【发布时间】：2020-06-04 22:32:13
【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，但得到的数组形状为(32, 6, 6)
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 labels 的 One_Hot_Encoding，以避免标签中出现多个“1”，这些“1”不能与 softmax 一起使用。
我希望有人能给我一个提示，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 sn-p 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)
【问题讨论】：
标签： arrays machine-learning keras deep-learning multilabel-classification