Python 基于CNN模型值误差的图像分类器

嗨，我一直在做一个有多个类别的图像分类器，我不断地得到这个错误

ValueError：检查目标时出错：预期密集_1具有形状（1），但获得具有形状（9）的数组

idk我做错了什么这是我的代码这在changin的分类到二进制的2类分类器上运行良好

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, Dense
from keras.layers import Activation, Dropout, Flatten, Dense
from keras.optimizers import Adam
from keras import backend as K
from PIL import ImageFile, Image
print(Image.__file__)
import numpy
import matplotlib.pyplot as plt

# dimensions of our images.
img_width, img_height = 256, 256

train_data_dir = r'C:\Users\Acer\imagerec\Mushrooms\TRAIN'
validation_data_dir = r'C:\Users\Acer\imagerec\Mushrooms\VAL'
nb_train_samples = 6714
nb_validation_samples = 6262
epochs = 20
batch_size = 30

if K.image_data_format() == 'channels_first':
    input_shape = (1, img_width, img_height)
else:
    input_shape = (img_width, img_height, 1)

from keras.applications.vgg19 import VGG19
from keras.models import Model
from keras.layers import Dense

vgg = VGG19(include_top=False, weights='imagenet', input_shape=(), pooling='avg')
x = vgg.output
x = Dense(1, activation='sigmoid')(x)
model = Model(vgg.input, x)
model.summary()

model.compile(loss='sparse_categorical_crossentropy',
              optimizer='Adam',
              metrics=['accuracy'])

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)

# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='categorical')

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='categorical')

model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=nb_validation_samples // batch_size)

from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
import seaborn as sns

test_steps_per_epoch = numpy.math.ceil(validation_generator.samples / validation_generator.batch_size)

predictions = model.predict_generator(validation_generator, steps=test_steps_per_epoch)
# Get most likely class
predicted_classes = numpy.argmax(predictions, axis=1)
true_classes = validation_generator.classes
class_labels = list(validation_generator.class_indices.keys())
report = classification_report(true_classes, predicted_classes, target_names=class_labels)
print(report)

cm=confusion_matrix(true_classes,predicted_classes)

sns.heatmap(cm, annot=True)

print(cm)

plt.show()

这里是错误

Traceback (most recent call last):
  File "C:/Users/Acer/PycharmProjects/condas/VGG19.py", line 69, in <module>
    validation_steps=nb_validation_samples // batch_size)
  File "C:\Users\Acer\Anaconda3\envs\condas\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
  File "C:\Users\Acer\Anaconda3\envs\condas\lib\site-packages\keras\engine\training.py", line 1732, in fit_generator
    initial_epoch=initial_epoch)
  File "C:\Users\Acer\Anaconda3\envs\condas\lib\site-packages\keras\engine\training_generator.py", line 220, in fit_generator
    reset_metrics=False)
  File "C:\Users\Acer\Anaconda3\envs\condas\lib\site-packages\keras\engine\training.py", line 1508, in train_on_batch
    class_weight=class_weight)
  File "C:\Users\Acer\Anaconda3\envs\condas\lib\site-packages\keras\engine\training.py", line 621, in _standardize_user_data
    exception_prefix='target')
  File "C:\Users\Acer\Anaconda3\envs\condas\lib\site-packages\keras\engine\training_utils.py", line 145, in standardize_input_data
    str(data_shape))
ValueError: Error when checking target: expected dense_1 to have shape (1,) but got array with shape (9,)

回溯（最近一次呼叫最后一次）：
文件“C:/Users/Acer/PycharmProjects/condas/VGG19.py”，第69行，在
验证\u步骤=nb\u验证\u样本//批次大小）
文件“C:\Users\Acer\Anaconda3\envs\condas\lib\site packages\keras\legacy\interfaces.py”，第91行，在包装器中
返回函数（*args，**kwargs）
文件“C:\Users\Acer\Anaconda3\envs\condas\lib\site packages\keras\engine\training.py”，第1732行，在fit\u generator中
初始_历元=初始_历元）
文件“C:\Users\Acer\Anaconda3\envs\condas\lib\site packages\keras\engine\training\u generator.py”，第220行，在fit\u generator中
重置（度量值=False）
文件“C:\Users\Acer\Anaconda3\envs\condas\lib\site packages\keras\engine\training.py”，第1508行，在批处理的列中
等级重量=等级重量）
文件“C:\Users\Acer\Anaconda3\envs\condas\lib\site packages\keras\engine\training.py”，第621行，在用户数据中
异常（前缀='target'）
文件“C:\Users\Acer\Anaconda3\envs\condas\lib\site packages\keras\engine\training\u utils.py”，第145行，标准化输入数据
str（数据形状））
ValueError:检查目标时出错：预期密集_1具有形状（1），但获得具有形状（9）的数组

您有

densite（1）

作为最后一层，它只能作为二进制分类，而

train\u data\u dir

可能有两个以上的类。将此更改为1以表示您的类数。您好，谢谢您的回复，我应该在哪里更改它？因此我将

x=densite（1，activation='sigmoid'）（x）

更改为

x=densite（9，activation='sigmoid'）（x）

相同错误

列车数据目录中有多少类？此外，由于您正在进行多类分类，您的最后一个密集层应具有激活softmax而不是sigmoid。我的train data dir上有9类