bojone/seq2seq

Issues

• 执行model.add_loss(cross_entropy)报错You must feed a value for placeholder tensor

  #18 opened 3 years ago by Yumeka999
  2

• 苏神您好，关于IndexError: index 1 is out of bounds for axis 0 with size 1

  #11 opened 6 years ago by Minnesota2121
  4

• ValueError: Dimension must be 5 but is 4 for '{{node attention_11/transpose_4}} = Transpose[T=DT_FLOAT, Tperm=DT_INT32](attention_11/truediv, attention_11/transpose_4/perm)' with input shapes: [?,8,?,8,?], [4].

  #17 opened 3 years ago by Yumeka999
  1

• 运行错误

  #16 opened 3 years ago by OldMy
  0

• 数据问题

  #15 opened 4 years ago by duan-boop
  0

• 相同错误 IndexError: index 2 is out of bounds for axis 0 with size 2，gen_sent（）函数中的_yr_id.append(list(yr_id[j]) + [r_arg_topk[j][k]+3])行，不知怎么回事，在完成第一个epoch后报错的！求助！多谢！

  #13 opened 5 years ago by zj890724
  3

• 您好，在训练时出现这个问题。An operation has `None` for gradient. Please make sure that all of your ops have a gradient defined (i.e. are differentiable). Common ops without gradient: K.argmax, K.round, K.eval.

  #12 opened 5 years ago by liziUCAS
  4

• 训练问题

  #7 opened 5 years ago by applon
  0

• 大数据的处理问题

  #8 opened 5 years ago by GITJolly
  1

• python36跑不通

  #9 opened 5 years ago by darrenwang00
  5

• 请问训练数据里需要人工做标记么？

  #10 opened 5 years ago by Minnesota2121
  1

• 请问你可以告知一下keras和tensorflow版本吗？

  #6 opened 6 years ago
  0

• keras和tensorflow版本？

  #5 opened 6 years ago
  10

• 对比文章和代码后的两个疑问

  #4 opened 6 years ago by 34127chi
  4

• 请问您用的是单个汉字还是词啊？

  #2 opened 6 years ago by whoisleilei
  2

• 您好，请问有数据吗

  #3 opened 6 years ago by tcxia
  1

• 请问数据集可以提供下载吗？

  #1 opened 6 years ago by qiangsiwei
  1