Tensorflow张量值图 [英] Tensorflow tensor value map

问题描述

我的问题是如何用字典映射张量?例如像这样:

my question is how to map tensor with a dictionary? for example like this:

dict = {1:3, 2:4}
origin_tensor = tf.Variable([1,2,1], tf.int32)

字典很大.现在，如何根据 dict 制作映射选项以将张量映射到 tf.Variable([3,4,3], tf.int32) ?

The dictionary is large. Now, How can I make a map options to map the tensor to tf.Variable([3,4,3], tf.int32) according to the dict ?

另外，mapping的时候没有办法使用.eval()，可以认为origin_tensor是batch reader的标签张量.

What's more, it is no way to use .eval() when mapping, you can think the origin_tensor is a label tensor from batch reader.

推荐答案

在 Tensorflow 2.0(与未测试的早期版本的兼容性)中使用 tf.lookup:

In Tensorflow 2.0 (compatibility with earlier versions not tested) use tf.lookup:

dictionary = {1:3, 2:4}
origin_tensor = tf.Variable([1,2,1], dtype=tf.int64)

注意:dict在python中是保留的，所以用dictionary代替，dtype=tf.int32用dtype代替=tf.int64 与 tf.lookup.KeyValueTensorInitializer

note: dict is reserved in python so it is replaced with dictionary and dtype=tf.int32 is replaced with dtype=tf.int64 for compatibility with tf.lookup.KeyValueTensorInitializer

这是原始张量:

origin_tensor
>> <tf.Variable 'Variable:0' shape=(3,) dtype=int64, numpy=array([1, 2, 1])>

这是由从 Python 字典初始化的键值张量构成的 Tensorflow 查找表:

This is the Tensorflow lookup table made from a key-value tensor initialized from a python dictionary:

table = tf.lookup.StaticVocabularyTable(
        tf.lookup.KeyValueTensorInitializer(
            list(dictionary.keys()),
            list(dictionary.values()),
            key_dtype=tf.int64,
            value_dtype=tf.int64,
        ),
        num_oov_buckets=1,
    )

这是根据查找表返回具有所需元素的 result_tensor 的实际查找:

This is the actual lookup that returns the result_tensor with desired elements based on the lookup table:

result_tensor = table.lookup(origin_tensor)

结果如下:

result_tensor
>> <tf.Tensor: id=400475, shape=(3,), dtype=int64, numpy=array([3, 4, 3])>

干杯！

这篇关于Tensorflow张量值图的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！