如何为卷积神经网络设置过滤器

Question

我正在尝试使用keras cnn构建一个多类图像分类器。我的图像输入大小是(256,256(像素。但我改用了(128,128(，因为处理(256,256(像素的图像需要很多时间。但是当我使用测试集测试网络时，尽管我在训练期间获得了 97% 的准确率，但我几乎没有获得 50% 的准确率。我认为过滤器或层数有问题。谁能解释一下如何提高我的基于 CNN 的分类器的效率。

我尝试更改纪元数，我将输入形状用作 (64,64(，但这些会产生小效果。

。enter code here

from keras.models import Sequential
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Dense
from keras.layers import Flatten
from keras.layers import Dropout
import os

classifier = Sequential()
classifier.add(Conv2D(64,(3,3), input_shape = (128,128,3), activation = "relu"))
classifier.add(Conv2D(64,(3,3), input_shape = (128,128,3), activation = "relu"))
classifier.add(Conv2D(32,(3,3), input_shape = (128,128,3), activation = "relu"))
classifier.add(Conv2D(32,(3,3), input_shape = (128,128,3), activation = "relu"))
classifier.add(MaxPooling2D(pool_size = (2,2)))

classifier.add(Flatten())
classifier.add(Dropout(0.5))
classifier.add(Dense(units= 64, activation = "relu"))
classifier.add(Dense(units= 6, activation = "softmax"))
classifier.compile(optimizer = "adam", loss = "categorical_crossentropy", metrics = ['accuracy'])

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("/home/user/Documents/final_year_project/dataset/training",
target_size = (128,128),
batch_size = 50,
class_mode="categorical")
test_set = test_datagen.flow_from_directory(
"/home/user/Documents/final_year_project/dataset/testing/",
target_size = (128,128),
batch_size = 32,
class_mode="categorical")

from IPython.display import display
from PIL import Image
classifier.fit_generator(training_set, steps_per_epoch=98, epochs=18)
target_dir = '/home/user/Documents/model'
if not os.path.exists(target_dir):
os.mkdir(target_dir)
classifier.save('/home/user/Documents/model/model.h5')
classifier.save_weights('/home/user/Documents/model/weights.h5')
print("Training Completed!!")

Answer 1

(

对我来说(你可以做一些明显的改进：

将批大小更改为 2 ** n(即 2 的 5 次方：batch_size = 32(。

input_shape仅保留给输入层(第一个卷积层(。

classifier = Sequential()
# Add extraction layers.
classifier.add(Conv2D(64,(3,3), input_shape = (128,128,3), 
               activation="relu"))
classifier.add(Conv2D(64,(3,3), activation="relu"))
classifier.add(MaxPooling2D(pool_size = (2,2)))     # <= this may help as well
classifier.add(Conv2D(32,(3,3), activation="relu"))
classifier.add(Conv2D(32,(3,3), activation="relu"))
classifier.add(MaxPooling2D(pool_size = (2,2)))
# Add classifier layers.
classifier.add(Flatten()) 
classifier.add(Dropout(0.5))        # might be too big, can try 0.2
classifier.add(Dense(units=64, activation="relu"))
classifier.add(Dense(units=6, activation="softmax"))
classifier.compile(optimizer="adam", loss="categorical_crossentropy", 
                   metrics = ['accuracy'])

最重要的是：将验证数据添加到训练中。训练：验证比率约为 80：20。

fit_generator(
    generator,              # *
    steps_per_epoch=None,   # **
    epochs=20,
    verbose=1,
    callbacks=None,
    validation_data=None,   # same format as training generator *
    validation_steps=None,  # same format as steps_per_epoch    **
    class_weight=None,
    max_queue_size=10,
    workers=1,
    use_multiprocessing=False,
    shuffle=True,
    initial_epoch=0
)