带有 featurewise_center 的 ImageDataGenerator() 上的 Keras fit() 验证准确性较差

Question

我有一个关于在 ImageDataGenerator 上使用 fit() 的问题。我使用 Dense 层成功地批量运行了 MNIST 测试。
以下代码完美运行（验证准确率 98.5%）。

加载

(X_train, y_train), (X_test, y_test) = mnist.load_data()
# separate data into train and validation
from sklearn.model_selection import train_test_split
# Split the data
valid_per = 0.15
X_train, X_valid, y_train, y_valid = train_test_split(X_train, y_train, test_size=valid_per, shuffle= True)

N1 = X_train.shape[0] # training size
N2 = X_test.shape[0] # test size
N3 = X_valid.shape[0] # valid size
h = X_train.shape[1]
w = X_train.shape[2]


num_pixels = h*w
# reshape N1 samples to num_pixels
#x_train = X_train.reshape(N1, num_pixels).astype('float32') # shape is now (51000,784)
#x_test = X_test.reshape(N2, num_pixels).astype('float32') # shape is now (9000,784)


y_train = np_utils.to_categorical(y_train) #(51000,10): 10000 lables for 10 classes
y_valid = np_utils.to_categorical(y_valid) #(9000,10): 9000 labels for 10 classes
y_test = np_utils.to_categorical(y_test) # (10000,10): 10000 lables for 10 classes

num_classes = y_test.shape[1]

def baseline_model():
# create model
 model = Sequential()
 # flatten input to (N1,w*h) as fit_generator expects (N1,w*h), but dont' have x,y as inputs(so cant reshape)
 model.add(Flatten(input_shape=(h,w,1)))
 model.add(Dense(num_pixels, input_dim=num_pixels, kernel_initializer='normal', activation='relu'))
 # Define output layer with softmax function
 model.add(Dense(num_classes, kernel_initializer='normal', activation='softmax'))
 model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
 return model

model = baseline_model()
model.summary()

batch_size = 200
epochs = 20
steps_per_epoch_tr = int(N1/ batch_size) # 51000/200
steps_per_epoch_val = int(N3/batch_size) 

# reshape to be [samples][width][height][ channel] for ImageData Gnerator->datagen.flow
x_t = X_train.reshape(N1, w, h, 1).astype('float32')
x_v = X_valid.reshape(N3, w, h, 1).astype('float32')

# define data preparation
#datagen = ImageDataGenerator(rescale=1./255,featurewise_center= True,featurewise_std_normalization=True,width_shift_range=0.1,height_shift_range=0.1) # scales x_t
datagen = ImageDataGenerator(rescale=1./255,width_shift_range=0.1,height_shift_range=0.1) # scales x_t
#datagen.fit(x_t)
#datagen.fit(x_v)
train_gen = datagen.flow(x_t, y_train, batch_size=batch_size)
valid_gen = datagen.flow(x_v,y_valid, batch_size=batch_size)

model.fit_generator(train_gen,steps_per_epoch = steps_per_epoch_tr,validation_data = valid_gen,
 validation_steps = steps_per_epoch_val,epochs=epochs)

现在，如果我注释掉第 53 行，并取消注释第 52、54 和 55 行，我会得到 1% 的验证准确度。所以，这给出了很差的准确性：

datagen = ImageDataGenerator(rescale=1./255,featurewise_center= True,featurewise_std_normalization=True,width_shift_range=0.1,height_shift_range=0.1) # scales x_t
##datagen = ImageDataGenerator(rescale=1./255,width_shift_range=0.1,height_shift_range=0.1) # scales x_t
datagen.fit(x_t)
datagen.fit(x_v)

如果我取消注释第 52 行，但保留注释掉第 54,55 行，则准确率再次为 98.5%，

datagen = ImageDataGenerator(rescale=1./255,featurewise_center= True,featurewise_std_normalization=True,width_shift_range=0.1,height_shift_range=0.1) # scales x_t
##datagen = ImageDataGenerator(rescale=1./255,width_shift_range=0.1,height_shift_range=0.1) # scales x_t
#datagen.fit(x_t)
#datagen.fit(x_v)

但是根据 Keras 文档，如果我们使用 featurewise_center，我们需要第 54 和 55 行。

所以，我很困惑出了什么问题。

Answer 1

您已经使用了重新缩放和特征标准化，这是问题的原因。在进行 feature_normalization 时不要使用重新缩放。这会导致网络的所有输入值为负。从 ImageDataGenerator 中删除“rescale=1./255”。

datagen = ImageDataGenerator(featurewise_center= True,featurewise_std_normalization=True,width_shift_range=0.1,height_shift_range=0.1) # scales x_t
datagen.fit(x_t)

此外，使用单独的 ImageDataGenerators 进行训练和验证，因为数据增强通常只针对训练数据进行。并且，均值/标准是在训练数据上计算的，并应用于验证/测试数据。

像这样：

x_v = (x_v - datagen.mean)/(datagen.std + 1e-6)
datagen_valid = ImageDataGenerator(...)
valid_gen = datagen_valid.flow(x_v, y_valid, batch_size=batch_size)