最初最原始数据为训练集文件夹50组图片和mask,测试集数据为30组图片和mask。如图总共22M
经过keras数据增强后,被扩展到惊人的32.8g
,
最后报错是:MemoryError,如下图
简单贴一下相关代码,
data_gen_args = dict(
featurewise_center=False,
featurewise_std_normalization=False,
rotation_range=10.,
width_shift_range=0.1,
height_shift_range=0.1,
horizontal_flip=True,
vertical_flip=True,
zoom_range=[1, 1.2],
fill_mode='constant',
preprocessing_function=elastic)
image_datagen = ImageDataGenerator(**data_gen_args)
mask_datagen = ImageDataGenerator(**data_gen_args)
seed = 2 #报错在这个位置
image_datagen.fit(X_train, seed=seed)
mask_datagen.fit(y_train, seed=seed)
image_generator = image_datagen.flow(X_train, batch_size=batch_size, seed=seed)
mask_generator = mask_datagen.flow(y_train, batch_size=batch_size, seed=seed)
train_generator = zip(image_generator, mask_generator)
有同学知道这个问题怎么解决吗?
来源:CSDN
作者:bingo_6
链接:https://blog.csdn.net/bingo_6/article/details/84559988