我正在尝试实际操作神经网络，为此任务我正在尝试对一些图像进行分类，基本上我有两个类别。因此，我从YouTube上的教程中以Keras和TensorFlow的CNN为例。
当我尝试将输出层的激活函数改为sigmoid时，我开始收到以下错误：
ValueError: logits and labels must have the same shape ((None, 6, 8, 1) vs (None, 1))具体在以下这行代码中出现：
validation_steps = nb_validation_Samples // batch_size)我的神经网络代码如下：
库
from keras.preprocessing.image import ImageDataGeneratorfrom keras.models import Sequentialfrom keras.layers import Conv2D, MaxPooling2Dfrom keras.layers import Activation, Dropout, Flatten, Densefrom keras import backend as Kimport numpy as npfrom keras.preprocessing import image设置
img_width, img_height = 128, 160train_data_dir = '/content/drive/My Drive/First-Group/Eyes/'validation_data_dir = '/content/drive/My Drive/First-Validation-Group/'nb_train_samples = 1300nb_validation_Samples = 1300epochs = 100batch_size = 16if 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')回答：
你的网络输入是4维的(batch_dim, height, width, channel)，而你的目标是2维的(batch_dim, 1)。你需要在网络中添加一些东西来从4维转换到2维，比如Flatten或全局池化。例如，你可以在最后一个最大池化层之后添加其中之一。
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'))如果你是处理二分类问题，使用binary_crossentropy作为损失函数，sigmoid作为激活函数，以及生成器中的class_mode='binary'似乎是没问题的
