GRAAL-Research / deepparse

Deepparse is a state-of-the-art library for parsing multinational street addresses using deep learning
https://deepparse.org/
GNU Lesser General Public License v3.0
294 stars 30 forks source link

[BUG]I don't know what does it mean and how can I solve it. I have download the model. #234

Open Olivercyf opened 1 week ago

Olivercyf commented 1 week ago

My Input:

  from deepparse.parser import AddressParser

  address_parser = AddressParser(model_type="bpemb")

The output:

RuntimeError: Error(s) in loading state_dict for BPEmbSeq2SeqModel:
    Missing key(s) in state_dict: "encoder.lstm.weight_ih_l0", "encoder.lstm.weight_hh_l0", "encoder.lstm.bias_ih_l0", "encoder.lstm.bias_hh_l0", "decoder.lstm.weight_ih_l0", "decoder.lstm.weight_hh_l0", "decoder.lstm.bias_ih_l0", "decoder.lstm.bias_hh_l0", "decoder.linear.weight", "decoder.linear.bias", "embedding_network.model.weight_ih_l0", "embedding_network.model.weight_hh_l0", "embedding_network.model.bias_ih_l0", "embedding_network.model.bias_hh_l0", "embedding_network.model.weight_ih_l0_reverse", "embedding_network.model.weight_hh_l0_reverse", "embedding_network.model.bias_ih_l0_reverse", "embedding_network.model.bias_hh_l0_reverse", "embedding_network.projection_layer.weight", "embedding_network.projection_layer.bias". 
    Unexpected key(s) in state_dict: "model_type", "address_tagger_model".
github-actions[bot] commented 1 week ago

Thank you for you interest in improving Deepparse.

davebulaval commented 1 week ago

Hi,

Can you fill out the bug template? We do not have much context on your problem.

Describe the bug A clear and concise description of what the bug is.

To Reproduce Minimal example of code that reproduces the behavior

Expected behavior A clear and concise description of what you expected to happen.

Screenshots If applicable, add screenshots to help explain your problem.

Desktop (please complete the following information):

OS: [e.g. Windows] Version [e.g. 0.5] Additional context Add any other context about the problem here.