AttributeError: 'DoubleBLSTMModel' object has no attribute 'processor'

[ahmad-alismail]

Hello,
I am trying to reimplement the same customized code explained in the documentation for text labeling:

from typing import Dict, Any

from tensorflow import keras

from kashgari.tasks.labeling.abc_model import ABCLabelingModel
from kashgari.layers import L

import logging
logging.basicConfig(level='DEBUG')

class DoubleBLSTMModel(ABCLabelingModel):
    """Bidirectional LSTM Sequence Labeling Model"""

    @classmethod
    def default_hyper_parameters(cls) -> Dict[str, Dict[str, Any]]:
        """
        Get hyper parameters of model
        Returns:
            hyper parameters dict
        """
        return {
            'layer_blstm1': {
                'units': 128,
                'return_sequences': True
            },
            'layer_blstm2': {
                'units': 128,
                'return_sequences': True
            },
            'layer_dropout': {
                'rate': 0.2
            },
            'layer_time_distributed': {},
            'layer_activation': {
                'activation': 'softmax'
            }
        }

    def build_model_arc(self):
        """
        build model architectural
        """
        output_dim = len(self.processor.label2idx)
        config = self.hyper_parameters
        embed_model = self.embedding.embed_model

        # Define your layers
        layer_blstm1 = L.Bidirectional(L.LSTM(**config['layer_blstm1']),
                                       name='layer_blstm1')
        layer_blstm2 = L.Bidirectional(L.LSTM(**config['layer_blstm2']),
                                       name='layer_blstm2')

        layer_dropout = L.Dropout(**config['layer_dropout'],
                                  name='layer_dropout')

        layer_time_distributed = L.TimeDistributed(L.Dense(output_dim,
                                                           **config['layer_time_distributed']),
                                                   name='layer_time_distributed')
        layer_activation = L.Activation(**config['layer_activation'])

        # Define tensor flow
        tensor = layer_blstm1(embed_model.output)
        tensor = layer_blstm2(tensor)
        tensor = layer_dropout(tensor)
        tensor = layer_time_distributed(tensor)
        output_tensor = layer_activation(tensor)

        # Init model
        self.tf_model = keras.Model(embed_model.inputs, output_tensor)

model = DoubleBLSTMModel()
model.fit(sentences_train, labels_train)

However, I have the following message error:

Preparing text vocab dict: 100%|██████████| 2418/2418 [00:00<00:00, 168482.88it/s]
2021-01-31 04:24:53,929 [DEBUG] kashgari - --- Build vocab dict finished, Total: 1695 ---
2021-01-31 04:24:53,930 [DEBUG] kashgari - Top-10: ['[PAD]', '[UNK]', '[CLS]', '[SEP]', '.', 'the', ',', 'and', 'a', 'to']
Preparing text vocab dict: 100%|██████████| 2418/2418 [00:00<00:00, 250094.37it/s]
2021-01-31 04:24:53,946 [DEBUG] kashgari - --- Build vocab dict finished, Total: 4 ---
2021-01-31 04:24:53,946 [DEBUG] kashgari - Top-10: ['[PAD]', 'O', 'B_A', 'I_A']
Calculating sequence length: 100%|██████████| 2418/2418 [00:00<00:00, 1627379.18it/s]
2021-01-31 04:25:36,860 [DEBUG] kashgari - Calculated sequence length = 42
---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-36-928aa2c1f3d0> in <module>()
----> 1 model.fit(sentences_train, labels_train)

3 frames
<ipython-input-35-b8fc908f6695> in build_model_arc(self)
     41         build model architectural
     42         """
---> 43         output_dim = len(self.processor.label2idx)
     44         config = self.hyper_parameters
     45         embed_model = self.embedding.embed_model

AttributeError: 'DoubleBLSTMModel' object has no attribute 'processor'

Environment

• OS [e.g. Mac OS, Linux]: Mac OS
• Python Version: Python 3.6 on google-colab

Could you help me to solve the problem please?

Thanks in advance!

[ahmad-alismail]

I think the documentation from the legacy version also?

[stale]

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.