如何在tensorflow数组中按批次进行切片

Question

我有一个数组output和一个id subject_ids。

output = [[[1, 2, 3]], [[4, 5, 6]], [[7, 8, 9]]]
subject_ids = [[0, 1], [1, 2], [0, 2]]

ID中的数字分别表示起始位置和结束位置，然后我想根据起始位置和终止位置得到它们之间的矢量。

例如，在这种情况下，我应该得到[[1, 2, 3], [4, 5, 6]]、[[4, 5, 6], [7, 8, 9]]和[[1, 2, 3], [4, 5, 6], [7, 8, 9]]。

我该怎么办？我尝试了tf.slice和tf.gather，但似乎不起作用。

Answer 1

如果只想使用Tensorflow，请尝试将tf.gather与tf.range和tf.ragged.stack:组合使用

import tensorflow as tf
output = tf.constant([
                      [[1, 2, 3]], 
                      [[4, 5, 6]], 
                      [[7, 8, 9]]
                      ])
subject_ids = tf.constant([[0, 1], [1, 2], [0, 2]])
ragged_ouput = tf.ragged.stack([tf.gather(output, tf.range(subject_ids[i, 0], subject_ids[i, 1] + 1)) for i in tf.range(0, tf.shape(subject_ids)[0])], axis=0)
ragged_ouput = tf.squeeze(ragged_ouput, axis=2)
print(ragged_ouput)

[[[1, 2, 3], [4, 5, 6]], [[4, 5, 6], [7, 8, 9]], [[1, 2, 3], [4, 5, 6], [7, 8, 9]]]

更新1:

import tensorflow as tf
tf.config.run_functions_eagerly(True)
output = tf.constant([
                      [[1, 2, 3]], 
                      [[4, 5, 6]], 
                      [[7, 8, 9]]
                      ])
subject_ids = tf.constant([[0, 1], [1, 2], [0, 2]])
def slice_tensor(x):
  return tf.ragged.stack([tf.gather(output, tf.range(x[0], x[1] + 1))], axis=0)
ragged_ouput = tf.map_fn(slice_tensor, subject_ids, fn_output_signature=tf.RaggedTensorSpec(shape=[1, None, None, 3],
                                                                    dtype=tf.int32,
                                                                    ragged_rank=2,
                                                                    row_splits_dtype=tf.int64))
ragged_ouput = tf.squeeze(ragged_ouput, axis=1)
tf.print(ragged_ouput, summarize=-1)

[[[[1, 2, 3]], [[4, 5, 6]]], [[[4, 5, 6]], [[7, 8, 9]]], [[[1, 2, 3]], [[4, 5, 6]], [[7, 8, 9]]]]

Answer 2

只有怎么样

>>> [output[np.arange(x, y+1)] for x, y in subject_ids] 
[array([[[1, 2, 3]],
        [[4, 5, 6]]]),
        
 array([[[4, 5, 6]],
        [[7, 8, 9]]]),
        
 array([[[1, 2, 3]],
        [[4, 5, 6]],
        [[7, 8, 9]]])]