Info-HCVAE
Info-HCVAE copied to clipboard
[ACL 2020] Generating Diverse and Consistent QA pairs from Contexts with Information-Maximizing Hierarchical Conditional VAEs
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
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...
help!
ModuleNotFoundError: No module named 'transformers.tokenization_bert' how can i sovle this problem
Runtime error : lengths should be 1-D CPU int64 tensor, got cuda:0 Long tensor
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...
/pytorch/aten/src/THC/THCTensorIndex.cu:361: void indexSelectLargeIndex(TensorInfo, TensorInfo, TensorInfo, int, int, IndexType, IndexType, long) [with T = float, IndexType = unsigned int, DstDim = 2, SrcDim = 2, IdxDim = -2, IndexIsMajor = true]:...
使用bert_base_chinese模型,在加载state_dict时出现key错误: Unexpected key(s) in state_dict: "answer_decoder.embedding.embedding.position_ids", "question_decoder.context_lstm.embedding.embedding.position_ids".
{"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...
 The version of Python is 3.11.5, Why is this error reported below? 