search

monikkinom / ner-lstm

Named Entity Recognition using multilayered bidirectional LSTM
540 stars 182 forks source link

model.py error #12

Closed exsperazo closed 7 years ago

exsperazo commented 7 years ago

Hello guys,

Thank you for the great work

I have been trying to adopt your code to my work but get this error

ValueError: Cannot feed value of shape (128, 40, 207) for Tensor 'Placeholder:0', which has shape '(?, 40, 200)'

I am not an ML guru but have tried to follow the instructions as best I can. What could be the issue? My embedding size is 200, sentence length is 40 and batch size is 128.

shreenibhar commented 7 years ago

The tensor flow code seems correct as it shoes cannot feed value in ?,40,200. But your embedding size seems wrong as it shows 128, 40, 207. Try loading the pickle files in python and check it's shape. Verify that it is 128, 40, 200. If not then generate the embedding again with size 193. The seven extra features will add up to 200.

On Apr 24, 2017 11:55 AM, "exsperazo" notifications@github.com wrote:

Hello guys,

Thank you for the great work

I have been trying to adopt your code to my work but get this error

ValueError: Cannot feed value of shape (128, 40, 207) for Tensor 'Placeholder:0', which has shape '(?, 40, 200)'

I am not an ML guru but think I have followed all the instructions as best I can. What could be the issue? My embedding size is 200, sentence length is 40 and batch size is 128.

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/monikkinom/ner-lstm/issues/12, or mute the thread https://github.com/notifications/unsubscribe-auth/ALSRm2vnoHXgn_Uah2h1qqh8Ex3Ws0_5ks5rzEBVgaJpZM4NFvhF .