Numpy 数组索引错误：IndexError：boolean 索引与维度 0 上的索引数组不匹配； 尺寸为 16

Question

以下代码引发错误：

Traceback (most recent call last):
  File "training.py", line 19, in <module>
    preds = model.predict(x_test, test_df)
  File "D:\brand\models\lstm_detection_model\lstm_brand_detection.py", line 46, in predict
    output = [' '.join(np.array(token_df[i])[np.array(ind[i])]) for i in range(len(ind))]
  File "D:\brand\models\lstm_detection_model\lstm_brand_detection.py", line 46, in <listcomp>
    output = [' '.join(np.array(token_df[i])[np.array(ind[i])]) for i in range(len(ind))]
IndexError: boolean index did not match indexed array along dimension 0; dimension is 16 but corresponding boolean dimension is 17

预测 function：

def predict(self, test_x, test_df=None):
    token_df = test_df.apply(word_tokenize)
    ind = self.model.predict(test_x, verbose=0).argmax(axis=-1)
    ind = [[z for z in obs if z!=2] for obs in ind]
    ind = [[False if elem == 0 else True for elem in obs] for obs in ind]
    output = [' '.join(np.array(token_df[i])[np.array(ind[i])]) for i in range(len(ind))]
    preds = pd.concat([test_df, pd.DataFrame(output, columns=['predictions'])], axis=1)
    return preds

这似乎是由于 Numpy 中的更新，有人知道纠正这个问题的方法吗？ 谢谢！

编辑：发布整个 LSTM_model 文件。这涉及 model 训练，然后将预测输出到单独的文件中：predictions.csv。 这就是错误出现的地方，训练后。

import numpy as np
import pandas as pd
from nltk import word_tokenize
from keras.layers import Dense
from keras.layers import LSTM
from keras.layers.core import Dropout
from keras.layers.wrappers import Bidirectional
from keras.layers.wrappers import TimeDistributed
from keras.models import Sequential
from crf_layer import ChainCRF
import warnings
warnings.filterwarnings("ignore")

class LstmBrandDetector:
    def __init__(self):
        self.model = None

    def create_model(self, dropout=0.5, units=150):
        self.model = Sequential()
        self.model.add(Bidirectional(LSTM(units, return_sequences=True),
                                     input_shape=(36, 50)))
        self.model.add(Dropout(dropout))
        self.model.add(Bidirectional(LSTM(units, return_sequences=True)))
        self.model.add(Dropout(dropout))
        self.model.add(TimeDistributed(Dense(3)))
        self.model.add(Dropout(dropout))
        crf = ChainCRF()
        self.model.add(crf)
        self.model.compile(loss=crf.loss, optimizer='Adam',
                           metrics=['categorical_accuracy'])

    def fit(self, train_x, train_y, epochs=5, batch=28):
        self.model.fit(train_x, train_y, epochs=epochs, batch_size=batch)

    def save(self, filepath):
        self.model.save(filepath)

    def print_summary(self):
        print(self.model.summary())

    def predict(self, test_x, test_df=None):
        token_df = test_df.apply(word_tokenize)
        ind = self.model.predict(test_x, verbose=0).argmax(axis=-1)
        ind = [[z for z in obs if z!=2] for obs in ind]
        ind = [[False if elem == 0 else True for elem in obs] for obs in ind]
        ind = ind[1:]
        output = [' '.join(np.array(token_df[i])[np.array(ind[i])]) for i in range(len(ind))]
        preds = pd.concat([test_df, pd.DataFrame(output, columns=['predictions'])], axis=1)
        return preds

    def evaluate(self, test_x, test_y):
        y_pred = self.model.predict(test_x, verbose=0).argmax(axis=-1)
        y_test = test_y.argmax(axis=-1)
        acc = [np.array_equal(y_pred[i], y_test[i]) for i in
               range(len(y_pred))].count(True) / len(y_pred)
        return acc

Crf_Layer，归入 BiLSTM Model：

from __future__ import absolute_import
from keras import backend as K
from keras import initializers
from keras import regularizers
from keras import constraints
from keras.engine import Layer, InputSpec


def path_energy(y, x, U, b_start=None, b_end=None, mask=None):
    '''
    Calculates the energy of a tag path y for a given input x (with mask),
    transition energies U and boundary energies b_start, b_end.
    '''
    x = add_boundary_energy(x, b_start, b_end, mask)
    return path_energy0(y, x, U, mask)


def path_energy0(y, x, U, mask=None):
    '''
    Path energy without boundary potential handling.
    '''
    n_classes = K.shape(x)[2]
    y_one_hot = K.one_hot(y, n_classes)

    energy = K.sum(x * y_one_hot, 2)
    energy = K.sum(energy, 1)

    y_t = y[:, :-1]
    y_tp1 = y[:, 1:]
    U_flat = K.reshape(U, [-1])
    flat_indices = y_t * n_classes + y_tp1
    U_y_t_tp1 = K.gather(U_flat, flat_indices)

    if mask is not None:
        mask = K.cast(mask, K.floatx())
        y_t_mask = mask[:, :-1]
        y_tp1_mask = mask[:, 1:]
        U_y_t_tp1 *= y_t_mask * y_tp1_mask

    energy += K.sum(U_y_t_tp1, axis=1)

    return energy


def sparse_chain_crf_loss(y, x, U, b_start=None, b_end=None, mask=None):
    '''
    Given the true sparsely encoded tag sequence y, input x (with mask),
    transition energies U, boundary energies b_start and b_end, it computes
    the loss function of a Linear Chain Conditional Random Field:

    loss(y, x) = NNL(P(y|x)), where P(y|x) = exp(E(y, x)) / Z.
    So, loss(y, x) = - E(y, x) + log(Z)

    Here, E(y, x) is the tag path energy, and Z is the normalization constant.
    The values log(Z) is also called free energy.
    '''
    x = add_boundary_energy(x, b_start, b_end, mask)
    energy = path_energy0(y, x, U, mask)
    energy -= free_energy0(x, U, mask)
    return K.expand_dims(-energy, -1)


def chain_crf_loss(y, x, U, b_start=None, b_end=None, mask=None):
    '''
    Variant of sparse_chain_crf_loss but with one-hot encoded tags y.
    '''
    y_sparse = K.argmax(y, -1)
    y_sparse = K.cast(y_sparse, 'int32')
    return sparse_chain_crf_loss(y_sparse, x, U, b_start, b_end, mask)


def add_boundary_energy(x, b_start=None, b_end=None, mask=None):
    '''
    Given the observations x, it adds the start boundary energy b_start (resp.
    end boundary energy b_end on the start (resp. end) elements and multiplies
    the mask.
    '''
    if mask is None:
        if b_start is not None:
            x = K.concatenate([x[:, :1, :] + b_start, x[:, 1:, :]], axis=1)
        if b_end is not None:
            x = K.concatenate([x[:, :-1, :], x[:, -1:, :] + b_end], axis=1)
    else:
        mask = K.cast(mask, K.floatx())
        mask = K.expand_dims(mask, 2)
        x *= mask
        if b_start is not None:
            mask_r = K.concatenate([K.zeros_like(mask[:, :1]), mask[:, :-1]],
                                   axis=1)
            start_mask = K.cast(K.greater(mask, mask_r), K.floatx())
            x = x + start_mask * b_start
        if b_end is not None:
            mask_l = K.concatenate([mask[:, 1:], K.zeros_like(mask[:, -1:])],
                                   axis=1)
            end_mask = K.cast(K.greater(mask, mask_l), K.floatx())
            x = x + end_mask * b_end
    return x


def viterbi_decode(x, U, b_start=None, b_end=None, mask=None):
    '''
    Computes the best tag sequence y for a given input x, i.e. the one that
    maximizes the value of path_energy.
    '''
    x = add_boundary_energy(x, b_start, b_end, mask)

    alpha_0 = x[:, 0, :]
    gamma_0 = K.zeros_like(alpha_0)
    initial_states = [gamma_0, alpha_0]
    _, gamma = _forward(x,
                        lambda B: [K.cast(K.argmax(B, axis=1), K.floatx()),
                                   K.max(B, axis=1)],
                        initial_states,
                        U,
                        mask)
    y = _backward(gamma, mask)
    return y


def free_energy(x, U, b_start=None, b_end=None, mask=None):
    '''
    Computes efficiently the sum of all path energies for input x, when
    runs over all possible tag sequences.
    '''
    x = add_boundary_energy(x, b_start, b_end, mask)
    return free_energy0(x, U, mask)


def free_energy0(x, U, mask=None):
    '''
    Free energy without boundary potential handling.
    '''
    initial_states = [x[:, 0, :]]
    last_alpha, _ = _forward(x,
                             lambda B: [K.logsumexp(B, axis=1)],
                             initial_states,
                             U,
                             mask)
    return last_alpha[:, 0]


def _forward(x, reduce_step, initial_states, U, mask=None):
    '''
    Forward recurrence of the linear chain crf.
    '''

    def _forward_step(energy_matrix_t, states):
        alpha_tm1 = states[-1]
        new_states = reduce_step(K.expand_dims(alpha_tm1, 2) + energy_matrix_t)
        return new_states[0], new_states

    U_shared = K.expand_dims(K.expand_dims(U, 0), 0)

    if mask is not None:
        mask = K.cast(mask, K.floatx())
        mask_U = K.expand_dims(K.expand_dims(mask[:, :-1] * mask[:, 1:], 2), 3)
        U_shared = U_shared * mask_U

    inputs = K.expand_dims(x[:, 1:, :], 2) + U_shared
    inputs = K.concatenate([inputs, K.zeros_like(inputs[:, -1:, :, :])],
                           axis=1)

    last, values, _ = K.rnn(_forward_step, inputs, initial_states)
    return last, values


def batch_gather(reference, indices):
    ref_shape = K.shape(reference)
    batch_size = ref_shape[0]
    n_classes = ref_shape[1]
    flat_indices = K.arange(0, batch_size) * n_classes + K.flatten(indices)
    return K.gather(K.flatten(reference), flat_indices)


def _backward(gamma, mask):
    '''
    Backward recurrence of the linear chain crf.
    '''
    gamma = K.cast(gamma, 'int32')

    def _backward_step(gamma_t, states):
        y_tm1 = K.squeeze(states[0], 0)
        y_t = batch_gather(gamma_t, y_tm1)
        return y_t, [K.expand_dims(y_t, 0)]

    initial_states = [K.expand_dims(K.zeros_like(gamma[:, 0, 0]), 0)]
    _, y_rev, _ = K.rnn(_backward_step,
                        gamma,
                        initial_states,
                        go_backwards=True)
    y = K.reverse(y_rev, 1)

    if mask is not None:
        mask = K.cast(mask, dtype='int32')
        y *= mask
        y += -(1 - mask)
    return y


class ChainCRF(Layer):
    '''
    A Linear Chain Conditional Random Field output layer.

    It carries the loss function and its weights for computing
    the global tag sequence scores. While training it acts as
    the identity function that passes the inputs to the subsequently
    used loss function. While testing it applies Viterbi decoding
    and returns the best scoring tag sequence as one-hot encoded vectors.

    # Arguments
        init: weight initialization function for chain energies U.
            Can be the name of an existing function (str),
            or a Theano function (see: [initializers](../initializers.md)).
        U_regularizer: instance of [WeightRegularizer](../regularizers.md)
            (eg. L1 or L2 regularization), applied to the transition
            weight matrix.
        b_start_regularizer: instance of [WeightRegularizer]
            (../regularizers.md), applied to the start bias b.
        b_end_regularizer: instance of [WeightRegularizer](../regularizers.md)
            module, applied to the end bias b.
        b_start_constraint: instance of the [constraints](../constraints.md)
            module, applied to the start bias b.
        b_end_constraint: instance of the [constraints](../constraints.md)
            module, applied to the end bias b.
        weights: list of Numpy arrays for initializing [U, b_start, b_end].
            Thus it should be a list of 3 elements of shape
            [(n_classes, n_classes), (n_classes, ), (n_classes, )]
    '''

    def __init__(self, init='glorot_uniform',
                 U_regularizer=None,
                 b_start_regularizer=None,
                 b_end_regularizer=None,
                 U_constraint=None,
                 b_start_constraint=None,
                 b_end_constraint=None,
                 weights=None,
                 **kwargs):
        super(ChainCRF, self).__init__(**kwargs)
        self.init = initializers.get(init)
        self.U_regularizer = regularizers.get(U_regularizer)
        self.b_start_regularizer = regularizers.get(b_start_regularizer)
        self.b_end_regularizer = regularizers.get(b_end_regularizer)
        self.U_constraint = constraints.get(U_constraint)
        self.b_start_constraint = constraints.get(b_start_constraint)
        self.b_end_constraint = constraints.get(b_end_constraint)

        self.initial_weights = weights

        self.supports_masking = True
        self.uses_learning_phase = True
        self.input_spec = [InputSpec(ndim=3)]

    def compute_output_shape(self, input_shape):
        assert input_shape and len(input_shape) == 3
        return (input_shape[0], input_shape[1], input_shape[2])

    def compute_mask(self, input, mask=None):
        if mask is not None:
            return K.any(mask, axis=1)
        return mask

    def _fetch_mask(self):
        mask = None
        if self.inbound_nodes:
            mask = self.inbound_nodes[0].input_masks[0]
        return mask

    def build(self, input_shape):
        assert len(input_shape) == 3
        n_classes = input_shape[2]
        n_steps = input_shape[1]
        assert n_steps is None or n_steps >= 2
        self.input_spec = [InputSpec(dtype=K.floatx(),
                                     shape=(None, n_steps, n_classes))]

        self.U = self.add_weight(shape=(n_classes, n_classes),
                                 initializer=self.init,
                                 name='U',
                                 regularizer=self.U_regularizer,
                                 constraint=self.U_constraint)

        self.b_start = self.add_weight(shape=(n_classes,),
                                       initializer='zero',
                                       name='b_start',
                                       regularizer=self.b_start_regularizer,
                                       constraint=self.b_start_constraint)

        self.b_end = self.add_weight(shape=(n_classes,),
                                     initializer='zero',
                                     name='b_end',
                                     regularizer=self.b_end_regularizer,
                                     constraint=self.b_end_constraint)

        if self.initial_weights is not None:
            self.set_weights(self.initial_weights)
            del self.initial_weights

        self.built = True

    def call(self, x, mask=None):
        y_pred = viterbi_decode(x, self.U, self.b_start, self.b_end, mask)
        nb_classes = self.input_spec[0].shape[2]
        y_pred_one_hot = K.one_hot(y_pred, nb_classes)
        return K.in_train_phase(x, y_pred_one_hot)

    def loss(self, y_true, y_pred):
        '''
        Linear Chain Conditional Random Field loss function.
        '''
        mask = self._fetch_mask()
        return chain_crf_loss(y_true, y_pred, self.U, self.b_start, self.b_end,
                              mask)

    def sparse_loss(self, y_true, y_pred):
        '''
        Linear Chain Conditional Random Field loss function with sparse
        tag sequences.
        '''
        y_true = K.cast(y_true, 'int32')
        y_true = K.squeeze(y_true, 2)
        mask = self._fetch_mask()
        return sparse_chain_crf_loss(y_true, y_pred, self.U, self.b_start,
                                     self.b_end, mask)

    def get_config(self):
        config = {
            'init': initializers.serialize(self.init),
            'U_regularizer': regularizers.serialize(self.U_regularizer),
            'b_start_regularizer': regularizers.serialize(
                self.b_start_regularizer),
            'b_end_regularizer': regularizers.serialize(
                self.b_end_regularizer),
            'U_constraint': constraints.serialize(self.U_constraint),
            'b_start_constraint': constraints.serialize(
                self.b_start_constraint),
            'b_end_constraint': constraints.serialize(self.b_end_constraint)
        }
        base_config = super(ChainCRF, self).get_config()
        return dict(list(base_config.items()) + list(config.items()))


def create_custom_objects():
    '''
    Returns the custom objects, needed for loading a persisted model.
    '''
    instanceHolder = {'instance': None}

    class ClassWrapper(ChainCRF):
        def __init__(self, *args, **kwargs):
            instanceHolder['instance'] = self
            super(ClassWrapper, self).__init__(*args, **kwargs)

    def loss(*args):
        method = getattr(instanceHolder['instance'], 'loss')
        return method(*args)

    def sparse_loss(*args):
        method = getattr(instanceHolder['instance'], 'sparse_loss')
        return method(*args)

    return {'ChainCRF': ClassWrapper, 'loss': loss, 'sparse_loss': sparse_loss}

Answer 1

是的，过去 boolean 索引 arrays 可能比他们正在索引的 object 更长； 现在他们必须匹配。 这是合乎逻辑的，对。 前一种行为让有缺陷的代码运行。

这一行创建了一个列表列表； 即使ind是二维数组，新列表的长度也可能不同：

ind = [[z for z in obs if z!=2] for obs in ind]

这只是将这些子列表中的元素转换为 boolean

ind = [[False if elem == 0 else True for elem in obs] for obs in ind]

这适用于 boolean 从 token_df 索引到token_df 。 对于至少一个i ， np.array(token_df[i])和ind[i]的长度不匹配。 鉴于ind的构建方式，我并不感到惊讶。

output = [' '.join(np.array(token_df[i])[np.array(ind[i])]) for i in range(len(ind))]

很难想象像这样构建 boolean 索引会产生正确结果的情况，即使长度是正确的。 较旧的 numpy 只是让您使用错误代码，而它本应引发错误。

Answer 2

我发现了解决这个问题的方法：

在这一行：

output = [' '.join(np.array(token_df[i])[np.array(ind[i])]) for i in range(len(ind))]

通过用 np.where 替换第二个 np.array，尺寸不匹配不再存在。