更新时间:2023-12-02 12:06:58
tfds.Split.ALL.subsplit
或 tfds.Split.TRAIN.subsplit
显然已弃用并且不再支持.
tfds.Split.ALL.subsplit
or tfds.Split.TRAIN.subsplit
apparently are deprecated and no longer supported.
一些数据集已经在训练和测试之间拆分.在这种情况下,我找到了以下解决方案(例如使用时尚 MNIST 数据集):
Some of the datasets are already split between train and test. In this case I found the following solution (using for example the fashion MNIST dataset):
splits, info = tfds.load('fashion_mnist', with_info=True, as_supervised=True,
split=['train+test[:80]','train+test[80:90]', 'train+test[90:]'],
data_dir=filePath)
(train_examples, validation_examples, test_examples) = splits