"AutoTrackable"对象在Python中不可调用 [英] 'AutoTrackable' object is not callable in Python

问题描述

我的tensorflow版本是2.0

My tensorflow version is 2.0

tensorflow_hub版本为0.7

tensorflow_hub version is 0.7

python版本是3.7

python version is 3.7

我有这些代码

import tensorflow as tf
import tensorflow_hub as hub
import summarizer_data_utils

specials = ["<EOS>", "<SOS>","<PAD>","<UNK>"]
word2ind, ind2word,  missing_words = summarizer_data_utils.create_word_inds_dicts(words_counted,
                                                                       specials = specials)

#embed = hub.Module("https://tfhub.dev/google/nnlm-en-dim128/1")
embed = hub.load("https://tfhub.dev/google/Wiki-words-250/1")
emb = embed([key for key in word2ind.keys()])

我得到这个错误

Processing Time:  32.69666647911072
---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-4-aefe0bf334ec> in <module>
     84 #embed = hub.Module("https://tfhub.dev/google/nnlm-en-dim128/1")
     85 embed = hub.load("https://tfhub.dev/google/Wiki-words-250/1")
---> 86 emb = embed([key for key in word2ind.keys()])
     87 
     88 with tf.Session() as sess:

TypeError: 'AutoTrackable' object is not callable

我应该如何解决?

我找到了解决方案.我只需要更改

Edited: I have found my solution. I just need to change

https://tfhub.dev/google/Wiki-words-250/1

到

https://tfhub.dev/google/Wiki-words-250/2

推荐答案

这是TensorFlow中常见问题的一部分: https://www.tensorflow.org/hub/common_issues

This is part of the common issues in TensorFlow: https://www.tensorflow.org/hub/common_issues

解决方案是提取所需的签名，例如:

Solution is to extract the signature that you need, for example:

embed = hub.load('https://tfhub.dev/google/nnlm-en-dim128/1')
embed.signatures['default'](['my text', 'batch'])

这篇关于"AutoTrackable"对象在Python中不可调用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！