簡體   English   中英

通過TensorFlow中的索引和值來操縱Tensor

[英]manipulate Tensor by indices and values in TensorFlow

需求

給定張量像:

SparseTensorValue(indices=array([[0, 0], [1, 0], [1, 1], [1, 2]]),
                  values=array([2, 0, 2, 5]),
                  dense_shape=array([2, 3]))

形狀是2x3

| 2 na na |
| 0  2  5 |

需要一個索引中具有值的新張量,如下所示:

請注意,值的總數為6([0、1、2、3、4、5]的集合),形狀為2x6

| 0 0 1 0 0 0 |
| 1 0 1 0 0 1 |

張量可以通過以下代碼創建:

SparseTensorValue(indices=array([[0, 2], [1, 0], [1, 2], [1, 5]]),
                  values=array([1, 1, 1, 1]),
                  dense_shape=array([2, 6]))

如何以TensorFlow方式進行? 以下兩種方法均無效

import tensorflow as tf

tags = tf.SparseTensor(indices=[[0, 0], [1, 0], [1, 1], [1, 2]],
                       values=[2, 0, 2, 5],
                       dense_shape=[2, 3])

print(type(tags.indices))

# approach 1:  the TensorFlow way to implement the python logic
new_indices = [[tags.indices[i], tags.values[i]]
               for i in range(tags.values.shape[0])]  # syntax incorrect

# approach 2:
indice_idx = tf.map_fn(lambda x : x[0], tags.indices)
value_idx = tf.map_fn(lambda x : x[1], tags.indices)
value_arr = tf.gather(tags.values, value_idx)

with tf.Session() as s1:
    print(indice_idx.eval())
    print(tags.values.eval())
    print('value_arr', value_arr.eval())


"""
[0 0 1 2]   <-- value_idx, which is the index of tags.values

want to combine
[0 1 1 1]   <-- indice_idx
[2 2 0 2]   <-- value_arr, which is the value of tags.values
==>
[[0,2], [1,2], [1,0], [1,2]]
"""
new_indices = tf.concat(indice_idx, value_arr)  # syntax incorrect

with tf.Session() as s:
    s.run([tf.global_variables_initializer(), tf.tables_initializer()])
    print(s.run(value_arr))
    print(s.run(tags.values))
    print(s.run(new_indices))
    print(s.run(tags.indices[3, 1]))

回答

在方法2中: new_indices = tf.stack([indice_idx, value_arr], axis=1)

完整版本的代碼是

import tensorflow as tf

tags = tf.SparseTensor(indices=[[0, 0], [1, 0], [1, 1], [1, 2]],
                       values=[2, 0, 2, 5],
                       dense_shape=[2, 3])

print(type(tags.indices))

# # approach 1:  any TensorFlow way to implement the Python logic below?
# new_indices = [[tags.indices[i], tags.values[i]]
#                for i in range(tags.values.shape[0])]  # syntax incorrect

# approach 2:
indice_idx = tf.map_fn(lambda x : x[0], tags.indices)
value_idx = tf.map_fn(lambda x : x[1], tags.indices)
value_arr = tf.cast(tf.gather(tags.values, value_idx), tf.int64)

with tf.Session() as s1:
    print(indice_idx.eval())
    print(tags.values.eval())
    print('value_arr', value_arr.eval())


"""
[0 0 1 2]   <-- value_idx, which is the index of tags.values

tf.stack does:
[0 1 1 1]   <-- indice_idx
[2 2 0 2]   <-- value_arr, which is the value of tags.values
==>
[[0,2], [1,2], [1,0], [1,2]]
"""
new_indices = tf.stack([indice_idx, value_arr], axis=1)

with tf.Session() as s:
    s.run([tf.global_variables_initializer(), tf.tables_initializer()])
    print(s.run(value_arr))
    print(s.run(tags.values))
    print(s.run(new_indices))
    print(s.run(tags.indices[3, 1]))

這個問題本身就解決了。

一個單獨的相關問題

附注:如果讀取文件,它將無法正常工作,請參閱:

通過TensorFlow中的CSV分類類別數組列創建多熱點SparseTensor

暫無
暫無

聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.

 
粵ICP備18138465號  © 2020-2024 STACKOOM.COM