用keras在花数据集上训练vgg，验证损失没有改变

Question

我正在使用 keras 在 VGG 网络上做一个小实验。我使用的数据集是 5 类的花卉数据集，包括玫瑰、向日葵、蒲公英、郁金香和雏菊。

有些事情我想不通：当我使用小型 CNN 网络（不是 VGG，在下面的代码中）时，它很快收敛，仅在大约 8 个 epoch 后就达到了大约 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，它输出类似：

Epoch 1/50 402/401 [==============================] - 199s 495ms/step - loss: 13.3214 - acc: 0.1713 - val_loss: 13.0144 - val_acc: 0.1926

Epoch 2/50 402/401 [==============================] - 190s 473ms/step - loss: 13.3473 - acc: 0.1719 - val_loss: 13.0144 - val_acc: 0.1926

Epoch 3/50 402/401 [==============================] - 204s 508ms/step - loss: 13.3423 - acc: 0.1722 - val_loss: 13.0144 - val_acc: 0.1926

Epoch 4/50 402/401 [==============================] - 190s 472ms/step - loss: 13.3522 - acc: 0.1716 - val_loss: 13.0144 - val_acc: 0.1926

Epoch 5/50 402/401 [==============================] - 189s 471ms/step - loss: 13.3364 - acc: 0.1726 - val_loss: 13.0144 - val_acc: 0.1926

Epoch 6/50 402/401 [==============================] - 189s 471ms/step - loss: 13.3453 - acc: 0.1720 - val_loss: 13.0144 - val_acc: 0.1926 Epoch 7/50

Epoch 7/50 402/401 [==============================] - 189s 471ms/step - loss: 13.3503 - acc: 0.1717 - val_loss: 13.0144 - val_acc: 0.1926

PS：我也用其他数据集和框架（带有 tensorflow 和 slim 的 place365 数据集）做了这个实验。结果是一样的。我查看了 VGG 论文（Simonyan&Zisserman），它说有多个阶段可以训练像 VGG 这样的深度网络，比如从阶段 A 到阶段 E 具有不同的网络结构。我不确定是否必须按照 VGG 论文中描述的方式训练我的 VGG 网络。而其他在线课程也没有提到这个复杂的培训过程。有人有什么想法吗？

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

问题已解决，我将学习率更改为 0.0001。它现在开始学习。 0.001好像不够小

用keras在花数据集上训练vgg，验证损失没有改变

training vgg on flowers dataset with keras, validation loss not changing

loss

training-data

convergence

deep-learning

keras