在 tensorflow 中使用迭代器生成特征和标签

Question

我有一个包含特征和标签的数据集。我想从中产生三样东西：

x,y,lb = train_data 

我的train_data具有索引中的特征和标签，比如0 to 100。我希望x 有来自1 to 100 的feature 样本，y 应该有来自0 to 99 的labels 和lb 应该有索引100 的标签。

此外，我想使用迭代器在滑动批次中执行此操作。目前我有以下代码从0 to 100和y从0 to 100生成x。下一批从x : 1 to 101和y:1 to 101开始，以此类推。

features_placeholder = tf.placeholder(tf.float32, shape=[None,None],name="input_features")
labels_placeholder = tf.placeholder(tf.float32, shape=[None,1],name = "input_labels")

iterator = (tf.data.Dataset.from_tensor_slices((features_placeholder, labels_placeholder))
           .apply(sliding.sliding_window_batch(timestep=100, stride=1))
           .batch(10)
           .make_initializable_iterator()
           )
next_element = iterator.get_next(name="batch")
init_op = iterator.initializer
saveable = tf.contrib.data.make_saveable_from_iterator(iterator)

Answer 1

您可以只拥有 101 个元素的窗口，然后再进行相应的切片：

import tensorflow as tf
from tensorflow.contrib.data.python.ops import sliding

features_placeholder = tf.placeholder(tf.float32, shape=[1000, 10],name="input_features")
labels_placeholder = tf.placeholder(tf.float32, shape=[1000, 1],name = "input_labels")
iterator = (tf.data.Dataset.from_tensor_slices((features_placeholder, labels_placeholder))
           .apply(sliding.sliding_window_batch(window_size=101, window_shift=1))
           .batch(10)
           .make_initializable_iterator()
           )
x_it, y_it = iterator.get_next(name="batch")
x, y, lb = x_it[:, 1:], y_it[:, :-1], y_it[:, -1]
init_op = iterator.initializer
saveable = tf.contrib.data.make_saveable_from_iterator(iterator)