python - 使用每个类的 ImageDataGenerator 仅使用 N 个图像

Question

有 10 个目录(标签)，每个目录(标签)有 800 张图像。我正在尝试使用迁移学习来训练我的模型。使用 ImageDataGenerator 加载数据，如下所示:

train_datagen = ImageDataGenerator(rescale=1./255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True,
    validation_split=0.2) # set validation split

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_height, img_width),
    batch_size=batch_size,
    class_mode='binary',
    subset='training') # set as training data

validation_generator = train_datagen.flow_from_directory(
    train_data_dir, # same directory as training data
    target_size=(img_height, img_width),
    batch_size=batch_size,
    class_mode='binary',
    subset='validation') # set as validation data

model.fit_generator(
    train_generator,
    steps_per_epoch = train_generator.samples // batch_size,
    validation_data = validation_generator, 
    validation_steps = validation_generator.samples // batch_size,
    epochs = nb_epochs)

是否可以使用 ImageDataGenerator 将每个目录中使用的图像数量限制为 100 个或 N 个图像，而不是所有 800 个图像？

Answer 1

def limit_data(data_dir,n=100):
    a=[]
    for i in os.listdir(data_dir):
        for k,j in enumerate(os.listdir(data_dir+'/'+i)):
            if k>n:continue
            a.append((f'{data_dir}/{i}/{j}',i))
    return pd.DataFrame(a,columns=['filename','class'])

然后使用 flow_from_dataframe method