问Tensorflow NIH胸部X光CNN验证准确性即使使用正则化也不会提高

EN

def create_model(settings):
    """
    Create a basic model
    """
    # create model
    model = tf.keras.models.Sequential()
    model.add(layers.Input((224, 224, 1)))
    # block 1
    model.add(layers.Conv2D(64, (3, 3), activation='relu', padding='same', kernel_initializer='he_uniform', use_bias=True, name='block1_conv'))
    model.add(layers.MaxPool2D((2, 2), strides=(2, 2), name='block1_pool'))
    # block 2
    model.add(layers.Conv2D(96, (3, 3), activation='relu', padding='same', kernel_initializer='he_uniform', use_bias=True, name='block2_conv'))
    model.add(layers.MaxPool2D((2, 2), strides=(2, 2), name='block2_pool'))
    # block 3
    model.add(layers.Conv2D(192, (3, 3), activation='relu', padding='same', kernel_initializer='he_uniform', use_bias=True, name='block3_conv1'))
    model.add(layers.Conv2D(192, (3, 3), activation='relu', padding='same', kernel_initializer='he_uniform', use_bias=True, name='block3_conv2'))
    model.add(layers.MaxPool2D((2, 2), strides=(2, 2), name='block3_pool'))
    # block 4
    model.add(layers.Conv2D(384, (3, 3), activation='relu', padding='same', kernel_initializer='he_uniform', use_bias=True, name='block4_conv1'))
    model.add(layers.Conv2D(384, (3, 3), activation='relu', padding='same', kernel_initializer='he_uniform', use_bias=True, name='block4_conv2'))
    model.add(layers.Conv2D(384, (3, 3), activation='relu', padding='same', kernel_initializer='he_uniform', use_bias=True, name='block4_conv3'))
    model.add(layers.MaxPool2D((2, 2), strides=(2, 2), name='block4_pool'))
    # block 5
    model.add(layers.Conv2D(512, (3, 3), activation='relu', padding='same', kernel_initializer='he_uniform', use_bias=True, name='block5_conv1'))
    model.add(layers.Conv2D(512, (3, 3), activation='relu', padding='same', kernel_initializer='he_uniform', use_bias=True, name='block5_conv2'))
    model.add(layers.Conv2D(512, (3, 3), activation='relu', padding='same', kernel_initializer='he_uniform', use_bias=True, name='block5_conv3'))
    model.add(layers.MaxPool2D((2, 2), strides=(2, 2), name='block5_pool'))
    # fully connected
    model.add(layers.GlobalAveragePooling2D(name='fc_pool'))   
    model.add(layers.Dropout(0.3, name='fc_dropout'))
    model.add(layers.Dense(1, activation='sigmoid', name='fc_output'))
    
    # compile model
    model.compile(
        optimizers.SGD(
            learning_rate=settings["lr_init"],
            momentum=settings["momentum"],
        ),
        loss='binary_crossentropy',
        metrics=[
            'accuracy',
            metrics.Precision(),
            metrics.Recall(),
            metrics.AUC()
        ]
    )
    model.summary()
    return model



def configure_callbacks(settings):
    """
    Create a list of callback objects
    """
    # tensorboard
    log_dir = "logs/fit/" + datetime.datetime.now().strftime("%Y%m%d-%H%M%S")
    tensorboard_callback = callbacks.TensorBoard(log_dir=log_dir, histogram_freq=1)
    
    # learning rate reduction on plateau
    lrreduce_callback = callbacks.ReduceLROnPlateau(
        monitor='val_loss',
        factor=settings["lr_factor"],
        patience=settings["lr_patience"],
        min_lr=settings["lr_min"],
        verbose=1,
    )
    
    # save model
    checkpoint_callback = callbacks.ModelCheckpoint(
        filepath="saves/" + settings["modelname"] + "/cp-{epoch:03d}",
        monitor='val_accuracy',
        mode='max',
        save_weights_only=True,
        save_best_only=True,
        verbose=1,
    )
    return [tensorboard_callback, lrreduce_callback, checkpoint_callback]



def get_data(settings):
    """ 
    Create a generator that will be used for training
    """
    df=pd.read_csv("dataset/y_train_binary.csv")
    columns = [
        "Abnormal"
    ]
    datagen = ImageDataGenerator(
        rescale=1./255.,
        rotation_range=5,
        brightness_range=(0.9, 1.1),
        zoom_range=(1,  1.1),
    )
    # 94.983% for training (106496 = 64*6656)
    traindata = datagen.flow_from_dataframe(
        dataframe=df[:NTRAIN],
        directory="dataset/images",
        x_col="Image Index",
        y_col=columns,
        color_mode='grayscale',
        batch_size=settings["batchsize"],
        class_mode="raw",
        target_size=(224,224),
        shuffle=True,
    )
    # 5.017% for testing (5624)
    testdata = datagen.flow_from_dataframe(
        dataframe=df[NTRAIN:],
        directory="dataset/images",
        x_col="Image Index",
        y_col=columns,
        color_mode='grayscale',
        batch_size=settings["batchsize"],
        class_mode="raw",
        target_size=(224,224),
        shuffle=True,
    )
    return (traindata, testdata)



def newtrain(settings):
    """
    Create a new model "(modelname)" and train for (epoch) epochs
    """
    model = create_model(settings)
    callbacks = configure_callbacks(settings)
    traindata, testdata = get_data(settings)
    
    # train
    model.fit(
        x=traindata,
        epochs=settings["epoch"],
        validation_data=testdata,
        callbacks=callbacks,
        verbose=1,
    )
    model.save_weights(f"saves/{settings['modelname']}/cp-{settings['epoch']:03d}")