Keras class_weight 多标签二分类

Keras class_weight in multi-label binary classification

使用 class_weight 解决我的多标签问题时遇到问题。也就是说,每个标签不是0就是1,但是每个输入样本有很多标签。

代码(带有用于 MWE 目的的随机数据):

import tensorflow as tf
from keras.models import Sequential, Model
from keras.layers import Input, Concatenate, LSTM, Dense
from keras import optimizers
from keras.utils import to_categorical
from keras import backend as K
import numpy as np

# from http://www.deepideas.net/unbalanced-classes-machine-learning/
def sensitivity(y_true, y_pred):
        true_positives = tf.reduce_sum(tf.round(K.clip(y_true * y_pred, 0, 1)))
        possible_positives = tf.reduce_sum(tf.round(K.clip(y_true, 0, 1)))
        return true_positives / (possible_positives + K.epsilon())

# from http://www.deepideas.net/unbalanced-classes-machine-learning/    
def specificity(y_true, y_pred):
        true_negatives = tf.reduce_sum(K.round(K.clip((1-y_true) * (1-y_pred), 0, 1)))
        possible_negatives = tf.reduce_sum(K.round(K.clip(1-y_true, 0, 1)))
        return true_negatives / (possible_negatives + K.epsilon())

def to_train(a_train, y_train):
        hours_np = [np.arange(a_train.shape[1])]*a_train.shape[0]
        train_hours = to_categorical(hours_np)
        n_samples = a_train.shape[0]
        n_classes = 4
        features_in = np.zeros((n_samples, n_classes))
        supp_feat = np.random.choice(n_classes, n_samples)
        features_in[np.arange(n_samples), supp_feat] = 1

        #This model has 3 separate inputs
        seq_model_in = Input(shape=(1,),batch_shape=(1, 1, a_train.shape[2]), name='seq_model_in')
        feat_in = Input(shape=(1,), batch_shape=(1, features_in.shape[1]), name='feat_in')
        feat_dense = Dense(1)(feat_in)
        hours_in = Input(shape=(1,), batch_shape=(1, 1, train_hours.shape[2]), name='hours_in')

        #Model intermediate layers
        t_concat = Concatenate(axis=-1)([seq_model_in, hours_in])
        lstm_layer = LSTM(1, batch_input_shape=(1, 1, (a_train.shape[2]+train_hours.shape[2])), return_sequences=False, stateful=True)(t_concat)
        merged_after_lstm = Concatenate(axis=-1)([lstm_layer, feat_dense]) #may need another Dense() after
        dense_merged = Dense(a_train.shape[2], activation="sigmoid")(merged_after_lstm)

        #Define input and output to create model, and compile
        model = Model(inputs=[seq_model_in, feat_in, hours_in], outputs=dense_merged)
        model.compile(loss='binary_crossentropy', optimizer='adam', metrics=[sensitivity, specificity])

        class_weights = {0.:1., 1.:118.}
        seq_length = 23

        #TRAINING (based on http://philipperemy.github.io/keras-stateful-lstm/)
        for epoch in range(2):
            for i in range(a_train.shape[0]):
                    y_true_1 = np.expand_dims(y_train[i,:], axis=1)
                    y_true = np.swapaxes(y_true_1, 0, 1)
                    #print 'y_true', y_true.shape
                    for j in range(seq_length-1):
                            input_1 = np.expand_dims(np.expand_dims(a_train[i][j], axis=1), axis=1)
                            input_1 = np.reshape(input_1, (1, 1, a_train.shape[2]))
                            input_2 = np.expand_dims(np.array(features_in[i]), axis=1)
                            input_2 = np.swapaxes(input_2, 0, 1)
                            input_3 = np.expand_dims(np.array([train_hours[i][j]]), axis=1)
                            tr_loss, tr_sens, tr_spec = model.train_on_batch([input_1, input_2, input_3], y_true, class_weight=class_weights)
                    model.reset_states()
       return 0

a_train = np.random.normal(size=(50,24,5625))
y_train = a_train[:, -1, :]
a_train = a_train[:, :-1, :]
y_train[y_train > 0.] = 1.
y_train[y_train < 0.] = 0.
to_train(a_train, y_train)

我得到的错误是:

ValueError: `class_weight` must contain all classes in the data. The classes set([330]) exist in the data but not in `class_weight`.

'set([...])' 内的值在每个 运行 发生变化。但是正如我所说,数据中仅有的两个 类 是 0 和 1;每个样本只有多个标签。因此,例如,一个响应 (y_train) 如下所示:

print y_train[0,:]
#[ 0.  0.  1. ...,  0.  1.  0.]

如何使用 class_weights 解决 Keras 中的多标签问题?

是的。这是 keras (issue #8011) 中的一个已知错误。基本上,keras代码假定one-hot编码,当确定类的数量时,而不是多标签序数编码。

keras/engine/training.py:

# if 2nd dimension is greater than 1, it must be one-hot encoded, 
# so let's just get the max index...
if y.shape[1] > 1:
  y_classes = y.argmax(axis=1)

我现在想不出更好的解决方法,除了设置 y_true[:, 1] = 1,即 "reserve" y 中的 1 位置始终为一个。这将导致y_classes = 1(这是二进制分类中的正确值)。

它为什么有效?y_true[i] 获取像 [0, 0, ..., 0, 1, ...] 的值时,代码会失败,其中包含一些前导零。 Keras 实现(错误地)通过最大元素的索引估计 类 的数量,结果是 j > 1 其中 y[i][j] = 1。这使得 Keras 引擎认为有超过 2 个 类,因此提供的 class_weights 是错误的。设置 y_true[i][1] = 1 确保 j <= 1(因为 np.argmax 选择最小的最大索引),这允许绕过 keras 守卫。

您可以创建一个回调,将标签的索引附加到列表中 例如:

y = [[0,1,0,1,1],[0,1,1,0,0]]

将创建一个列表:category_list = [1, 3, 4, 1, 2]

标签的每个实例都在 category_list

中统计

那么你可以使用

weighted_list = class_weight.compute_class_weight('balanced', np.unique(category_list), category_list)

然后只需将 weighted_list 转换为字典即可在 Keras 中使用。

对于多标签,我找到了两个选项:

  1. 创建多输出模型,每 1 个标签 1 个输出并通过标准 class_weight 字典
  2. 创建 weights_aware_binary_crossentropy 损失,它可以根据传递的 class_weight 字典列表和 y_true 计算掩码并执行:

K.binary_crossentropy(y_true, y_pred) * mask