Question

代码：

#Importing the Keras libraries and packages
from keras.models import Sequential
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense
import keras.optimizers as optimizers

#Initialising the CNN
classifier = Sequential()

#Convolution Layer
classifier.add(Conv2D(32, (3, 3), input_shape = (32, 32, 3), activation = 'relu'))

#Max Pooling
classifier.add(MaxPooling2D(pool_size = (2, 2)))

#Flattening
classifier.add(Flatten())

#Full connection
classifier.add(Dense(units = 128, activation = 'relu'))
classifier.add(Dense(units = 1, activation = 'sigmoid'))

# Compiling the CNN
sgd = optimizers.SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
classifier.compile(loss='mean_squared_error', optimizer=sgd, metrics = ['accuracy'])


#Fitting the CNN to the images
from keras.preprocessing.image import ImageDataGenerator

train_datagen = ImageDataGenerator(rescale = 1./255,
                                   shear_range = 0.2,
                                   zoom_range = 0.2,
                                   horizontal_flip = True)

test_datagen = ImageDataGenerator(rescale = 1./255)

training_set = train_datagen.flow_from_directory('Oranges/training_set',
                                                 target_size = (32, 32),
                                                 batch_size = 32,
                                                 class_mode = 'binary')

test_set = test_datagen.flow_from_directory('Oranges/test_set',
                                            target_size = (32, 32),
                                            batch_size = 32,
                                            class_mode = 'binary')

classifier.fit_generator(training_set,
                         steps_per_epoch = 800,
                         epochs = 25,
                         validation_data = test_set,
                         validation_steps = 62.5)

classifier.save('my_model.h5')  # creates a HDF5 file 'my_model.h5'

输入大约是200个属于5个类别（蔬菜）的图像。虽然我让它训练整个过程（800步* 30个时期，批量大小为32），但仍然保持在18-19％左右。我试着弄乱优化器设置（lr，decay），但似乎没有什么对我有用。我有什么想法吗？

基于Keras的CNN acc在训练期间保持在1 / n％左右

0 个答案: