DeepCut Tokenize Error

[rkcosmos]

DeepCut Tokenize Error

[titipata]

@CherryChann, did you solve this problem? I cannot reproduce the error that you got. It would be great if I can have more details.

[CherryChann]

@titipata I have called deepcut.tokenize before starting app. Before calling deepcut.tokenize, I need to call this method with another word. For example: "import deepcut print(deepcut.tokenize('ตัดคำได้ดีมาก')) deepcut.tokenize('ตัดคำไ')" But i think this is not a correct solution. Also right now I m having a problem for deepcut.tokenize. I got this error : " ValueError: Tensor Tensor("dense_14/Sigmoid:0", shape=(?, 1), dtype=float32) is not an element of this graph." This error comes from y_predict = model.predict([x_char, x_type]) from deepcut library. My tensorflow version is 1.10.0 and deepcut version is (0.6.0.0).

…

On Tue, Oct 2, 2018 at 4:30 AM Titipat Achakulvisut < ***@***.***> wrote: @CherryChann <https://github.com/CherryChann>, did you solve this problem? I cannot reproduce the error that you got. It would be great if I can have more details. — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <#38 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/AJLeFEkXj_A5L8KAvgF-1Jv3NfkAhddAks5ugolxgaJpZM4WJJEX> .

[titipata]

@CherryChann I'll close this issue for now as we move to version 0.7.0. Let me know if the current version of the deepcut 0.7.0 works for you.