimSize failed.
/pytorch/aten/src/THC/THCTensorIndex.cu:361: void indexSelectLargeIndex(TensorInfo<T, IndexType>, TensorInfo<T, IndexType>, TensorInfo<long, IndexType>, int, int, IndexType, IndexType, long) [with T = float, IndexType = unsigned int, DstDim = 2, SrcDim = 2, IdxDim = -2, IndexIsMajor = true]: block: [57,0,0], thread: [93,0,0] Assertion srcIndex < srcSelectDimSize failed.
/pytorch/aten/src/THC/THCTensorIndex.cu:361: void indexSelectLargeIndex(TensorInfo<T, IndexType>, TensorInfo<T, IndexType>, TensorInfo<long, IndexType>, int, int, IndexType, IndexType, long) [with T = float, IndexType = unsigned int, DstDim = 2, SrcDim = 2, IdxDim = -2, IndexIsMajor = true]: block: [57,0,0], thread: [94,0,0] Assertion srcIndex < srcSelectDimSize failed.
/pytorch/aten/src/THC/THCTensorIndex.cu:361: void indexSelectLargeIndex(TensorInfo<T, IndexType>, TensorInfo<T, IndexType>, TensorInfo<long, IndexType>, int, int, IndexType, IndexType, long) [with T = float, IndexType = unsigned int, DstDim = 2, SrcDim = 2, IdxDim = -2, IndexIsMajor = true]: block: [57,0,0], thread: [95,0,0] Assertion srcIndex < srcSelectDimSize failed.
Epoch: 55%|?????????????????????????????????????????????????????????????????????????? | 11/20 [00:22<00:18, 2.07s/it]
Traceback (most recent call last):
File "main.py", line 136, in
main(args)
File "main.py", line 51, in main
metric_dict, bleu, rouge_1, rouge_2, _ = eval_vae(epoch, args, trainer, eval_data)
File "/home/codes/Info-HCVAE/vae/eval.py", line 74, in eval_vae
posterior_z_prob = trainer.generate_posterior(c_ids, q_ids, a_ids)
File "/home/codes/Info-HCVAE/vae/trainer.py", line 49, in generate_posterior
_, _, zq, _, za = self.vae.posterior_encoder(c_ids, q_ids, a_ids)
File "/home/.local/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/codes/Info-HCVAE/vae/models.py", line 199, in forward
c_hs, c_state = self.encoder(c_embeddings, c_lengths)
File "/home/.local/lib/python3.7/site-packages/torch/nn/modules/module.py", line 532, in call
result = self.forward(*input, **kwargs)
File "/home/codes/Info-HCVAE/vae/models.py", line 146, in forward
batch_first=True, enforce_sorted=False)
File "/home/.local/lib/python3.7/site-packages/torch/nn/utils/rnn.py", line 223, in pack_padded_sequence
lengths = torch.as_tensor(lengths, dtype=torch.int64)
RuntimeError: CUDA error: device-side assert triggered

Do you have any idea about this error ? Thank you! The only changing value is "max_c_len" (from 384(default) to 1000). It seems that this error is triggered by the increasing of "max_c_len"

Would you mind sharing processed data with me? I clicked the link and found that it was invalid

ModuleNotFoundError: No module named 'transformers.tokenization_bert'
how can i sovle this problem

Can you provide models that have been trained in main.py and saved at./save/vae-checkpoint? My email is [email protected]. Your research is very helpful to me and I will cite your article in my paper!I really appreciate your help

Hi, thank you for open sourcing your work. It's really nice. Do you have any plan to share the pre-trained QAG model that can reproduce the results in the paper (the one that you get from running python main.py)?

Otherwise, providing the generated QA pairs used in your work would be nice as well. Thanks.

(I missed the README saying it's TBA. I just want to know when they will be available)