python - 在 Keras 中使用 MobileV2 一开始验证损失无法改善

Question

我为我的案例使用了两种不同的模型。案例是对不同类型表面缺陷的分类。输入形状为 (200, 200, 1)，共有 6 个类。训练数据数为1440（1类240），验证数据数为360（1类60）。

第一个模型的训练过程非常好。训练损失和验证损失都在迅速下降。之后，我想使用 keras 的 MobileNetV2 来比较训练结果。MobileV2 中的训练损失和准确率有所提高，但验证准确率停留在 0.1667（损失比较坎坷）。

我想知道是什么导致了这个结果，我可以把这种情况称为“过度拟合”吗？或者只是这个模型对我来说太深了？

第一个模型：

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

input_shape = (parameter.IMAGE_SIZE_Y, parameter.IMAGE_SIZE_X, parameter.channel)

def MyModel():    

    model = Sequential()

    model.add(Conv2D(16, (3, 3), input_shape = input_shape, padding='same', activation='relu'))

    model.add(MaxPooling2D(pool_size = (2, 2), strides = (2, 2)))

    model.add(Conv2D(32, (3, 3), padding='same', activation='relu'))

    model.add(MaxPooling2D(pool_size = (2, 2), strides = (2, 2)))

    model.add(Conv2D(64, (3, 3), padding='same', activation='relu'))

    model.add(MaxPooling2D(pool_size = (2, 2), strides = (2, 2)))

    model.add(Conv2D(128, (3, 3), padding='same', activation='relu'))

    model.add(MaxPooling2D(pool_size = (2, 2), strides = (2, 2)))

    model.add(Flatten())   

    model.add(Dense(256, activation = 'relu'))

    model.add(Dropout(0.5))

    model.add(Dense(6, activation = 'softmax'))

    model.summary()

    return model

第二种型号：

from keras.models import Sequential, Model
from keras.layers import Dense, Activation, Dropout, Flatten, Conv2D, MaxPooling2D, BatchNormalization, GlobalAveragePooling2D
from keras.optimizers import Adam
from keras.applications import MobileNetV2
import parameter

def MyMobileNetV2():

    input_shape = (parameter.IMAGE_SIZE_X, parameter.IMAGE_SIZE_Y, parameter.channel)

    model = MobileNetV2(input_shape = input_shape,
                        include_top = False,
                        weights = 'imagenet')

    x = model.output
    x = GlobalAveragePooling2D()(x)
    x = BatchNormalization()(x)
    x = Dense(1280, activation='relu')(x)
    x = BatchNormalization()(x)
    predictions = Dense(6, activation='softmax', kernel_initializer='random_uniform', bias_initializer='zeros')(x)

    model = Model(inputs = model.input, outputs = predictions)

    optimizer = Adam(lr=0.01)

    loss = "categorical_crossentropy"

    for layer in model.layers:
        layer.trainable = True

    model.compile(optimizer=optimizer,    
                  loss=loss,
                  metrics=["accuracy"])

    model.summary()

    for i, layer in enumerate(model.layers):
        print(i, layer.name, layer.trainable)



    return model

标签： pythontensorflowmachine-learningkerasdeep-learning