arrays - 如何为 KERAS 多标签问题提供 DataGenerator？

问题描述

我正在使用 KERAS 解决多标签分类问题。当我执行这样的代码时，出现以下错误：

ValueError：检查目标时出错：预期 activation_19 有 2 维，但得到了形状为 (32, 6, 6) 的数组

这是因为我的标签字典中的列表充满了“0”和“1”，正如我最近了解到的那样，它们在 return 语句中不适合 keras.utils.to_categorical。softmax 也不能处理多个“1”。

我想我首先需要一个 Label_Encoder，然后是 One_Hot_Encoding for labels，以避免标签中出现多个“1”，这与 softmax 不一起使用。

我希望有人能给我提示如何预处理或转换标签数据，以修复代码。我会很感激。即使是代码片段也会很棒。

csv 看起来像这样：

Filename  label1  label2  label3  label4  ...   ID
abc1.jpg    1       0       0       1     ...  id-1
def2.jpg    0       1       0       1     ...  id-2
ghi3.jpg    0       0       0       1     ...  id-3
...

import numpy as np
import keras
from keras.layers import *
from keras.models import Sequential

class DataGenerator(keras.utils.Sequence):
    'Generates data for Keras'
    def __init__(self, list_IDs, labels, batch_size=32, dim=(224,224), n_channels=3,
                 n_classes=21, shuffle=True):
        'Initialization'
        self.dim = dim
        self.batch_size = batch_size
        self.labels = labels
        self.list_IDs = list_IDs
        self.n_channels = n_channels
        self.n_classes = n_classes
        self.shuffle = shuffle
        self.on_epoch_end()


    def __getitem__(self, index):
        'Generate one batch of data'
        # Generate indexes of the batch
        indexes = self.indexes[index*self.batch_size:(index+1)*self.batch_size]

        # Find list of IDs
        list_IDs_temp = [self.list_IDs[k] for k in indexes]

        # Generate data
        X, y = self.__data_generation(list_IDs_temp)

        return X, y

    def on_epoch_end(self):
        'Updates indexes after each epoch'
        self.indexes = np.arange(len(self.list_IDs))
        if self.shuffle == True:
            np.random.shuffle(self.indexes)

    def __data_generation(self, list_IDs_temp):
        'Generates data containing batch_size samples' # X : (n_samples, *dim, n_channels)
        # Initialization
        X = np.empty((self.batch_size, *self.dim, self.n_channels))
        y = np.empty((self.batch_size, self.n_classes), dtype=int)

        # Generate data
        for i, ID in enumerate(list_IDs_temp):
            # Store sample
            X[i,] = np.load('Folder with npy files/' + ID + '.npy')

            # Store class
            y[i] = self.labels[ID]

        return X, keras.utils.to_categorical(y, num_classes=self.n_classes)

-----------------------

# Parameters
params = {'dim': (224, 224),
          'batch_size': 32,
          'n_classes': 21,
          'n_channels': 3,
          'shuffle': True}

# Datasets
partition = partition
labels = labels

# Generators
training_generator = DataGenerator(partition['train'], labels, **params)
validation_generator = DataGenerator(partition['validation'], labels, **params)

# Design model
model = Sequential()

model.add(Conv2D(32, (3,3), input_shape=(224, 224, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2)))

...

model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dense(21))
model.add(Activation('softmax'))

model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])

# Train model on dataset
model.fit_generator(generator=training_generator,
                    validation_data=validation_generator)

标签： arraysmachine-learningkerasdeep-learningmultilabel-classification

arrays - 如何为 KERAS 多标签问题提供 DataGenerator？

问题描述

解决方案

推荐阅读