input array shape error ,

[firasfrikha]

Hello everyone,

i'm trying to load my trained model to spacy pipe line. when i'am trying to load a sentence i get the followin error

f=nlp('Je suis Firas')

---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-4-cd42a45d2899> in <module>
----> 1 f=nlp('Je suis FIras')

~/anaconda3/envs/coref1/lib/python3.8/site-packages/spacy/language.py in __call__(self, text, disable, component_cfg)
    437             if not hasattr(proc, "__call__"):
    438                 raise ValueError(Errors.E003.format(component=type(proc), name=name))
--> 439             doc = proc(doc, **component_cfg.get(name, {}))
    440             if doc is None:
    441                 raise ValueError(Errors.E005.format(name=name))

neuralcoref.pyx in neuralcoref.neuralcoref.NeuralCoref.__call__()

neuralcoref.pyx in neuralcoref.neuralcoref.NeuralCoref.predict()

neuralcoref.pyx in neuralcoref.neuralcoref.NeuralCoref.get_mention_embeddings()

ValueError: could not broadcast input array from shape (300) into shape (50)

could any one help me please, Thank you

[svlandeg]

It looks like somehow there's an embedding layer in your pipeline with mismatched dimensions. How was nlp defined? Can you provide a minimal code snippet that produces this error?

[stale[bot]]

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.