使用keras在花卉数据集上训练vgg，验证损失不变

Question

我和keras在VGG网络上做了一个小实验。我使用的数据集是花卉数据集，有5个类，包括玫瑰、向日葵、蒲公英、郁金香和雏菊。

有一点我想不通:当我使用一个小的CNN网络(不是VGG，在下面的代码中)时，它收敛很快，仅经过大约8个周期就达到了大约75%的验证准确率。

然后我切换到VGG网络（代码中注释掉的区域）。网络的损失和准确性根本没有改变，它输出如下内容：

纪元1/50 402/401 [==============================] - 199s 495ms/步进-损耗： 13.3214-acc： 0.1713-val_loss： 13.0144-val_acc： 0.1926

纪元2/50 402/401 [==============================] - 20世纪初473ms/步进-损失： 13.3473-acc： 0.1719-val_loss： 13.0144-val_acc： 0.1926

纪元3/50 402/401[=======================]-204s 508ms/步-损耗：13.3423-acc:0.1722-val_loss:13.0144-val-acc:0.1926

新纪元4/50 402/401[=======================]-190s 472ms/步-损耗：13.3522-acc:0.1716-val_loss:13.0144-val-acc:0.1926

Epoch 5/50 402/401 [================================================] - 189秒 471毫秒/步 - 损耗： 13.3364 - 截至： 0.1726 - val_loss： 13.0144 - val_acc： 0.1926

纪元6/50 402/401 [==============================] - 189s 471毫秒/步-损失： 13.3453-acc： 0.1720-val_loss： 13.0144-val_acc： 0.1926纪元7/50

新纪元7/50 402/401[=======================]-189s 471ms/步-损耗：13.3503-acc:0.1717-val_损耗：13-0144-val-acc:0.1926

PS：我也用其他数据集和框架做了这个实验（具有张量流和瘦的place365数据集）。结果是一样的。我研究了VGG论文（西蒙尼扬

我的代码：

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


# dimensions of our images.
img_width, img_height = 224, 224

train_data_dir = './data/train'
validation_data_dir = './data/val'
nb_train_samples = 3213
nb_validation_samples = 457
epochs = 50
batch_size = 8

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

# random cnn model: 
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(64, (3, 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(Dropout(0.5))
model.add(Dense(5))
model.add(Activation('softmax'))

# vgg model:
'''model = Sequential([
    Conv2D(64, (3, 3), input_shape=input_shape, padding='same',
           activation='relu'),
    Conv2D(64, (3, 3), activation='relu', padding='same'),
    MaxPooling2D(pool_size=(2, 2), strides=(2, 2)),
    Conv2D(128, (3, 3), activation='relu', padding='same'),
    Conv2D(128, (3, 3), activation='relu', padding='same',),
    MaxPooling2D(pool_size=(2, 2), strides=(2, 2)),
    Conv2D(256, (3, 3), activation='relu', padding='same',),
    Conv2D(256, (3, 3), activation='relu', padding='same',),
    Conv2D(256, (3, 3), activation='relu', padding='same',),
    MaxPooling2D(pool_size=(2, 2), strides=(2, 2)),
    Conv2D(512, (3, 3), activation='relu', padding='same',),
    Conv2D(512, (3, 3), activation='relu', padding='same',),
    Conv2D(512, (3, 3), activation='relu', padding='same',),
    MaxPooling2D(pool_size=(2, 2), strides=(2, 2)),
    Conv2D(512, (3, 3), activation='relu', padding='same',),
    Conv2D(512, (3, 3), activation='relu', padding='same',),
    Conv2D(512, (3, 3), activation='relu', padding='same',),
    MaxPooling2D(pool_size=(2, 2), strides=(2, 2)),
    Flatten(),
    Dense(256, activation='relu'),
    Dense(256, activation='relu'),
    Dense(5, activation='softmax')
])'''


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

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

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)

model.save_weights('flowers.h5')

Answer 1

问题解决了，我把学习率改成了0.0001。它现在开始学习。似乎0.001还不够小。