时间戳

首页 > 解决方案 > TensorFlow | 如何实现 10 倍交叉验证？

python - TensorFlow | 如何实现 10 倍交叉验证？

问题描述

我如何在这段代码中实现 10 折交叉验证？

(train_ds, val_ds, test_ds), metadata = tfds.load(
    'tf_flowers',
    split=['train[:60%]', 'train[60%:90%]', 'train[90%:]'],
    with_info=True,
    as_supervised=True)

附言

也许我做了 10 倍交叉验证，但我不确定。

(train_ds, test_ds), metadata = tfds.load(
    'tf_flowers',
    split=['train[:90%]', 'train[90%:]'],
    with_info=True,
    as_supervised=True
)

val_ds = train_ds.split = [
  f'train[{k}%:{k+10}%]' for k in range(0, 100, 10)
]

标签： pythontensorflowkerasdeep-learningconv-neural-network

解决方案

对我有什么帮助！

(train_ds, test_ds), metadata = tfds.load(
    'tf_flowers',
    split=['train[:90%]', 'train[90%:]'],
    with_info=True,
    as_supervised=True
)

val_ds = train_ds.split = [
  f'train[{k}%:{k+10}%]' for k in range(0, 100, 10)
]

推荐阅读