CNN模型不学习

Question

我正在构建一个 CNN 模型来对图像进行分类，但是，我猜我的模型没有学习，因为准确度和损失函数的值是恒定的。请参阅下面的代码：

构建图像训练、测试和验证数据集

import pandas as pd
from keras_preprocessing.image import ImageDataGenerator
import numpy as np

#Creating three datasets from the the 3 .txt files.
trainingfile = pd.read_table('data/training.txt', delim_whitespace=True, names=('class', 'image'))
testingfile = pd.read_table('data/testing.txt', delim_whitespace=True, names=('class', 'image'))
validationfile = pd.read_table('data/validation.txt', delim_whitespace=True, names=('class', 'image'))
#Changing target variable type
trainingfile = trainingfile.replace([0, 1, 2], ['class0', 'class1', 'class2'])
testingfile = testingfile.replace([0, 1, 2], ['class0', 'class1', 'class2'])
validationfile = validationfile.replace([0, 1, 2], ['class0', 'class1', 'class2'])

#Data augmentation
datagen=ImageDataGenerator()
train_datagen = ImageDataGenerator( 
    #Apliquem una mica de rotació no gaire ja que generalment les fotografies estaran centrades
    rotation_range=5,
    zoom_range=0.1)

#Final datasets containing the images 
train=train_datagen.flow_from_dataframe(dataframe=trainingfile, directory="data/", x_col="image", y_col="class", class_mode="categorical", target_size=(256,256),color_mode='rgb',batch_size=32)
test=datagen.flow_from_dataframe(dataframe=testingfile, directory="data/", x_col="image", y_col="class", class_mode="categorical", target_size=(256,256),color_mode='rgb',batch_size=32)
#No data augmentation to the validation dataset.
validation=datagen.flow_from_dataframe(dataframe=validationfile, directory="data/", x_col="image", y_col="class", class_mode="categorical", target_size=(256,256),color_mode='rgb', batch_size=32)

CNN 模型

from keras.models import Sequential
from keras.layers import Dense, Conv2D, Flatten, Activation, Dropout, MaxPooling2D, BatchNormalization
from keras.constraints import maxnorm

#Creació del model
model = Sequential()
#1r bloc convolució
model.add(Conv2D(32, kernel_size = (3, 3), activation='relu', input_shape=(256, 256,3)))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(BatchNormalization())
#2n bloc convolució
model.add(Conv2D(64, kernel_size=(3,3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(BatchNormalization())
#3r bloc convolució
model.add(Conv2D(64, kernel_size=(3,3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(BatchNormalization())
#4t bloc convolució
model.add(Conv2D(96, kernel_size=(3,3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(BatchNormalization())
#5e bloc convolució
model.add(Conv2D(32, kernel_size=(3,3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2,2)))
model.add(BatchNormalization())
#Dropout
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
#model.add(Dropout(0.3))
model.add(Dense(3, activation = 'softmax'))

from keras import regularizers, optimizers
from keras.optimizers import RMSprop
from keras.callbacks import EarlyStopping
# Compile model
model.compile(optimizer='adam',loss="categorical_crossentropy",metrics=["accuracy"])
# Early stopping
es = EarlyStopping(monitor='val_loss', mode='min', verbose=1,patience=10)

训练模型

h=model.fit_generator(generator=train,
                      validation_data=validation,
                      epochs=50,
                      callbacks=[es])

结果

这是我第一次使用 fit_generator，也许我没有正确使用它？

Answer 1

从结果图像中可以看出，您只训练了 1 个 epoch。这可能是因为 EarlyStopping 过于严格。尝试在 EarlyStopping 回调中添加patience=3。

es = EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=3)

编辑

过拟合示例：

查看此post 以了解有关如何处理过拟合的更多信息。