Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Char Embedding Error #80

Open
LizzyFarrugia opened this issue Mar 1, 2019 · 2 comments
Open

Char Embedding Error #80

LizzyFarrugia opened this issue Mar 1, 2019 · 2 comments

Comments

@LizzyFarrugia
Copy link

Hi,

First of all thank you very much for publishing this method!
I have already trained a model on a new dataset. However, now I am training it on another and I'm getting the following error:

[[Node: chars/char_embeddings = GatherV2[Taxis=DT_INT32, Tindices=DT_INT32, Tparams=DT_FLOAT, _class=["loc:@train_step/Adam/update_chars/_char_embeddings/AssignSub"], _device="/job:localhost/replica:0/task:0/device:CPU:0"](chars/_char_embeddings/read, _arg_char_ids_0_0, chars/char_embeddings/axis)]]

Could you please advice me why I am getting this error?

Thank you very much.

@guillaumegenthial
Copy link
Owner

I can't tell for sure given the error message, but it can be two things

  1. you have out-of-vocabulary characters
  2. you're trying to reload existing checkpoints (tensorflow parameter files) but your network dimensions have changed (bigger vocabulary etc.)

@snehasahu2626
Copy link

Hello guillaumegenthial,

as you have said in the above comments "you're trying to reload existing checkpoints (tensor flow parameter files) but your network dimensions have changed (bigger vocabulary etc.)"
so i do face the same issue when in the test.txt file i increase the number of tags please tell me how to get rid of this error . would be a grate help from your side

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants