python - ValueError : logits and labels must have the same shape ((None, 6, 8, 1) vs (None, 1))

Question

我试图在实践中接触神经网络，对于这样的任务，我试图对一些图像进行分类，我基本上有两个类。因此，我以 CNN 为例，使用来自 youtube 教程的 keras 和 tensorflow。
我尝试将输出层激活更改为 sigmoid，何时更改，我开始收到错误消息:

 ValueError: logits and labels must have the same shape ((None, 6, 8, 1) vs (None, 1))

在以下行中具体给出:

validation_steps = nb_validation_Samples // batch_size)

我的神经网络代码:
图书馆

from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
import numpy as np
from keras.preprocessing import image

设置

img_width, img_height = 128, 160

train_data_dir = '/content/drive/My Drive/First-Group/Eyes/'
validation_data_dir = '/content/drive/My Drive/First-Validation-Group/'
nb_train_samples = 1300
nb_validation_Samples = 1300
epochs = 100
batch_size = 16


if K.image_data_format() == 'channels_first':
   input_shape = (3, img_width, img_height)
else:
   input_shape = (img_width, img_height, 3)

train_datagen = ImageDataGenerator(
    zoom_range=0.2,
)

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='binary')


validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode="binary")



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


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

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

model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.25))
model.add(Dense(64))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))
model.summary()

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


model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data = validation_generator,
error line -> **validation_steps = nb_validation_Samples // batch_size)**


model.save_weights('weights.npy')

Answer 1

你的网络的输入是 4d (batch_dim, height, width, channel) ，而您的目标是 2d (batch_dim, 1) .您需要网络中的某些内容从 4d 传递到 2d，例如 flatten 或 global pooling。例如，您可以在最后一个最大池化层之后添加其中一个。

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

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

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

model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten()) #<========================
model.add(Dense(64))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))

binary_crossentropy的用法作为 sigmoid 和 class_mode='binary' 的损失如果您正在处理二元分类问题，在生成器中似乎没问题