数据挖掘 - 为什么我的最小 CNN 示例显示出剧烈波动的验证损失？ - 吾爱随笔录

我在使用神经网络方面还很陌生，并且认为我犯了一些基本错误。我正在尝试将模拟图像分配给 5 个类进行测试，哪些（如果有）网络有助于解决我们小组中的大数据问题。我正在用 40000 个（256 x 256 像素灰度）图像训练 Keras 中包含的 ResNet50 CNN。虽然训练损失在第一个时期内迅速改善，但验证损失以（对我而言）相当随机的方式剧烈波动。

我正在尝试使用尽可能多的高级函数，并最终得到以下代码：

from keras.preprocessing.image import ImageDataGenerator
from keras.applications.resnet50 import ResNet50
from keras.models import Model
from keras.layers import GlobalAveragePooling2D, Dense


inputShape = (256, 256,1)
targetSize = (256, 256  )
batchSize = 128

# First, load resnet
base_model = ResNet50(include_top =False,
                weights =None,
                input_shape=inputShape)
x = base_model.output

# modified based on the article https://github.com/priya-dwivedi/
# Deep-Learning/blob/master/resnet_keras/Residual_Networks_yourself.ipynb

x = GlobalAveragePooling2D()(x)
predictions = Dense(5, activation= 'softmax')(x)
model = Model(inputs = base_model.input, outputs = predictions)


# Compile model, might want to change loss and metrics
model.compile(loss='categorical_crossentropy',
        optimizer='adam',
        metrics = ["acc"]
        )

# Define the generators to read the data. Training generator performs data argumentation as well
train_datagen = ImageDataGenerator(
        samplewise_center =True,
        samplewise_std_normalization = True,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)

test_datagen = ImageDataGenerator(
        samplewise_center =True,
        samplewise_std_normalization = True,
        )

train_generator = train_datagen.flow_from_directory(
        'trainingData/FolderBasedTrain256',
        target_size=targetSize,
        color_mode = 'grayscale',
        batch_size=batchSize,
        save_to_dir = 'trainingData/argumentedImages',
        class_mode='categorical')

validation_generator = test_datagen.flow_from_directory(
        'trainingData/FolderBasedValidation256',
        target_size=targetSize,
        batch_size=batchSize,
        color_mode = 'grayscale',
        class_mode='categorical')

# Fit the Modell, saving the history for later plotting
history = model.fit_generator(
        train_generator,
        epochs=20,
        validation_data=validation_generator,
        #steps_per_epoch = 62,
        steps_per_epoch = 31,
        #callbacks=[checkpointer],
        validation_steps=9)

我总是可以创建更多图像或训练更长时间，但对我来说，这看起来好像是某个地方出了问题。我将非常感谢任何和所有的想法。谢谢！

编辑：有人告诉我要强调验证和训练集都是由完全相同的模拟程序创建的，所以它们应该相对容易分类

EDIT2：发现错误！我的批量大小与数据量和 epoch 的步数不匹配，导致 CNN 看不到所有的训练数据。现在一切都很好地收敛，我可以评估模型的选择。感谢所有贡献者