Keras:如何扩展validation_split以生成第三个集合，即测试集?

Question

我正在使用带有TensorFlow后端的Keras。我正在使用带有validation_split参数的图像数据生成器将数据拆分为训练集和验证集。因此，我将子集与"训练"和"测试"一起使用flow_from_directory，如下所示：

total_gen = ImageDataGenerator(validation_split=0.3)

train_gen = data_generator.flow_from_directory(my_dir, target_size=(input_size, input_size), shuffle=False, seed=13,
class_mode='categorical', batch_size=BATCH_SIZE, subset="training")
valid_gen = data_generator.flow_from_directory(my_dir, target_size=(input_size, input_size), shuffle=False, seed=13,
class_mode='categorical', batch_size=32, subset="validation")

这非常方便，因为它允许我只使用一个目录而不是两个(一个用于训练，一个用于验证(。现在我想知道是否有可能扩展此过程以生成第三个集合，即测试集？

Answer 1

这不可能开箱即用。您应该能够通过对ImageDataGenerator源代码进行一些小的修改来做到这一点：

if subset is not None:
if subset not in {'training', 'validation'}: # add a third subset here
raise ValueError('Invalid subset name:', subset,
'; expected "training" or "validation".') # adjust message
split_idx = int(len(x) * image_data_generator._validation_split) 
# you'll need two split indices here
if subset == 'validation':
x = x[:split_idx]
x_misc = [np.asarray(xx[:split_idx]) for xx in x_misc]
if y is not None:
y = y[:split_idx]
elif subset == '...' # add extra case here
else:
x = x[split_idx:]
x_misc = [np.asarray(xx[split_idx:]) for xx in x_misc] # change slicing
if y is not None:
y = y[split_idx:] # change slicing

编辑：这是修改代码的方法：

if subset is not None:
if subset not in {'training', 'validation', 'test'}:
raise ValueError('Invalid subset name:', subset,
'; expected "training" or "validation" or "test".')
split_idxs = (int(len(x) * v) for v in image_data_generator._validation_split)
if subset == 'validation':
x = x[:split_idxs[0]]
x_misc = [np.asarray(xx[:split_idxs[0]]) for xx in x_misc]
if y is not None:
y = y[:split_idxs[0]]
elif subset == 'test':
x = x[split_idxs[0]:split_idxs[1]]
x_misc = [np.asarray(xx[split_idxs[0]:split_idxs[1]]) for xx in x_misc]
if y is not None:
y = y[split_idxs[0]:split_idxs[1]]
else:
x = x[split_idxs[1]:]
x_misc = [np.asarray(xx[split_idxs[1]:]) for xx in x_misc]
if y is not None:
y = y[split_idxs[1]:]

基本上，validation_split现在预计是两个浮点数的元组，而不是单个浮点数。验证数据将是 0 到validation_split[0]之间的数据比例，validation_split[0] and validation_split[1]之间的测试数据和validation_split[1]到 1 之间的训练数据。这是您可以使用它的方式：

import keras
# keras_custom_preprocessing is how i named my directory
from keras_custom_preprocessing.image import ImageDataGenerator
generator = ImageDataGenerator(validation_split=(0.1, 0.5))
# First 10%: validation data - next 40% test data - rest: training data        
gen = generator.flow_from_directory(directory='./data/', subset='test')
# Finds 40% of the images in the dir

您将需要在两行或三行中修改文件(您必须更改类型检查(，但仅此而已，这应该有效。我有修改后的文件，如果您有兴趣，请告诉我，我可以将其托管在我的 github 上。