Question

我是机器学习的新手，并且正在使用一个小的数据集来训练CNN。我已经尝试过数据增强，但是不会超过75％的准确性。我想知道k折交叉验证是否可能是下一步行动。但是我不知道如何为它编写代码。

到目前为止，这是我的代码：

数据目录：

train_dir = '../input/train_images'
train_labels = pd.read_csv('../input/train.csv')
train_labels['diagnosis'] = train_labels['diagnosis'].astype(str)
train_labels["id_code"]=train_labels["id_code"].apply(lambda x:x+".png")


test_dir = '../input/test_images'
test_labels = '../input/test.csv'

预处理：

from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(rescale=1./255,)

train_generator = train_datagen.flow_from_dataframe(
    train_labels, 
    directory= train_dir,
    x_col='id_code', y_col='diagnosis', 
    target_size=(150, 150), 
    color_mode='grayscale', 
    class_mode='categorical', 
    batch_size=32, 
    shuffle=True,)

模型：

def get_model():
    model = models.Sequential()
    model.add(layers.Conv2D(32, (3,3), activation='relu', input_shape=(150,150,3)))
    model.add(layers.MaxPooling2D(2,2))
    model.add(layers.Conv2D(64, (3,3), activation='relu'))
    model.add(layers.MaxPooling2D(2,2))
    model.add(layers.Conv2D(128, (3,3), activation='relu'))
    model.add(layers.Conv2D(128, (3,3), activation='relu'))
    model.add(layers.MaxPooling2D(2,2))
    model.add(layers.Conv2D(128, (3,3), activation='relu'))
    model.add(layers.Conv2D(128, (3,3), activation='relu'))
    model.add(layers.MaxPooling2D(2,2))

    model.add(layers.Flatten())
    model.add(layers.Dropout(0.5))
    model.add(layers.Dense(512, activation='relu'))
    model.add(layers.Dense(5, activation='softmax'))

    #Compile your model
    model.compile(loss='categorical_crossentropy',
                optimizer=optimizers.Adam(),
                metrics=['acc'])

    return model

可以在以下链接中找到数据集： https://www.kaggle.com/c/aptos2019-blindness-detection/data

如何在keras中编写用于k折交叉验证的代码

0 个答案: